diff --git a/ros2_ws/src/yolov3_ros/launch/pipe_detection.launch.py b/ros2_ws/src/yolov3_ros/launch/pipe_detection.launch.py
new file mode 100644
index 00000000..cd028590
--- /dev/null
+++ b/ros2_ws/src/yolov3_ros/launch/pipe_detection.launch.py
@@ -0,0 +1,25 @@
+
+from launch import LaunchDescription
+from launch.actions import DeclareLaunchArgument, SetEnvironmentVariable
+from launch.substitutions import LaunchConfiguration
+from launch_ros.actions import Node
+
+def generate_launch_description():
+
+ return LaunchDescription([
+
+ # Launch arguments
+ DeclareLaunchArgument('best_weights', default_value='src/pipe_weights.pt', description='Path to best weights file (.pt)'),
+
+ # Nodes to launch
+ Node(
+ package='yolov3_ros', executable='yolov3_ros_node', output='screen',
+ parameters=[{
+ 'best_weights':LaunchConfiguration('best_weights'),
+ }],
+ # remappings=[
+ # ('rgb_img', LaunchConfiguration('rgb_topic')),
+ # ('depth_img', LaunchConfiguration('depth_topic')),
+ # ('camera_info', LaunchConfiguration('camera_info_topic'))]
+ ),
+ ])
diff --git a/ros2_ws/src/yolov3_ros/models/__init__.py b/ros2_ws/src/yolov3_ros/models/__init__.py
new file mode 100644
index 00000000..e69de29b
diff --git a/ros2_ws/src/yolov3_ros/models/__pycache__/__init__.cpython-310.pyc b/ros2_ws/src/yolov3_ros/models/__pycache__/__init__.cpython-310.pyc
new file mode 100644
index 00000000..52d0fe19
Binary files /dev/null and b/ros2_ws/src/yolov3_ros/models/__pycache__/__init__.cpython-310.pyc differ
diff --git a/ros2_ws/src/yolov3_ros/models/__pycache__/common.cpython-310.pyc b/ros2_ws/src/yolov3_ros/models/__pycache__/common.cpython-310.pyc
new file mode 100644
index 00000000..3af1ff61
Binary files /dev/null and b/ros2_ws/src/yolov3_ros/models/__pycache__/common.cpython-310.pyc differ
diff --git a/ros2_ws/src/yolov3_ros/models/__pycache__/experimental.cpython-310.pyc b/ros2_ws/src/yolov3_ros/models/__pycache__/experimental.cpython-310.pyc
new file mode 100644
index 00000000..377e1bc8
Binary files /dev/null and b/ros2_ws/src/yolov3_ros/models/__pycache__/experimental.cpython-310.pyc differ
diff --git a/ros2_ws/src/yolov3_ros/models/__pycache__/yolo.cpython-310.pyc b/ros2_ws/src/yolov3_ros/models/__pycache__/yolo.cpython-310.pyc
new file mode 100644
index 00000000..9386372f
Binary files /dev/null and b/ros2_ws/src/yolov3_ros/models/__pycache__/yolo.cpython-310.pyc differ
diff --git a/ros2_ws/src/yolov3_ros/models/common.py b/ros2_ws/src/yolov3_ros/models/common.py
new file mode 100644
index 00000000..a76fc628
--- /dev/null
+++ b/ros2_ws/src/yolov3_ros/models/common.py
@@ -0,0 +1,593 @@
+# YOLOv3 🚀 by Ultralytics, GPL-3.0 license
+"""
+Common modules
+"""
+
+import json
+import math
+import platform
+import warnings
+from copy import copy
+from pathlib import Path
+
+import cv2
+import numpy as np
+import pandas as pd
+import requests
+import torch
+import torch.nn as nn
+from PIL import Image
+from torch.cuda import amp
+
+from utils.datasets import exif_transpose, letterbox
+from utils.general import (LOGGER, check_requirements, check_suffix, colorstr, increment_path, make_divisible,
+ non_max_suppression, scale_coords, xywh2xyxy, xyxy2xywh)
+from utils.plots import Annotator, colors, save_one_box
+from utils.torch_utils import time_sync
+
+
+def autopad(k, p=None): # kernel, padding
+ # Pad to 'same'
+ if p is None:
+ p = k // 2 if isinstance(k, int) else [x // 2 for x in k] # auto-pad
+ return p
+
+
+class Conv(nn.Module):
+ # Standard convolution
+ def __init__(self, c1, c2, k=1, s=1, p=None, g=1, act=True): # ch_in, ch_out, kernel, stride, padding, groups
+ super().__init__()
+ self.conv = nn.Conv2d(c1, c2, k, s, autopad(k, p), groups=g, bias=False)
+ self.bn = nn.BatchNorm2d(c2)
+ self.act = nn.SiLU() if act is True else (act if isinstance(act, nn.Module) else nn.Identity())
+
+ def forward(self, x):
+ return self.act(self.bn(self.conv(x)))
+
+ def forward_fuse(self, x):
+ return self.act(self.conv(x))
+
+
+class DWConv(Conv):
+ # Depth-wise convolution class
+ def __init__(self, c1, c2, k=1, s=1, act=True): # ch_in, ch_out, kernel, stride, padding, groups
+ super().__init__(c1, c2, k, s, g=math.gcd(c1, c2), act=act)
+
+
+class TransformerLayer(nn.Module):
+ # Transformer layer https://arxiv.org/abs/2010.11929 (LayerNorm layers removed for better performance)
+ def __init__(self, c, num_heads):
+ super().__init__()
+ self.q = nn.Linear(c, c, bias=False)
+ self.k = nn.Linear(c, c, bias=False)
+ self.v = nn.Linear(c, c, bias=False)
+ self.ma = nn.MultiheadAttention(embed_dim=c, num_heads=num_heads)
+ self.fc1 = nn.Linear(c, c, bias=False)
+ self.fc2 = nn.Linear(c, c, bias=False)
+
+ def forward(self, x):
+ x = self.ma(self.q(x), self.k(x), self.v(x))[0] + x
+ x = self.fc2(self.fc1(x)) + x
+ return x
+
+
+class TransformerBlock(nn.Module):
+ # Vision Transformer https://arxiv.org/abs/2010.11929
+ def __init__(self, c1, c2, num_heads, num_layers):
+ super().__init__()
+ self.conv = None
+ if c1 != c2:
+ self.conv = Conv(c1, c2)
+ self.linear = nn.Linear(c2, c2) # learnable position embedding
+ self.tr = nn.Sequential(*(TransformerLayer(c2, num_heads) for _ in range(num_layers)))
+ self.c2 = c2
+
+ def forward(self, x):
+ if self.conv is not None:
+ x = self.conv(x)
+ b, _, w, h = x.shape
+ p = x.flatten(2).unsqueeze(0).transpose(0, 3).squeeze(3)
+ return self.tr(p + self.linear(p)).unsqueeze(3).transpose(0, 3).reshape(b, self.c2, w, h)
+
+
+class Bottleneck(nn.Module):
+ # Standard bottleneck
+ def __init__(self, c1, c2, shortcut=True, g=1, e=0.5): # ch_in, ch_out, shortcut, groups, expansion
+ super().__init__()
+ c_ = int(c2 * e) # hidden channels
+ self.cv1 = Conv(c1, c_, 1, 1)
+ self.cv2 = Conv(c_, c2, 3, 1, g=g)
+ self.add = shortcut and c1 == c2
+
+ def forward(self, x):
+ return x + self.cv2(self.cv1(x)) if self.add else self.cv2(self.cv1(x))
+
+
+class BottleneckCSP(nn.Module):
+ # CSP Bottleneck https://github.com/WongKinYiu/CrossStagePartialNetworks
+ def __init__(self, c1, c2, n=1, shortcut=True, g=1, e=0.5): # ch_in, ch_out, number, shortcut, groups, expansion
+ super().__init__()
+ c_ = int(c2 * e) # hidden channels
+ self.cv1 = Conv(c1, c_, 1, 1)
+ self.cv2 = nn.Conv2d(c1, c_, 1, 1, bias=False)
+ self.cv3 = nn.Conv2d(c_, c_, 1, 1, bias=False)
+ self.cv4 = Conv(2 * c_, c2, 1, 1)
+ self.bn = nn.BatchNorm2d(2 * c_) # applied to cat(cv2, cv3)
+ self.act = nn.SiLU()
+ self.m = nn.Sequential(*(Bottleneck(c_, c_, shortcut, g, e=1.0) for _ in range(n)))
+
+ def forward(self, x):
+ y1 = self.cv3(self.m(self.cv1(x)))
+ y2 = self.cv2(x)
+ return self.cv4(self.act(self.bn(torch.cat((y1, y2), dim=1))))
+
+
+class C3(nn.Module):
+ # CSP Bottleneck with 3 convolutions
+ def __init__(self, c1, c2, n=1, shortcut=True, g=1, e=0.5): # ch_in, ch_out, number, shortcut, groups, expansion
+ super().__init__()
+ c_ = int(c2 * e) # hidden channels
+ self.cv1 = Conv(c1, c_, 1, 1)
+ self.cv2 = Conv(c1, c_, 1, 1)
+ self.cv3 = Conv(2 * c_, c2, 1) # act=FReLU(c2)
+ self.m = nn.Sequential(*(Bottleneck(c_, c_, shortcut, g, e=1.0) for _ in range(n)))
+ # self.m = nn.Sequential(*[CrossConv(c_, c_, 3, 1, g, 1.0, shortcut) for _ in range(n)])
+
+ def forward(self, x):
+ return self.cv3(torch.cat((self.m(self.cv1(x)), self.cv2(x)), dim=1))
+
+
+class C3TR(C3):
+ # C3 module with TransformerBlock()
+ def __init__(self, c1, c2, n=1, shortcut=True, g=1, e=0.5):
+ super().__init__(c1, c2, n, shortcut, g, e)
+ c_ = int(c2 * e)
+ self.m = TransformerBlock(c_, c_, 4, n)
+
+
+class C3SPP(C3):
+ # C3 module with SPP()
+ def __init__(self, c1, c2, k=(5, 9, 13), n=1, shortcut=True, g=1, e=0.5):
+ super().__init__(c1, c2, n, shortcut, g, e)
+ c_ = int(c2 * e)
+ self.m = SPP(c_, c_, k)
+
+
+class C3Ghost(C3):
+ # C3 module with GhostBottleneck()
+ def __init__(self, c1, c2, n=1, shortcut=True, g=1, e=0.5):
+ super().__init__(c1, c2, n, shortcut, g, e)
+ c_ = int(c2 * e) # hidden channels
+ self.m = nn.Sequential(*(GhostBottleneck(c_, c_) for _ in range(n)))
+
+
+class SPP(nn.Module):
+ # Spatial Pyramid Pooling (SPP) layer https://arxiv.org/abs/1406.4729
+ def __init__(self, c1, c2, k=(5, 9, 13)):
+ super().__init__()
+ c_ = c1 // 2 # hidden channels
+ self.cv1 = Conv(c1, c_, 1, 1)
+ self.cv2 = Conv(c_ * (len(k) + 1), c2, 1, 1)
+ self.m = nn.ModuleList([nn.MaxPool2d(kernel_size=x, stride=1, padding=x // 2) for x in k])
+
+ def forward(self, x):
+ x = self.cv1(x)
+ with warnings.catch_warnings():
+ warnings.simplefilter('ignore') # suppress torch 1.9.0 max_pool2d() warning
+ return self.cv2(torch.cat([x] + [m(x) for m in self.m], 1))
+
+
+class SPPF(nn.Module):
+ # Spatial Pyramid Pooling - Fast (SPPF) layer for by Glenn Jocher
+ def __init__(self, c1, c2, k=5): # equivalent to SPP(k=(5, 9, 13))
+ super().__init__()
+ c_ = c1 // 2 # hidden channels
+ self.cv1 = Conv(c1, c_, 1, 1)
+ self.cv2 = Conv(c_ * 4, c2, 1, 1)
+ self.m = nn.MaxPool2d(kernel_size=k, stride=1, padding=k // 2)
+
+ def forward(self, x):
+ x = self.cv1(x)
+ with warnings.catch_warnings():
+ warnings.simplefilter('ignore') # suppress torch 1.9.0 max_pool2d() warning
+ y1 = self.m(x)
+ y2 = self.m(y1)
+ return self.cv2(torch.cat([x, y1, y2, self.m(y2)], 1))
+
+
+class Focus(nn.Module):
+ # Focus wh information into c-space
+ def __init__(self, c1, c2, k=1, s=1, p=None, g=1, act=True): # ch_in, ch_out, kernel, stride, padding, groups
+ super().__init__()
+ self.conv = Conv(c1 * 4, c2, k, s, p, g, act)
+ # self.contract = Contract(gain=2)
+
+ def forward(self, x): # x(b,c,w,h) -> y(b,4c,w/2,h/2)
+ return self.conv(torch.cat([x[..., ::2, ::2], x[..., 1::2, ::2], x[..., ::2, 1::2], x[..., 1::2, 1::2]], 1))
+ # return self.conv(self.contract(x))
+
+
+class GhostConv(nn.Module):
+ # Ghost Convolution https://github.com/huawei-noah/ghostnet
+ def __init__(self, c1, c2, k=1, s=1, g=1, act=True): # ch_in, ch_out, kernel, stride, groups
+ super().__init__()
+ c_ = c2 // 2 # hidden channels
+ self.cv1 = Conv(c1, c_, k, s, None, g, act)
+ self.cv2 = Conv(c_, c_, 5, 1, None, c_, act)
+
+ def forward(self, x):
+ y = self.cv1(x)
+ return torch.cat([y, self.cv2(y)], 1)
+
+
+class GhostBottleneck(nn.Module):
+ # Ghost Bottleneck https://github.com/huawei-noah/ghostnet
+ def __init__(self, c1, c2, k=3, s=1): # ch_in, ch_out, kernel, stride
+ super().__init__()
+ c_ = c2 // 2
+ self.conv = nn.Sequential(GhostConv(c1, c_, 1, 1), # pw
+ DWConv(c_, c_, k, s, act=False) if s == 2 else nn.Identity(), # dw
+ GhostConv(c_, c2, 1, 1, act=False)) # pw-linear
+ self.shortcut = nn.Sequential(DWConv(c1, c1, k, s, act=False),
+ Conv(c1, c2, 1, 1, act=False)) if s == 2 else nn.Identity()
+
+ def forward(self, x):
+ return self.conv(x) + self.shortcut(x)
+
+
+class Contract(nn.Module):
+ # Contract width-height into channels, i.e. x(1,64,80,80) to x(1,256,40,40)
+ def __init__(self, gain=2):
+ super().__init__()
+ self.gain = gain
+
+ def forward(self, x):
+ b, c, h, w = x.size() # assert (h / s == 0) and (W / s == 0), 'Indivisible gain'
+ s = self.gain
+ x = x.view(b, c, h // s, s, w // s, s) # x(1,64,40,2,40,2)
+ x = x.permute(0, 3, 5, 1, 2, 4).contiguous() # x(1,2,2,64,40,40)
+ return x.view(b, c * s * s, h // s, w // s) # x(1,256,40,40)
+
+
+class Expand(nn.Module):
+ # Expand channels into width-height, i.e. x(1,64,80,80) to x(1,16,160,160)
+ def __init__(self, gain=2):
+ super().__init__()
+ self.gain = gain
+
+ def forward(self, x):
+ b, c, h, w = x.size() # assert C / s ** 2 == 0, 'Indivisible gain'
+ s = self.gain
+ x = x.view(b, s, s, c // s ** 2, h, w) # x(1,2,2,16,80,80)
+ x = x.permute(0, 3, 4, 1, 5, 2).contiguous() # x(1,16,80,2,80,2)
+ return x.view(b, c // s ** 2, h * s, w * s) # x(1,16,160,160)
+
+
+class Concat(nn.Module):
+ # Concatenate a list of tensors along dimension
+ def __init__(self, dimension=1):
+ super().__init__()
+ self.d = dimension
+
+ def forward(self, x):
+ return torch.cat(x, self.d)
+
+
+class DetectMultiBackend(nn.Module):
+ # MultiBackend class for python inference on various backends
+ def __init__(self, weights='yolov3.pt', device=None, dnn=True):
+ # Usage:
+ # PyTorch: weights = *.pt
+ # TorchScript: *.torchscript.pt
+ # CoreML: *.mlmodel
+ # TensorFlow: *_saved_model
+ # TensorFlow: *.pb
+ # TensorFlow Lite: *.tflite
+ # ONNX Runtime: *.onnx
+ # OpenCV DNN: *.onnx with dnn=True
+ super().__init__()
+ w = str(weights[0] if isinstance(weights, list) else weights)
+ suffix, suffixes = Path(w).suffix.lower(), ['.pt', '.onnx', '.tflite', '.pb', '', '.mlmodel']
+ check_suffix(w, suffixes) # check weights have acceptable suffix
+ pt, onnx, tflite, pb, saved_model, coreml = (suffix == x for x in suffixes) # backend booleans
+ jit = pt and 'torchscript' in w.lower()
+ stride, names = 64, [f'class{i}' for i in range(1000)] # assign defaults
+
+ if jit: # TorchScript
+ LOGGER.info(f'Loading {w} for TorchScript inference...')
+ extra_files = {'config.txt': ''} # model metadata
+ model = torch.jit.load(w, _extra_files=extra_files)
+ if extra_files['config.txt']:
+ d = json.loads(extra_files['config.txt']) # extra_files dict
+ stride, names = int(d['stride']), d['names']
+ elif pt: # PyTorch
+ from models.experimental import attempt_load # scoped to avoid circular import
+ model = torch.jit.load(w) if 'torchscript' in w else attempt_load(weights, map_location=device)
+ stride = int(model.stride.max()) # model stride
+ names = model.module.names if hasattr(model, 'module') else model.names # get class names
+ elif coreml: # CoreML *.mlmodel
+ import coremltools as ct
+ model = ct.models.MLModel(w)
+ elif dnn: # ONNX OpenCV DNN
+ LOGGER.info(f'Loading {w} for ONNX OpenCV DNN inference...')
+ check_requirements(('opencv-python>=4.5.4',))
+ net = cv2.dnn.readNetFromONNX(w)
+ elif onnx: # ONNX Runtime
+ LOGGER.info(f'Loading {w} for ONNX Runtime inference...')
+ cuda = torch.cuda.is_available()
+ check_requirements(('onnx', 'onnxruntime-gpu' if cuda else 'onnxruntime'))
+ import onnxruntime
+ providers = ['CUDAExecutionProvider', 'CPUExecutionProvider'] if cuda else ['CPUExecutionProvider']
+ session = onnxruntime.InferenceSession(w, providers=providers)
+ else: # TensorFlow model (TFLite, pb, saved_model)
+ import tensorflow as tf
+ if pb: # https://www.tensorflow.org/guide/migrate#a_graphpb_or_graphpbtxt
+ def wrap_frozen_graph(gd, inputs, outputs):
+ x = tf.compat.v1.wrap_function(lambda: tf.compat.v1.import_graph_def(gd, name=""), []) # wrapped
+ return x.prune(tf.nest.map_structure(x.graph.as_graph_element, inputs),
+ tf.nest.map_structure(x.graph.as_graph_element, outputs))
+
+ LOGGER.info(f'Loading {w} for TensorFlow *.pb inference...')
+ graph_def = tf.Graph().as_graph_def()
+ graph_def.ParseFromString(open(w, 'rb').read())
+ frozen_func = wrap_frozen_graph(gd=graph_def, inputs="x:0", outputs="Identity:0")
+ elif saved_model:
+ LOGGER.info(f'Loading {w} for TensorFlow saved_model inference...')
+ model = tf.keras.models.load_model(w)
+ elif tflite: # https://www.tensorflow.org/lite/guide/python#install_tensorflow_lite_for_python
+ if 'edgetpu' in w.lower():
+ LOGGER.info(f'Loading {w} for TensorFlow Edge TPU inference...')
+ import tflite_runtime.interpreter as tfli
+ delegate = {'Linux': 'libedgetpu.so.1', # install https://coral.ai/software/#edgetpu-runtime
+ 'Darwin': 'libedgetpu.1.dylib',
+ 'Windows': 'edgetpu.dll'}[platform.system()]
+ interpreter = tfli.Interpreter(model_path=w, experimental_delegates=[tfli.load_delegate(delegate)])
+ else:
+ LOGGER.info(f'Loading {w} for TensorFlow Lite inference...')
+ interpreter = tf.lite.Interpreter(model_path=w) # load TFLite model
+ interpreter.allocate_tensors() # allocate
+ input_details = interpreter.get_input_details() # inputs
+ output_details = interpreter.get_output_details() # outputs
+ self.__dict__.update(locals()) # assign all variables to self
+
+ def forward(self, im, augment=False, visualize=False, val=False):
+ # MultiBackend inference
+ b, ch, h, w = im.shape # batch, channel, height, width
+ if self.pt: # PyTorch
+ y = self.model(im) if self.jit else self.model(im, augment=augment, visualize=visualize)
+ return y if val else y[0]
+ elif self.coreml: # CoreML *.mlmodel
+ im = im.permute(0, 2, 3, 1).cpu().numpy() # torch BCHW to numpy BHWC shape(1,320,192,3)
+ im = Image.fromarray((im[0] * 255).astype('uint8'))
+ # im = im.resize((192, 320), Image.ANTIALIAS)
+ y = self.model.predict({'image': im}) # coordinates are xywh normalized
+ box = xywh2xyxy(y['coordinates'] * [[w, h, w, h]]) # xyxy pixels
+ conf, cls = y['confidence'].max(1), y['confidence'].argmax(1).astype(np.float)
+ y = np.concatenate((box, conf.reshape(-1, 1), cls.reshape(-1, 1)), 1)
+ elif self.onnx: # ONNX
+ im = im.cpu().numpy() # torch to numpy
+ if self.dnn: # ONNX OpenCV DNN
+ self.net.setInput(im)
+ y = self.net.forward()
+ else: # ONNX Runtime
+ y = self.session.run([self.session.get_outputs()[0].name], {self.session.get_inputs()[0].name: im})[0]
+ else: # TensorFlow model (TFLite, pb, saved_model)
+ im = im.permute(0, 2, 3, 1).cpu().numpy() # torch BCHW to numpy BHWC shape(1,320,192,3)
+ if self.pb:
+ y = self.frozen_func(x=self.tf.constant(im)).numpy()
+ elif self.saved_model:
+ y = self.model(im, training=False).numpy()
+ elif self.tflite:
+ input, output = self.input_details[0], self.output_details[0]
+ int8 = input['dtype'] == np.uint8 # is TFLite quantized uint8 model
+ if int8:
+ scale, zero_point = input['quantization']
+ im = (im / scale + zero_point).astype(np.uint8) # de-scale
+ self.interpreter.set_tensor(input['index'], im)
+ self.interpreter.invoke()
+ y = self.interpreter.get_tensor(output['index'])
+ if int8:
+ scale, zero_point = output['quantization']
+ y = (y.astype(np.float32) - zero_point) * scale # re-scale
+ y[..., 0] *= w # x
+ y[..., 1] *= h # y
+ y[..., 2] *= w # w
+ y[..., 3] *= h # h
+ y = torch.tensor(y)
+ return (y, []) if val else y
+
+
+class AutoShape(nn.Module):
+ # input-robust model wrapper for passing cv2/np/PIL/torch inputs. Includes preprocessing, inference and NMS
+ conf = 0.25 # NMS confidence threshold
+ iou = 0.45 # NMS IoU threshold
+ classes = None # (optional list) filter by class, i.e. = [0, 15, 16] for COCO persons, cats and dogs
+ multi_label = False # NMS multiple labels per box
+ max_det = 1000 # maximum number of detections per image
+
+ def __init__(self, model):
+ super().__init__()
+ self.model = model.eval()
+
+ def autoshape(self):
+ LOGGER.info('AutoShape already enabled, skipping... ') # model already converted to model.autoshape()
+ return self
+
+ def _apply(self, fn):
+ # Apply to(), cpu(), cuda(), half() to model tensors that are not parameters or registered buffers
+ self = super()._apply(fn)
+ m = self.model.model[-1] # Detect()
+ m.stride = fn(m.stride)
+ m.grid = list(map(fn, m.grid))
+ if isinstance(m.anchor_grid, list):
+ m.anchor_grid = list(map(fn, m.anchor_grid))
+ return self
+
+ @torch.no_grad()
+ def forward(self, imgs, size=640, augment=False, profile=False):
+ # Inference from various sources. For height=640, width=1280, RGB images example inputs are:
+ # file: imgs = 'data/images/zidane.jpg' # str or PosixPath
+ # URI: = 'https://ultralytics.com/images/zidane.jpg'
+ # OpenCV: = cv2.imread('image.jpg')[:,:,::-1] # HWC BGR to RGB x(640,1280,3)
+ # PIL: = Image.open('image.jpg') or ImageGrab.grab() # HWC x(640,1280,3)
+ # numpy: = np.zeros((640,1280,3)) # HWC
+ # torch: = torch.zeros(16,3,320,640) # BCHW (scaled to size=640, 0-1 values)
+ # multiple: = [Image.open('image1.jpg'), Image.open('image2.jpg'), ...] # list of images
+
+ t = [time_sync()]
+ p = next(self.model.parameters()) # for device and type
+ if isinstance(imgs, torch.Tensor): # torch
+ with amp.autocast(enabled=p.device.type != 'cpu'):
+ return self.model(imgs.to(p.device).type_as(p), augment, profile) # inference
+
+ # Pre-process
+ n, imgs = (len(imgs), imgs) if isinstance(imgs, list) else (1, [imgs]) # number of images, list of images
+ shape0, shape1, files = [], [], [] # image and inference shapes, filenames
+ for i, im in enumerate(imgs):
+ f = f'image{i}' # filename
+ if isinstance(im, (str, Path)): # filename or uri
+ im, f = Image.open(requests.get(im, stream=True).raw if str(im).startswith('http') else im), im
+ im = np.asarray(exif_transpose(im))
+ elif isinstance(im, Image.Image): # PIL Image
+ im, f = np.asarray(exif_transpose(im)), getattr(im, 'filename', f) or f
+ files.append(Path(f).with_suffix('.jpg').name)
+ if im.shape[0] < 5: # image in CHW
+ im = im.transpose((1, 2, 0)) # reverse dataloader .transpose(2, 0, 1)
+ im = im[..., :3] if im.ndim == 3 else np.tile(im[..., None], 3) # enforce 3ch input
+ s = im.shape[:2] # HWC
+ shape0.append(s) # image shape
+ g = (size / max(s)) # gain
+ shape1.append([y * g for y in s])
+ imgs[i] = im if im.data.contiguous else np.ascontiguousarray(im) # update
+ shape1 = [make_divisible(x, int(self.stride.max())) for x in np.stack(shape1, 0).max(0)] # inference shape
+ x = [letterbox(im, new_shape=shape1, auto=False)[0] for im in imgs] # pad
+ x = np.stack(x, 0) if n > 1 else x[0][None] # stack
+ x = np.ascontiguousarray(x.transpose((0, 3, 1, 2))) # BHWC to BCHW
+ x = torch.from_numpy(x).to(p.device).type_as(p) / 255 # uint8 to fp16/32
+ t.append(time_sync())
+
+ with amp.autocast(enabled=p.device.type != 'cpu'):
+ # Inference
+ y = self.model(x, augment, profile)[0] # forward
+ t.append(time_sync())
+
+ # Post-process
+ y = non_max_suppression(y, self.conf, iou_thres=self.iou, classes=self.classes,
+ multi_label=self.multi_label, max_det=self.max_det) # NMS
+ for i in range(n):
+ scale_coords(shape1, y[i][:, :4], shape0[i])
+
+ t.append(time_sync())
+ return Detections(imgs, y, files, t, self.names, x.shape)
+
+
+class Detections:
+ # detections class for inference results
+ def __init__(self, imgs, pred, files, times=None, names=None, shape=None):
+ super().__init__()
+ d = pred[0].device # device
+ gn = [torch.tensor([*(im.shape[i] for i in [1, 0, 1, 0]), 1, 1], device=d) for im in imgs] # normalizations
+ self.imgs = imgs # list of images as numpy arrays
+ self.pred = pred # list of tensors pred[0] = (xyxy, conf, cls)
+ self.names = names # class names
+ self.files = files # image filenames
+ self.xyxy = pred # xyxy pixels
+ self.xywh = [xyxy2xywh(x) for x in pred] # xywh pixels
+ self.xyxyn = [x / g for x, g in zip(self.xyxy, gn)] # xyxy normalized
+ self.xywhn = [x / g for x, g in zip(self.xywh, gn)] # xywh normalized
+ self.n = len(self.pred) # number of images (batch size)
+ self.t = tuple((times[i + 1] - times[i]) * 1000 / self.n for i in range(3)) # timestamps (ms)
+ self.s = shape # inference BCHW shape
+
+ def display(self, pprint=False, show=False, save=False, crop=False, render=False, save_dir=Path('')):
+ crops = []
+ for i, (im, pred) in enumerate(zip(self.imgs, self.pred)):
+ s = f'image {i + 1}/{len(self.pred)}: {im.shape[0]}x{im.shape[1]} ' # string
+ if pred.shape[0]:
+ for c in pred[:, -1].unique():
+ n = (pred[:, -1] == c).sum() # detections per class
+ s += f"{n} {self.names[int(c)]}{'s' * (n > 1)}, " # add to string
+ if show or save or render or crop:
+ annotator = Annotator(im, example=str(self.names))
+ for *box, conf, cls in reversed(pred): # xyxy, confidence, class
+ label = f'{self.names[int(cls)]} {conf:.2f}'
+ if crop:
+ file = save_dir / 'crops' / self.names[int(cls)] / self.files[i] if save else None
+ crops.append({'box': box, 'conf': conf, 'cls': cls, 'label': label,
+ 'im': save_one_box(box, im, file=file, save=save)})
+ else: # all others
+ annotator.box_label(box, label, color=colors(cls))
+ im = annotator.im
+ else:
+ s += '(no detections)'
+
+ im = Image.fromarray(im.astype(np.uint8)) if isinstance(im, np.ndarray) else im # from np
+ if pprint:
+ LOGGER.info(s.rstrip(', '))
+ if show:
+ im.show(self.files[i]) # show
+ if save:
+ f = self.files[i]
+ im.save(save_dir / f) # save
+ if i == self.n - 1:
+ LOGGER.info(f"Saved {self.n} image{'s' * (self.n > 1)} to {colorstr('bold', save_dir)}")
+ if render:
+ self.imgs[i] = np.asarray(im)
+ if crop:
+ if save:
+ LOGGER.info(f'Saved results to {save_dir}\n')
+ return crops
+
+ def print(self):
+ self.display(pprint=True) # print results
+ LOGGER.info(f'Speed: %.1fms pre-process, %.1fms inference, %.1fms NMS per image at shape {tuple(self.s)}' %
+ self.t)
+
+ def show(self):
+ self.display(show=True) # show results
+
+ def save(self, save_dir='runs/detect/exp'):
+ save_dir = increment_path(save_dir, exist_ok=save_dir != 'runs/detect/exp', mkdir=True) # increment save_dir
+ self.display(save=True, save_dir=save_dir) # save results
+
+ def crop(self, save=True, save_dir='runs/detect/exp'):
+ save_dir = increment_path(save_dir, exist_ok=save_dir != 'runs/detect/exp', mkdir=True) if save else None
+ return self.display(crop=True, save=save, save_dir=save_dir) # crop results
+
+ def render(self):
+ self.display(render=True) # render results
+ return self.imgs
+
+ def pandas(self):
+ # return detections as pandas DataFrames, i.e. print(results.pandas().xyxy[0])
+ new = copy(self) # return copy
+ ca = 'xmin', 'ymin', 'xmax', 'ymax', 'confidence', 'class', 'name' # xyxy columns
+ cb = 'xcenter', 'ycenter', 'width', 'height', 'confidence', 'class', 'name' # xywh columns
+ for k, c in zip(['xyxy', 'xyxyn', 'xywh', 'xywhn'], [ca, ca, cb, cb]):
+ a = [[x[:5] + [int(x[5]), self.names[int(x[5])]] for x in x.tolist()] for x in getattr(self, k)] # update
+ setattr(new, k, [pd.DataFrame(x, columns=c) for x in a])
+ return new
+
+ def tolist(self):
+ # return a list of Detections objects, i.e. 'for result in results.tolist():'
+ x = [Detections([self.imgs[i]], [self.pred[i]], self.names, self.s) for i in range(self.n)]
+ for d in x:
+ for k in ['imgs', 'pred', 'xyxy', 'xyxyn', 'xywh', 'xywhn']:
+ setattr(d, k, getattr(d, k)[0]) # pop out of list
+ return x
+
+ def __len__(self):
+ return self.n
+
+
+class Classify(nn.Module):
+ # Classification head, i.e. x(b,c1,20,20) to x(b,c2)
+ def __init__(self, c1, c2, k=1, s=1, p=None, g=1): # ch_in, ch_out, kernel, stride, padding, groups
+ super().__init__()
+ self.aap = nn.AdaptiveAvgPool2d(1) # to x(b,c1,1,1)
+ self.conv = nn.Conv2d(c1, c2, k, s, autopad(k, p), groups=g) # to x(b,c2,1,1)
+ self.flat = nn.Flatten()
+
+ def forward(self, x):
+ z = torch.cat([self.aap(y) for y in (x if isinstance(x, list) else [x])], 1) # cat if list
+ return self.flat(self.conv(z)) # flatten to x(b,c2)
diff --git a/ros2_ws/src/yolov3_ros/models/experimental.py b/ros2_ws/src/yolov3_ros/models/experimental.py
new file mode 100644
index 00000000..ab8266a1
--- /dev/null
+++ b/ros2_ws/src/yolov3_ros/models/experimental.py
@@ -0,0 +1,121 @@
+# YOLOv3 🚀 by Ultralytics, GPL-3.0 license
+"""
+Experimental modules
+"""
+import math
+
+import numpy as np
+import torch
+import torch.nn as nn
+
+from models.common import Conv
+from utils.downloads import attempt_download
+
+
+class CrossConv(nn.Module):
+ # Cross Convolution Downsample
+ def __init__(self, c1, c2, k=3, s=1, g=1, e=1.0, shortcut=False):
+ # ch_in, ch_out, kernel, stride, groups, expansion, shortcut
+ super().__init__()
+ c_ = int(c2 * e) # hidden channels
+ self.cv1 = Conv(c1, c_, (1, k), (1, s))
+ self.cv2 = Conv(c_, c2, (k, 1), (s, 1), g=g)
+ self.add = shortcut and c1 == c2
+
+ def forward(self, x):
+ return x + self.cv2(self.cv1(x)) if self.add else self.cv2(self.cv1(x))
+
+
+class Sum(nn.Module):
+ # Weighted sum of 2 or more layers https://arxiv.org/abs/1911.09070
+ def __init__(self, n, weight=False): # n: number of inputs
+ super().__init__()
+ self.weight = weight # apply weights boolean
+ self.iter = range(n - 1) # iter object
+ if weight:
+ self.w = nn.Parameter(-torch.arange(1.0, n) / 2, requires_grad=True) # layer weights
+
+ def forward(self, x):
+ y = x[0] # no weight
+ if self.weight:
+ w = torch.sigmoid(self.w) * 2
+ for i in self.iter:
+ y = y + x[i + 1] * w[i]
+ else:
+ for i in self.iter:
+ y = y + x[i + 1]
+ return y
+
+
+class MixConv2d(nn.Module):
+ # Mixed Depth-wise Conv https://arxiv.org/abs/1907.09595
+ def __init__(self, c1, c2, k=(1, 3), s=1, equal_ch=True): # ch_in, ch_out, kernel, stride, ch_strategy
+ super().__init__()
+ n = len(k) # number of convolutions
+ if equal_ch: # equal c_ per group
+ i = torch.linspace(0, n - 1E-6, c2).floor() # c2 indices
+ c_ = [(i == g).sum() for g in range(n)] # intermediate channels
+ else: # equal weight.numel() per group
+ b = [c2] + [0] * n
+ a = np.eye(n + 1, n, k=-1)
+ a -= np.roll(a, 1, axis=1)
+ a *= np.array(k) ** 2
+ a[0] = 1
+ c_ = np.linalg.lstsq(a, b, rcond=None)[0].round() # solve for equal weight indices, ax = b
+
+ self.m = nn.ModuleList(
+ [nn.Conv2d(c1, int(c_), k, s, k // 2, groups=math.gcd(c1, int(c_)), bias=False) for k, c_ in zip(k, c_)])
+ self.bn = nn.BatchNorm2d(c2)
+ self.act = nn.SiLU()
+
+ def forward(self, x):
+ return self.act(self.bn(torch.cat([m(x) for m in self.m], 1)))
+
+
+class Ensemble(nn.ModuleList):
+ # Ensemble of models
+ def __init__(self):
+ super().__init__()
+
+ def forward(self, x, augment=False, profile=False, visualize=False):
+ y = []
+ for module in self:
+ y.append(module(x, augment, profile, visualize)[0])
+ # y = torch.stack(y).max(0)[0] # max ensemble
+ # y = torch.stack(y).mean(0) # mean ensemble
+ y = torch.cat(y, 1) # nms ensemble
+ return y, None # inference, train output
+
+
+def attempt_load(weights, map_location=None, inplace=True, fuse=True):
+ from models.yolo import Detect, Model
+
+ # Loads an ensemble of models weights=[a,b,c] or a single model weights=[a] or weights=a
+ model = Ensemble()
+ for w in weights if isinstance(weights, list) else [weights]:
+ ckpt = torch.load(attempt_download(w), map_location=map_location) # load
+ ckpt = (ckpt['ema'] or ckpt['model']).float() # FP32 model
+ model.append(ckpt.fuse().eval() if fuse else ckpt.eval()) # fused or un-fused model in eval mode
+
+ # Compatibility updates
+ for m in model.modules():
+ t = type(m)
+ if t in (nn.Hardswish, nn.LeakyReLU, nn.ReLU, nn.ReLU6, nn.SiLU, Detect, Model):
+ m.inplace = inplace # torch 1.7.0 compatibility
+ if t is Detect:
+ if not isinstance(m.anchor_grid, list): # new Detect Layer compatibility
+ delattr(m, 'anchor_grid')
+ setattr(m, 'anchor_grid', [torch.zeros(1)] * m.nl)
+ elif t is Conv:
+ m._non_persistent_buffers_set = set() # torch 1.6.0 compatibility
+ elif t is nn.Upsample and not hasattr(m, 'recompute_scale_factor'):
+ m.recompute_scale_factor = None # torch 1.11.0 compatibility
+
+ if len(model) == 1:
+ return model[-1] # return model
+ else:
+ print(f'Ensemble created with {weights}\n')
+ for k in ['names']:
+ setattr(model, k, getattr(model[-1], k))
+ model.stride = model[torch.argmax(torch.tensor([m.stride.max() for m in model])).int()].stride # max stride
+ return model # return ensemble
diff --git a/ros2_ws/src/yolov3_ros/models/hub/anchors.yaml b/ros2_ws/src/yolov3_ros/models/hub/anchors.yaml
new file mode 100644
index 00000000..fc252c19
--- /dev/null
+++ b/ros2_ws/src/yolov3_ros/models/hub/anchors.yaml
@@ -0,0 +1,59 @@
+# YOLOv3 🚀 by Ultralytics, GPL-3.0 license
+# Default anchors for COCO data
+
+
+# P5 -------------------------------------------------------------------------------------------------------------------
+# P5-640:
+anchors_p5_640:
+ - [10,13, 16,30, 33,23] # P3/8
+ - [30,61, 62,45, 59,119] # P4/16
+ - [116,90, 156,198, 373,326] # P5/32
+
+
+# P6 -------------------------------------------------------------------------------------------------------------------
+# P6-640: thr=0.25: 0.9964 BPR, 5.54 anchors past thr, n=12, img_size=640, metric_all=0.281/0.716-mean/best, past_thr=0.469-mean: 9,11, 21,19, 17,41, 43,32, 39,70, 86,64, 65,131, 134,130, 120,265, 282,180, 247,354, 512,387
+anchors_p6_640:
+ - [9,11, 21,19, 17,41] # P3/8
+ - [43,32, 39,70, 86,64] # P4/16
+ - [65,131, 134,130, 120,265] # P5/32
+ - [282,180, 247,354, 512,387] # P6/64
+
+# P6-1280: thr=0.25: 0.9950 BPR, 5.55 anchors past thr, n=12, img_size=1280, metric_all=0.281/0.714-mean/best, past_thr=0.468-mean: 19,27, 44,40, 38,94, 96,68, 86,152, 180,137, 140,301, 303,264, 238,542, 436,615, 739,380, 925,792
+anchors_p6_1280:
+ - [19,27, 44,40, 38,94] # P3/8
+ - [96,68, 86,152, 180,137] # P4/16
+ - [140,301, 303,264, 238,542] # P5/32
+ - [436,615, 739,380, 925,792] # P6/64
+
+# P6-1920: thr=0.25: 0.9950 BPR, 5.55 anchors past thr, n=12, img_size=1920, metric_all=0.281/0.714-mean/best, past_thr=0.468-mean: 28,41, 67,59, 57,141, 144,103, 129,227, 270,205, 209,452, 455,396, 358,812, 653,922, 1109,570, 1387,1187
+anchors_p6_1920:
+ - [28,41, 67,59, 57,141] # P3/8
+ - [144,103, 129,227, 270,205] # P4/16
+ - [209,452, 455,396, 358,812] # P5/32
+ - [653,922, 1109,570, 1387,1187] # P6/64
+
+
+# P7 -------------------------------------------------------------------------------------------------------------------
+# P7-640: thr=0.25: 0.9962 BPR, 6.76 anchors past thr, n=15, img_size=640, metric_all=0.275/0.733-mean/best, past_thr=0.466-mean: 11,11, 13,30, 29,20, 30,46, 61,38, 39,92, 78,80, 146,66, 79,163, 149,150, 321,143, 157,303, 257,402, 359,290, 524,372
+anchors_p7_640:
+ - [11,11, 13,30, 29,20] # P3/8
+ - [30,46, 61,38, 39,92] # P4/16
+ - [78,80, 146,66, 79,163] # P5/32
+ - [149,150, 321,143, 157,303] # P6/64
+ - [257,402, 359,290, 524,372] # P7/128
+
+# P7-1280: thr=0.25: 0.9968 BPR, 6.71 anchors past thr, n=15, img_size=1280, metric_all=0.273/0.732-mean/best, past_thr=0.463-mean: 19,22, 54,36, 32,77, 70,83, 138,71, 75,173, 165,159, 148,334, 375,151, 334,317, 251,626, 499,474, 750,326, 534,814, 1079,818
+anchors_p7_1280:
+ - [19,22, 54,36, 32,77] # P3/8
+ - [70,83, 138,71, 75,173] # P4/16
+ - [165,159, 148,334, 375,151] # P5/32
+ - [334,317, 251,626, 499,474] # P6/64
+ - [750,326, 534,814, 1079,818] # P7/128
+
+# P7-1920: thr=0.25: 0.9968 BPR, 6.71 anchors past thr, n=15, img_size=1920, metric_all=0.273/0.732-mean/best, past_thr=0.463-mean: 29,34, 81,55, 47,115, 105,124, 207,107, 113,259, 247,238, 222,500, 563,227, 501,476, 376,939, 749,711, 1126,489, 801,1222, 1618,1227
+anchors_p7_1920:
+ - [29,34, 81,55, 47,115] # P3/8
+ - [105,124, 207,107, 113,259] # P4/16
+ - [247,238, 222,500, 563,227] # P5/32
+ - [501,476, 376,939, 749,711] # P6/64
+ - [1126,489, 801,1222, 1618,1227] # P7/128
diff --git a/ros2_ws/src/yolov3_ros/models/hub/yolov5-bifpn.yaml b/ros2_ws/src/yolov3_ros/models/hub/yolov5-bifpn.yaml
new file mode 100644
index 00000000..7d17a347
--- /dev/null
+++ b/ros2_ws/src/yolov3_ros/models/hub/yolov5-bifpn.yaml
@@ -0,0 +1,48 @@
+# YOLOv3 🚀 by Ultralytics, GPL-3.0 license
+
+# Parameters
+nc: 80 # number of classes
+depth_multiple: 1.0 # model depth multiple
+width_multiple: 1.0 # layer channel multiple
+anchors:
+ - [10,13, 16,30, 33,23] # P3/8
+ - [30,61, 62,45, 59,119] # P4/16
+ - [116,90, 156,198, 373,326] # P5/32
+
+# YOLOv5 v6.0 backbone
+backbone:
+ # [from, number, module, args]
+ [[-1, 1, Conv, [64, 6, 2, 2]], # 0-P1/2
+ [-1, 1, Conv, [128, 3, 2]], # 1-P2/4
+ [-1, 3, C3, [128]],
+ [-1, 1, Conv, [256, 3, 2]], # 3-P3/8
+ [-1, 6, C3, [256]],
+ [-1, 1, Conv, [512, 3, 2]], # 5-P4/16
+ [-1, 9, C3, [512]],
+ [-1, 1, Conv, [1024, 3, 2]], # 7-P5/32
+ [-1, 3, C3, [1024]],
+ [-1, 1, SPPF, [1024, 5]], # 9
+ ]
+
+# YOLOv5 v6.0 BiFPN head
+head:
+ [[-1, 1, Conv, [512, 1, 1]],
+ [-1, 1, nn.Upsample, [None, 2, 'nearest']],
+ [[-1, 6], 1, Concat, [1]], # cat backbone P4
+ [-1, 3, C3, [512, False]], # 13
+
+ [-1, 1, Conv, [256, 1, 1]],
+ [-1, 1, nn.Upsample, [None, 2, 'nearest']],
+ [[-1, 4], 1, Concat, [1]], # cat backbone P3
+ [-1, 3, C3, [256, False]], # 17 (P3/8-small)
+
+ [-1, 1, Conv, [256, 3, 2]],
+ [[-1, 14, 6], 1, Concat, [1]], # cat P4 <--- BiFPN change
+ [-1, 3, C3, [512, False]], # 20 (P4/16-medium)
+
+ [-1, 1, Conv, [512, 3, 2]],
+ [[-1, 10], 1, Concat, [1]], # cat head P5
+ [-1, 3, C3, [1024, False]], # 23 (P5/32-large)
+
+ [[17, 20, 23], 1, Detect, [nc, anchors]], # Detect(P3, P4, P5)
+ ]
diff --git a/ros2_ws/src/yolov3_ros/models/hub/yolov5-fpn.yaml b/ros2_ws/src/yolov3_ros/models/hub/yolov5-fpn.yaml
new file mode 100644
index 00000000..0c91f931
--- /dev/null
+++ b/ros2_ws/src/yolov3_ros/models/hub/yolov5-fpn.yaml
@@ -0,0 +1,42 @@
+# YOLOv3 🚀 by Ultralytics, GPL-3.0 license
+
+# Parameters
+nc: 80 # number of classes
+depth_multiple: 1.0 # model depth multiple
+width_multiple: 1.0 # layer channel multiple
+anchors:
+ - [10,13, 16,30, 33,23] # P3/8
+ - [30,61, 62,45, 59,119] # P4/16
+ - [116,90, 156,198, 373,326] # P5/32
+
+# YOLOv5 v6.0 backbone
+backbone:
+ # [from, number, module, args]
+ [[-1, 1, Conv, [64, 6, 2, 2]], # 0-P1/2
+ [-1, 1, Conv, [128, 3, 2]], # 1-P2/4
+ [-1, 3, C3, [128]],
+ [-1, 1, Conv, [256, 3, 2]], # 3-P3/8
+ [-1, 6, C3, [256]],
+ [-1, 1, Conv, [512, 3, 2]], # 5-P4/16
+ [-1, 9, C3, [512]],
+ [-1, 1, Conv, [1024, 3, 2]], # 7-P5/32
+ [-1, 3, C3, [1024]],
+ [-1, 1, SPPF, [1024, 5]], # 9
+ ]
+
+# YOLOv5 v6.0 FPN head
+head:
+ [[-1, 3, C3, [1024, False]], # 10 (P5/32-large)
+
+ [-1, 1, nn.Upsample, [None, 2, 'nearest']],
+ [[-1, 6], 1, Concat, [1]], # cat backbone P4
+ [-1, 1, Conv, [512, 1, 1]],
+ [-1, 3, C3, [512, False]], # 14 (P4/16-medium)
+
+ [-1, 1, nn.Upsample, [None, 2, 'nearest']],
+ [[-1, 4], 1, Concat, [1]], # cat backbone P3
+ [-1, 1, Conv, [256, 1, 1]],
+ [-1, 3, C3, [256, False]], # 18 (P3/8-small)
+
+ [[18, 14, 10], 1, Detect, [nc, anchors]], # Detect(P3, P4, P5)
+ ]
diff --git a/ros2_ws/src/yolov3_ros/models/hub/yolov5-p2.yaml b/ros2_ws/src/yolov3_ros/models/hub/yolov5-p2.yaml
new file mode 100644
index 00000000..23264db0
--- /dev/null
+++ b/ros2_ws/src/yolov3_ros/models/hub/yolov5-p2.yaml
@@ -0,0 +1,54 @@
+# YOLOv3 🚀 by Ultralytics, GPL-3.0 license
+
+# Parameters
+nc: 80 # number of classes
+depth_multiple: 1.0 # model depth multiple
+width_multiple: 1.0 # layer channel multiple
+anchors: 3 # AutoAnchor evolves 3 anchors per P output layer
+
+# YOLOv5 v6.0 backbone
+backbone:
+ # [from, number, module, args]
+ [[-1, 1, Conv, [64, 6, 2, 2]], # 0-P1/2
+ [-1, 1, Conv, [128, 3, 2]], # 1-P2/4
+ [-1, 3, C3, [128]],
+ [-1, 1, Conv, [256, 3, 2]], # 3-P3/8
+ [-1, 6, C3, [256]],
+ [-1, 1, Conv, [512, 3, 2]], # 5-P4/16
+ [-1, 9, C3, [512]],
+ [-1, 1, Conv, [1024, 3, 2]], # 7-P5/32
+ [-1, 3, C3, [1024]],
+ [-1, 1, SPPF, [1024, 5]], # 9
+ ]
+
+# YOLOv5 v6.0 head with (P2, P3, P4, P5) outputs
+head:
+ [[-1, 1, Conv, [512, 1, 1]],
+ [-1, 1, nn.Upsample, [None, 2, 'nearest']],
+ [[-1, 6], 1, Concat, [1]], # cat backbone P4
+ [-1, 3, C3, [512, False]], # 13
+
+ [-1, 1, Conv, [256, 1, 1]],
+ [-1, 1, nn.Upsample, [None, 2, 'nearest']],
+ [[-1, 4], 1, Concat, [1]], # cat backbone P3
+ [-1, 3, C3, [256, False]], # 17 (P3/8-small)
+
+ [-1, 1, Conv, [128, 1, 1]],
+ [-1, 1, nn.Upsample, [None, 2, 'nearest']],
+ [[-1, 2], 1, Concat, [1]], # cat backbone P2
+ [-1, 1, C3, [128, False]], # 21 (P2/4-xsmall)
+
+ [-1, 1, Conv, [128, 3, 2]],
+ [[-1, 18], 1, Concat, [1]], # cat head P3
+ [-1, 3, C3, [256, False]], # 24 (P3/8-small)
+
+ [-1, 1, Conv, [256, 3, 2]],
+ [[-1, 14], 1, Concat, [1]], # cat head P4
+ [-1, 3, C3, [512, False]], # 27 (P4/16-medium)
+
+ [-1, 1, Conv, [512, 3, 2]],
+ [[-1, 10], 1, Concat, [1]], # cat head P5
+ [-1, 3, C3, [1024, False]], # 30 (P5/32-large)
+
+ [[21, 24, 27, 30], 1, Detect, [nc, anchors]], # Detect(P2, P3, P4, P5)
+ ]
diff --git a/ros2_ws/src/yolov3_ros/models/hub/yolov5-p34.yaml b/ros2_ws/src/yolov3_ros/models/hub/yolov5-p34.yaml
new file mode 100644
index 00000000..c7f76e30
--- /dev/null
+++ b/ros2_ws/src/yolov3_ros/models/hub/yolov5-p34.yaml
@@ -0,0 +1,41 @@
+# YOLOv3 🚀 by Ultralytics, GPL-3.0 license
+
+# Parameters
+nc: 80 # number of classes
+depth_multiple: 0.33 # model depth multiple
+width_multiple: 0.50 # layer channel multiple
+anchors: 3 # AutoAnchor evolves 3 anchors per P output layer
+
+# YOLOv5 v6.0 backbone
+backbone:
+ # [from, number, module, args]
+ [[-1, 1, Conv, [64, 6, 2, 2]], # 0-P1/2
+ [-1, 1, Conv, [128, 3, 2]], # 1-P2/4
+ [-1, 3, C3, [128]],
+ [-1, 1, Conv, [256, 3, 2]], # 3-P3/8
+ [-1, 6, C3, [256]],
+ [-1, 1, Conv, [512, 3, 2]], # 5-P4/16
+ [-1, 9, C3, [512]],
+ [-1, 1, Conv, [1024, 3, 2]], # 7-P5/32
+ [-1, 3, C3, [1024]],
+ [-1, 1, SPPF, [1024, 5]], # 9
+ ]
+
+# YOLOv5 v6.0 head with (P3, P4) outputs
+head:
+ [[-1, 1, Conv, [512, 1, 1]],
+ [-1, 1, nn.Upsample, [None, 2, 'nearest']],
+ [[-1, 6], 1, Concat, [1]], # cat backbone P4
+ [-1, 3, C3, [512, False]], # 13
+
+ [-1, 1, Conv, [256, 1, 1]],
+ [-1, 1, nn.Upsample, [None, 2, 'nearest']],
+ [[-1, 4], 1, Concat, [1]], # cat backbone P3
+ [-1, 3, C3, [256, False]], # 17 (P3/8-small)
+
+ [-1, 1, Conv, [256, 3, 2]],
+ [[-1, 14], 1, Concat, [1]], # cat head P4
+ [-1, 3, C3, [512, False]], # 20 (P4/16-medium)
+
+ [[17, 20], 1, Detect, [nc, anchors]], # Detect(P3, P4)
+ ]
diff --git a/ros2_ws/src/yolov3_ros/models/hub/yolov5-p6.yaml b/ros2_ws/src/yolov3_ros/models/hub/yolov5-p6.yaml
new file mode 100644
index 00000000..a7b79a57
--- /dev/null
+++ b/ros2_ws/src/yolov3_ros/models/hub/yolov5-p6.yaml
@@ -0,0 +1,56 @@
+# YOLOv3 🚀 by Ultralytics, GPL-3.0 license
+
+# Parameters
+nc: 80 # number of classes
+depth_multiple: 1.0 # model depth multiple
+width_multiple: 1.0 # layer channel multiple
+anchors: 3 # AutoAnchor evolves 3 anchors per P output layer
+
+# YOLOv5 v6.0 backbone
+backbone:
+ # [from, number, module, args]
+ [[-1, 1, Conv, [64, 6, 2, 2]], # 0-P1/2
+ [-1, 1, Conv, [128, 3, 2]], # 1-P2/4
+ [-1, 3, C3, [128]],
+ [-1, 1, Conv, [256, 3, 2]], # 3-P3/8
+ [-1, 6, C3, [256]],
+ [-1, 1, Conv, [512, 3, 2]], # 5-P4/16
+ [-1, 9, C3, [512]],
+ [-1, 1, Conv, [768, 3, 2]], # 7-P5/32
+ [-1, 3, C3, [768]],
+ [-1, 1, Conv, [1024, 3, 2]], # 9-P6/64
+ [-1, 3, C3, [1024]],
+ [-1, 1, SPPF, [1024, 5]], # 11
+ ]
+
+# YOLOv5 v6.0 head with (P3, P4, P5, P6) outputs
+head:
+ [[-1, 1, Conv, [768, 1, 1]],
+ [-1, 1, nn.Upsample, [None, 2, 'nearest']],
+ [[-1, 8], 1, Concat, [1]], # cat backbone P5
+ [-1, 3, C3, [768, False]], # 15
+
+ [-1, 1, Conv, [512, 1, 1]],
+ [-1, 1, nn.Upsample, [None, 2, 'nearest']],
+ [[-1, 6], 1, Concat, [1]], # cat backbone P4
+ [-1, 3, C3, [512, False]], # 19
+
+ [-1, 1, Conv, [256, 1, 1]],
+ [-1, 1, nn.Upsample, [None, 2, 'nearest']],
+ [[-1, 4], 1, Concat, [1]], # cat backbone P3
+ [-1, 3, C3, [256, False]], # 23 (P3/8-small)
+
+ [-1, 1, Conv, [256, 3, 2]],
+ [[-1, 20], 1, Concat, [1]], # cat head P4
+ [-1, 3, C3, [512, False]], # 26 (P4/16-medium)
+
+ [-1, 1, Conv, [512, 3, 2]],
+ [[-1, 16], 1, Concat, [1]], # cat head P5
+ [-1, 3, C3, [768, False]], # 29 (P5/32-large)
+
+ [-1, 1, Conv, [768, 3, 2]],
+ [[-1, 12], 1, Concat, [1]], # cat head P6
+ [-1, 3, C3, [1024, False]], # 32 (P6/64-xlarge)
+
+ [[23, 26, 29, 32], 1, Detect, [nc, anchors]], # Detect(P3, P4, P5, P6)
+ ]
diff --git a/ros2_ws/src/yolov3_ros/models/hub/yolov5-p7.yaml b/ros2_ws/src/yolov3_ros/models/hub/yolov5-p7.yaml
new file mode 100644
index 00000000..3846496b
--- /dev/null
+++ b/ros2_ws/src/yolov3_ros/models/hub/yolov5-p7.yaml
@@ -0,0 +1,67 @@
+# YOLOv3 🚀 by Ultralytics, GPL-3.0 license
+
+# Parameters
+nc: 80 # number of classes
+depth_multiple: 1.0 # model depth multiple
+width_multiple: 1.0 # layer channel multiple
+anchors: 3 # AutoAnchor evolves 3 anchors per P output layer
+
+# YOLOv5 v6.0 backbone
+backbone:
+ # [from, number, module, args]
+ [[-1, 1, Conv, [64, 6, 2, 2]], # 0-P1/2
+ [-1, 1, Conv, [128, 3, 2]], # 1-P2/4
+ [-1, 3, C3, [128]],
+ [-1, 1, Conv, [256, 3, 2]], # 3-P3/8
+ [-1, 6, C3, [256]],
+ [-1, 1, Conv, [512, 3, 2]], # 5-P4/16
+ [-1, 9, C3, [512]],
+ [-1, 1, Conv, [768, 3, 2]], # 7-P5/32
+ [-1, 3, C3, [768]],
+ [-1, 1, Conv, [1024, 3, 2]], # 9-P6/64
+ [-1, 3, C3, [1024]],
+ [-1, 1, Conv, [1280, 3, 2]], # 11-P7/128
+ [-1, 3, C3, [1280]],
+ [-1, 1, SPPF, [1280, 5]], # 13
+ ]
+
+# YOLOv5 v6.0 head with (P3, P4, P5, P6, P7) outputs
+head:
+ [[-1, 1, Conv, [1024, 1, 1]],
+ [-1, 1, nn.Upsample, [None, 2, 'nearest']],
+ [[-1, 10], 1, Concat, [1]], # cat backbone P6
+ [-1, 3, C3, [1024, False]], # 17
+
+ [-1, 1, Conv, [768, 1, 1]],
+ [-1, 1, nn.Upsample, [None, 2, 'nearest']],
+ [[-1, 8], 1, Concat, [1]], # cat backbone P5
+ [-1, 3, C3, [768, False]], # 21
+
+ [-1, 1, Conv, [512, 1, 1]],
+ [-1, 1, nn.Upsample, [None, 2, 'nearest']],
+ [[-1, 6], 1, Concat, [1]], # cat backbone P4
+ [-1, 3, C3, [512, False]], # 25
+
+ [-1, 1, Conv, [256, 1, 1]],
+ [-1, 1, nn.Upsample, [None, 2, 'nearest']],
+ [[-1, 4], 1, Concat, [1]], # cat backbone P3
+ [-1, 3, C3, [256, False]], # 29 (P3/8-small)
+
+ [-1, 1, Conv, [256, 3, 2]],
+ [[-1, 26], 1, Concat, [1]], # cat head P4
+ [-1, 3, C3, [512, False]], # 32 (P4/16-medium)
+
+ [-1, 1, Conv, [512, 3, 2]],
+ [[-1, 22], 1, Concat, [1]], # cat head P5
+ [-1, 3, C3, [768, False]], # 35 (P5/32-large)
+
+ [-1, 1, Conv, [768, 3, 2]],
+ [[-1, 18], 1, Concat, [1]], # cat head P6
+ [-1, 3, C3, [1024, False]], # 38 (P6/64-xlarge)
+
+ [-1, 1, Conv, [1024, 3, 2]],
+ [[-1, 14], 1, Concat, [1]], # cat head P7
+ [-1, 3, C3, [1280, False]], # 41 (P7/128-xxlarge)
+
+ [[29, 32, 35, 38, 41], 1, Detect, [nc, anchors]], # Detect(P3, P4, P5, P6, P7)
+ ]
diff --git a/ros2_ws/src/yolov3_ros/models/hub/yolov5-panet.yaml b/ros2_ws/src/yolov3_ros/models/hub/yolov5-panet.yaml
new file mode 100644
index 00000000..9a9a34dd
--- /dev/null
+++ b/ros2_ws/src/yolov3_ros/models/hub/yolov5-panet.yaml
@@ -0,0 +1,48 @@
+# YOLOv3 🚀 by Ultralytics, GPL-3.0 license
+
+# Parameters
+nc: 80 # number of classes
+depth_multiple: 1.0 # model depth multiple
+width_multiple: 1.0 # layer channel multiple
+anchors:
+ - [10,13, 16,30, 33,23] # P3/8
+ - [30,61, 62,45, 59,119] # P4/16
+ - [116,90, 156,198, 373,326] # P5/32
+
+# YOLOv5 v6.0 backbone
+backbone:
+ # [from, number, module, args]
+ [[-1, 1, Conv, [64, 6, 2, 2]], # 0-P1/2
+ [-1, 1, Conv, [128, 3, 2]], # 1-P2/4
+ [-1, 3, C3, [128]],
+ [-1, 1, Conv, [256, 3, 2]], # 3-P3/8
+ [-1, 6, C3, [256]],
+ [-1, 1, Conv, [512, 3, 2]], # 5-P4/16
+ [-1, 9, C3, [512]],
+ [-1, 1, Conv, [1024, 3, 2]], # 7-P5/32
+ [-1, 3, C3, [1024]],
+ [-1, 1, SPPF, [1024, 5]], # 9
+ ]
+
+# YOLOv5 v6.0 PANet head
+head:
+ [[-1, 1, Conv, [512, 1, 1]],
+ [-1, 1, nn.Upsample, [None, 2, 'nearest']],
+ [[-1, 6], 1, Concat, [1]], # cat backbone P4
+ [-1, 3, C3, [512, False]], # 13
+
+ [-1, 1, Conv, [256, 1, 1]],
+ [-1, 1, nn.Upsample, [None, 2, 'nearest']],
+ [[-1, 4], 1, Concat, [1]], # cat backbone P3
+ [-1, 3, C3, [256, False]], # 17 (P3/8-small)
+
+ [-1, 1, Conv, [256, 3, 2]],
+ [[-1, 14], 1, Concat, [1]], # cat head P4
+ [-1, 3, C3, [512, False]], # 20 (P4/16-medium)
+
+ [-1, 1, Conv, [512, 3, 2]],
+ [[-1, 10], 1, Concat, [1]], # cat head P5
+ [-1, 3, C3, [1024, False]], # 23 (P5/32-large)
+
+ [[17, 20, 23], 1, Detect, [nc, anchors]], # Detect(P3, P4, P5)
+ ]
diff --git a/ros2_ws/src/yolov3_ros/models/hub/yolov5l6.yaml b/ros2_ws/src/yolov3_ros/models/hub/yolov5l6.yaml
new file mode 100644
index 00000000..e9f03b34
--- /dev/null
+++ b/ros2_ws/src/yolov3_ros/models/hub/yolov5l6.yaml
@@ -0,0 +1,60 @@
+# YOLOv3 🚀 by Ultralytics, GPL-3.0 license
+
+# Parameters
+nc: 80 # number of classes
+depth_multiple: 1.0 # model depth multiple
+width_multiple: 1.0 # layer channel multiple
+anchors:
+ - [19,27, 44,40, 38,94] # P3/8
+ - [96,68, 86,152, 180,137] # P4/16
+ - [140,301, 303,264, 238,542] # P5/32
+ - [436,615, 739,380, 925,792] # P6/64
+
+# YOLOv5 v6.0 backbone
+backbone:
+ # [from, number, module, args]
+ [[-1, 1, Conv, [64, 6, 2, 2]], # 0-P1/2
+ [-1, 1, Conv, [128, 3, 2]], # 1-P2/4
+ [-1, 3, C3, [128]],
+ [-1, 1, Conv, [256, 3, 2]], # 3-P3/8
+ [-1, 6, C3, [256]],
+ [-1, 1, Conv, [512, 3, 2]], # 5-P4/16
+ [-1, 9, C3, [512]],
+ [-1, 1, Conv, [768, 3, 2]], # 7-P5/32
+ [-1, 3, C3, [768]],
+ [-1, 1, Conv, [1024, 3, 2]], # 9-P6/64
+ [-1, 3, C3, [1024]],
+ [-1, 1, SPPF, [1024, 5]], # 11
+ ]
+
+# YOLOv5 v6.0 head
+head:
+ [[-1, 1, Conv, [768, 1, 1]],
+ [-1, 1, nn.Upsample, [None, 2, 'nearest']],
+ [[-1, 8], 1, Concat, [1]], # cat backbone P5
+ [-1, 3, C3, [768, False]], # 15
+
+ [-1, 1, Conv, [512, 1, 1]],
+ [-1, 1, nn.Upsample, [None, 2, 'nearest']],
+ [[-1, 6], 1, Concat, [1]], # cat backbone P4
+ [-1, 3, C3, [512, False]], # 19
+
+ [-1, 1, Conv, [256, 1, 1]],
+ [-1, 1, nn.Upsample, [None, 2, 'nearest']],
+ [[-1, 4], 1, Concat, [1]], # cat backbone P3
+ [-1, 3, C3, [256, False]], # 23 (P3/8-small)
+
+ [-1, 1, Conv, [256, 3, 2]],
+ [[-1, 20], 1, Concat, [1]], # cat head P4
+ [-1, 3, C3, [512, False]], # 26 (P4/16-medium)
+
+ [-1, 1, Conv, [512, 3, 2]],
+ [[-1, 16], 1, Concat, [1]], # cat head P5
+ [-1, 3, C3, [768, False]], # 29 (P5/32-large)
+
+ [-1, 1, Conv, [768, 3, 2]],
+ [[-1, 12], 1, Concat, [1]], # cat head P6
+ [-1, 3, C3, [1024, False]], # 32 (P6/64-xlarge)
+
+ [[23, 26, 29, 32], 1, Detect, [nc, anchors]], # Detect(P3, P4, P5, P6)
+ ]
diff --git a/ros2_ws/src/yolov3_ros/models/hub/yolov5m6.yaml b/ros2_ws/src/yolov3_ros/models/hub/yolov5m6.yaml
new file mode 100644
index 00000000..7077be1a
--- /dev/null
+++ b/ros2_ws/src/yolov3_ros/models/hub/yolov5m6.yaml
@@ -0,0 +1,60 @@
+# YOLOv3 🚀 by Ultralytics, GPL-3.0 license
+
+# Parameters
+nc: 80 # number of classes
+depth_multiple: 0.67 # model depth multiple
+width_multiple: 0.75 # layer channel multiple
+anchors:
+ - [19,27, 44,40, 38,94] # P3/8
+ - [96,68, 86,152, 180,137] # P4/16
+ - [140,301, 303,264, 238,542] # P5/32
+ - [436,615, 739,380, 925,792] # P6/64
+
+# YOLOv5 v6.0 backbone
+backbone:
+ # [from, number, module, args]
+ [[-1, 1, Conv, [64, 6, 2, 2]], # 0-P1/2
+ [-1, 1, Conv, [128, 3, 2]], # 1-P2/4
+ [-1, 3, C3, [128]],
+ [-1, 1, Conv, [256, 3, 2]], # 3-P3/8
+ [-1, 6, C3, [256]],
+ [-1, 1, Conv, [512, 3, 2]], # 5-P4/16
+ [-1, 9, C3, [512]],
+ [-1, 1, Conv, [768, 3, 2]], # 7-P5/32
+ [-1, 3, C3, [768]],
+ [-1, 1, Conv, [1024, 3, 2]], # 9-P6/64
+ [-1, 3, C3, [1024]],
+ [-1, 1, SPPF, [1024, 5]], # 11
+ ]
+
+# YOLOv5 v6.0 head
+head:
+ [[-1, 1, Conv, [768, 1, 1]],
+ [-1, 1, nn.Upsample, [None, 2, 'nearest']],
+ [[-1, 8], 1, Concat, [1]], # cat backbone P5
+ [-1, 3, C3, [768, False]], # 15
+
+ [-1, 1, Conv, [512, 1, 1]],
+ [-1, 1, nn.Upsample, [None, 2, 'nearest']],
+ [[-1, 6], 1, Concat, [1]], # cat backbone P4
+ [-1, 3, C3, [512, False]], # 19
+
+ [-1, 1, Conv, [256, 1, 1]],
+ [-1, 1, nn.Upsample, [None, 2, 'nearest']],
+ [[-1, 4], 1, Concat, [1]], # cat backbone P3
+ [-1, 3, C3, [256, False]], # 23 (P3/8-small)
+
+ [-1, 1, Conv, [256, 3, 2]],
+ [[-1, 20], 1, Concat, [1]], # cat head P4
+ [-1, 3, C3, [512, False]], # 26 (P4/16-medium)
+
+ [-1, 1, Conv, [512, 3, 2]],
+ [[-1, 16], 1, Concat, [1]], # cat head P5
+ [-1, 3, C3, [768, False]], # 29 (P5/32-large)
+
+ [-1, 1, Conv, [768, 3, 2]],
+ [[-1, 12], 1, Concat, [1]], # cat head P6
+ [-1, 3, C3, [1024, False]], # 32 (P6/64-xlarge)
+
+ [[23, 26, 29, 32], 1, Detect, [nc, anchors]], # Detect(P3, P4, P5, P6)
+ ]
diff --git a/ros2_ws/src/yolov3_ros/models/hub/yolov5n6.yaml b/ros2_ws/src/yolov3_ros/models/hub/yolov5n6.yaml
new file mode 100644
index 00000000..2b4374c8
--- /dev/null
+++ b/ros2_ws/src/yolov3_ros/models/hub/yolov5n6.yaml
@@ -0,0 +1,60 @@
+# YOLOv3 🚀 by Ultralytics, GPL-3.0 license
+
+# Parameters
+nc: 80 # number of classes
+depth_multiple: 0.33 # model depth multiple
+width_multiple: 0.25 # layer channel multiple
+anchors:
+ - [19,27, 44,40, 38,94] # P3/8
+ - [96,68, 86,152, 180,137] # P4/16
+ - [140,301, 303,264, 238,542] # P5/32
+ - [436,615, 739,380, 925,792] # P6/64
+
+# YOLOv5 v6.0 backbone
+backbone:
+ # [from, number, module, args]
+ [[-1, 1, Conv, [64, 6, 2, 2]], # 0-P1/2
+ [-1, 1, Conv, [128, 3, 2]], # 1-P2/4
+ [-1, 3, C3, [128]],
+ [-1, 1, Conv, [256, 3, 2]], # 3-P3/8
+ [-1, 6, C3, [256]],
+ [-1, 1, Conv, [512, 3, 2]], # 5-P4/16
+ [-1, 9, C3, [512]],
+ [-1, 1, Conv, [768, 3, 2]], # 7-P5/32
+ [-1, 3, C3, [768]],
+ [-1, 1, Conv, [1024, 3, 2]], # 9-P6/64
+ [-1, 3, C3, [1024]],
+ [-1, 1, SPPF, [1024, 5]], # 11
+ ]
+
+# YOLOv5 v6.0 head
+head:
+ [[-1, 1, Conv, [768, 1, 1]],
+ [-1, 1, nn.Upsample, [None, 2, 'nearest']],
+ [[-1, 8], 1, Concat, [1]], # cat backbone P5
+ [-1, 3, C3, [768, False]], # 15
+
+ [-1, 1, Conv, [512, 1, 1]],
+ [-1, 1, nn.Upsample, [None, 2, 'nearest']],
+ [[-1, 6], 1, Concat, [1]], # cat backbone P4
+ [-1, 3, C3, [512, False]], # 19
+
+ [-1, 1, Conv, [256, 1, 1]],
+ [-1, 1, nn.Upsample, [None, 2, 'nearest']],
+ [[-1, 4], 1, Concat, [1]], # cat backbone P3
+ [-1, 3, C3, [256, False]], # 23 (P3/8-small)
+
+ [-1, 1, Conv, [256, 3, 2]],
+ [[-1, 20], 1, Concat, [1]], # cat head P4
+ [-1, 3, C3, [512, False]], # 26 (P4/16-medium)
+
+ [-1, 1, Conv, [512, 3, 2]],
+ [[-1, 16], 1, Concat, [1]], # cat head P5
+ [-1, 3, C3, [768, False]], # 29 (P5/32-large)
+
+ [-1, 1, Conv, [768, 3, 2]],
+ [[-1, 12], 1, Concat, [1]], # cat head P6
+ [-1, 3, C3, [1024, False]], # 32 (P6/64-xlarge)
+
+ [[23, 26, 29, 32], 1, Detect, [nc, anchors]], # Detect(P3, P4, P5, P6)
+ ]
diff --git a/ros2_ws/src/yolov3_ros/models/hub/yolov5s-LeakyReLU.yaml b/ros2_ws/src/yolov3_ros/models/hub/yolov5s-LeakyReLU.yaml
new file mode 100644
index 00000000..0d3dbc0d
--- /dev/null
+++ b/ros2_ws/src/yolov3_ros/models/hub/yolov5s-LeakyReLU.yaml
@@ -0,0 +1,49 @@
+# YOLOv3 🚀 by Ultralytics, GPL-3.0 license
+
+# Parameters
+nc: 80 # number of classes
+activation: nn.LeakyReLU(0.1) # <----- Conv() activation used throughout entire YOLOv5 model
+depth_multiple: 0.33 # model depth multiple
+width_multiple: 0.50 # layer channel multiple
+anchors:
+ - [10,13, 16,30, 33,23] # P3/8
+ - [30,61, 62,45, 59,119] # P4/16
+ - [116,90, 156,198, 373,326] # P5/32
+
+# YOLOv5 v6.0 backbone
+backbone:
+ # [from, number, module, args]
+ [[-1, 1, Conv, [64, 6, 2, 2]], # 0-P1/2
+ [-1, 1, Conv, [128, 3, 2]], # 1-P2/4
+ [-1, 3, C3, [128]],
+ [-1, 1, Conv, [256, 3, 2]], # 3-P3/8
+ [-1, 6, C3, [256]],
+ [-1, 1, Conv, [512, 3, 2]], # 5-P4/16
+ [-1, 9, C3, [512]],
+ [-1, 1, Conv, [1024, 3, 2]], # 7-P5/32
+ [-1, 3, C3, [1024]],
+ [-1, 1, SPPF, [1024, 5]], # 9
+ ]
+
+# YOLOv5 v6.0 head
+head:
+ [[-1, 1, Conv, [512, 1, 1]],
+ [-1, 1, nn.Upsample, [None, 2, 'nearest']],
+ [[-1, 6], 1, Concat, [1]], # cat backbone P4
+ [-1, 3, C3, [512, False]], # 13
+
+ [-1, 1, Conv, [256, 1, 1]],
+ [-1, 1, nn.Upsample, [None, 2, 'nearest']],
+ [[-1, 4], 1, Concat, [1]], # cat backbone P3
+ [-1, 3, C3, [256, False]], # 17 (P3/8-small)
+
+ [-1, 1, Conv, [256, 3, 2]],
+ [[-1, 14], 1, Concat, [1]], # cat head P4
+ [-1, 3, C3, [512, False]], # 20 (P4/16-medium)
+
+ [-1, 1, Conv, [512, 3, 2]],
+ [[-1, 10], 1, Concat, [1]], # cat head P5
+ [-1, 3, C3, [1024, False]], # 23 (P5/32-large)
+
+ [[17, 20, 23], 1, Detect, [nc, anchors]], # Detect(P3, P4, P5)
+ ]
diff --git a/ros2_ws/src/yolov3_ros/models/hub/yolov5s-ghost.yaml b/ros2_ws/src/yolov3_ros/models/hub/yolov5s-ghost.yaml
new file mode 100644
index 00000000..e8bbcfe3
--- /dev/null
+++ b/ros2_ws/src/yolov3_ros/models/hub/yolov5s-ghost.yaml
@@ -0,0 +1,48 @@
+# YOLOv3 🚀 by Ultralytics, GPL-3.0 license
+
+# Parameters
+nc: 80 # number of classes
+depth_multiple: 0.33 # model depth multiple
+width_multiple: 0.50 # layer channel multiple
+anchors:
+ - [10,13, 16,30, 33,23] # P3/8
+ - [30,61, 62,45, 59,119] # P4/16
+ - [116,90, 156,198, 373,326] # P5/32
+
+# YOLOv5 v6.0 backbone
+backbone:
+ # [from, number, module, args]
+ [[-1, 1, Conv, [64, 6, 2, 2]], # 0-P1/2
+ [-1, 1, GhostConv, [128, 3, 2]], # 1-P2/4
+ [-1, 3, C3Ghost, [128]],
+ [-1, 1, GhostConv, [256, 3, 2]], # 3-P3/8
+ [-1, 6, C3Ghost, [256]],
+ [-1, 1, GhostConv, [512, 3, 2]], # 5-P4/16
+ [-1, 9, C3Ghost, [512]],
+ [-1, 1, GhostConv, [1024, 3, 2]], # 7-P5/32
+ [-1, 3, C3Ghost, [1024]],
+ [-1, 1, SPPF, [1024, 5]], # 9
+ ]
+
+# YOLOv5 v6.0 head
+head:
+ [[-1, 1, GhostConv, [512, 1, 1]],
+ [-1, 1, nn.Upsample, [None, 2, 'nearest']],
+ [[-1, 6], 1, Concat, [1]], # cat backbone P4
+ [-1, 3, C3Ghost, [512, False]], # 13
+
+ [-1, 1, GhostConv, [256, 1, 1]],
+ [-1, 1, nn.Upsample, [None, 2, 'nearest']],
+ [[-1, 4], 1, Concat, [1]], # cat backbone P3
+ [-1, 3, C3Ghost, [256, False]], # 17 (P3/8-small)
+
+ [-1, 1, GhostConv, [256, 3, 2]],
+ [[-1, 14], 1, Concat, [1]], # cat head P4
+ [-1, 3, C3Ghost, [512, False]], # 20 (P4/16-medium)
+
+ [-1, 1, GhostConv, [512, 3, 2]],
+ [[-1, 10], 1, Concat, [1]], # cat head P5
+ [-1, 3, C3Ghost, [1024, False]], # 23 (P5/32-large)
+
+ [[17, 20, 23], 1, Detect, [nc, anchors]], # Detect(P3, P4, P5)
+ ]
diff --git a/ros2_ws/src/yolov3_ros/models/hub/yolov5s-transformer.yaml b/ros2_ws/src/yolov3_ros/models/hub/yolov5s-transformer.yaml
new file mode 100644
index 00000000..a0a3ce8e
--- /dev/null
+++ b/ros2_ws/src/yolov3_ros/models/hub/yolov5s-transformer.yaml
@@ -0,0 +1,48 @@
+# YOLOv3 🚀 by Ultralytics, GPL-3.0 license
+
+# Parameters
+nc: 80 # number of classes
+depth_multiple: 0.33 # model depth multiple
+width_multiple: 0.50 # layer channel multiple
+anchors:
+ - [10,13, 16,30, 33,23] # P3/8
+ - [30,61, 62,45, 59,119] # P4/16
+ - [116,90, 156,198, 373,326] # P5/32
+
+# YOLOv5 v6.0 backbone
+backbone:
+ # [from, number, module, args]
+ [[-1, 1, Conv, [64, 6, 2, 2]], # 0-P1/2
+ [-1, 1, Conv, [128, 3, 2]], # 1-P2/4
+ [-1, 3, C3, [128]],
+ [-1, 1, Conv, [256, 3, 2]], # 3-P3/8
+ [-1, 6, C3, [256]],
+ [-1, 1, Conv, [512, 3, 2]], # 5-P4/16
+ [-1, 9, C3, [512]],
+ [-1, 1, Conv, [1024, 3, 2]], # 7-P5/32
+ [-1, 3, C3TR, [1024]], # 9 <--- C3TR() Transformer module
+ [-1, 1, SPPF, [1024, 5]], # 9
+ ]
+
+# YOLOv5 v6.0 head
+head:
+ [[-1, 1, Conv, [512, 1, 1]],
+ [-1, 1, nn.Upsample, [None, 2, 'nearest']],
+ [[-1, 6], 1, Concat, [1]], # cat backbone P4
+ [-1, 3, C3, [512, False]], # 13
+
+ [-1, 1, Conv, [256, 1, 1]],
+ [-1, 1, nn.Upsample, [None, 2, 'nearest']],
+ [[-1, 4], 1, Concat, [1]], # cat backbone P3
+ [-1, 3, C3, [256, False]], # 17 (P3/8-small)
+
+ [-1, 1, Conv, [256, 3, 2]],
+ [[-1, 14], 1, Concat, [1]], # cat head P4
+ [-1, 3, C3, [512, False]], # 20 (P4/16-medium)
+
+ [-1, 1, Conv, [512, 3, 2]],
+ [[-1, 10], 1, Concat, [1]], # cat head P5
+ [-1, 3, C3, [1024, False]], # 23 (P5/32-large)
+
+ [[17, 20, 23], 1, Detect, [nc, anchors]], # Detect(P3, P4, P5)
+ ]
diff --git a/ros2_ws/src/yolov3_ros/models/hub/yolov5s6.yaml b/ros2_ws/src/yolov3_ros/models/hub/yolov5s6.yaml
new file mode 100644
index 00000000..85f3ef5a
--- /dev/null
+++ b/ros2_ws/src/yolov3_ros/models/hub/yolov5s6.yaml
@@ -0,0 +1,60 @@
+# YOLOv3 🚀 by Ultralytics, GPL-3.0 license
+
+# Parameters
+nc: 80 # number of classes
+depth_multiple: 0.33 # model depth multiple
+width_multiple: 0.50 # layer channel multiple
+anchors:
+ - [19,27, 44,40, 38,94] # P3/8
+ - [96,68, 86,152, 180,137] # P4/16
+ - [140,301, 303,264, 238,542] # P5/32
+ - [436,615, 739,380, 925,792] # P6/64
+
+# YOLOv5 v6.0 backbone
+backbone:
+ # [from, number, module, args]
+ [[-1, 1, Conv, [64, 6, 2, 2]], # 0-P1/2
+ [-1, 1, Conv, [128, 3, 2]], # 1-P2/4
+ [-1, 3, C3, [128]],
+ [-1, 1, Conv, [256, 3, 2]], # 3-P3/8
+ [-1, 6, C3, [256]],
+ [-1, 1, Conv, [512, 3, 2]], # 5-P4/16
+ [-1, 9, C3, [512]],
+ [-1, 1, Conv, [768, 3, 2]], # 7-P5/32
+ [-1, 3, C3, [768]],
+ [-1, 1, Conv, [1024, 3, 2]], # 9-P6/64
+ [-1, 3, C3, [1024]],
+ [-1, 1, SPPF, [1024, 5]], # 11
+ ]
+
+# YOLOv5 v6.0 head
+head:
+ [[-1, 1, Conv, [768, 1, 1]],
+ [-1, 1, nn.Upsample, [None, 2, 'nearest']],
+ [[-1, 8], 1, Concat, [1]], # cat backbone P5
+ [-1, 3, C3, [768, False]], # 15
+
+ [-1, 1, Conv, [512, 1, 1]],
+ [-1, 1, nn.Upsample, [None, 2, 'nearest']],
+ [[-1, 6], 1, Concat, [1]], # cat backbone P4
+ [-1, 3, C3, [512, False]], # 19
+
+ [-1, 1, Conv, [256, 1, 1]],
+ [-1, 1, nn.Upsample, [None, 2, 'nearest']],
+ [[-1, 4], 1, Concat, [1]], # cat backbone P3
+ [-1, 3, C3, [256, False]], # 23 (P3/8-small)
+
+ [-1, 1, Conv, [256, 3, 2]],
+ [[-1, 20], 1, Concat, [1]], # cat head P4
+ [-1, 3, C3, [512, False]], # 26 (P4/16-medium)
+
+ [-1, 1, Conv, [512, 3, 2]],
+ [[-1, 16], 1, Concat, [1]], # cat head P5
+ [-1, 3, C3, [768, False]], # 29 (P5/32-large)
+
+ [-1, 1, Conv, [768, 3, 2]],
+ [[-1, 12], 1, Concat, [1]], # cat head P6
+ [-1, 3, C3, [1024, False]], # 32 (P6/64-xlarge)
+
+ [[23, 26, 29, 32], 1, Detect, [nc, anchors]], # Detect(P3, P4, P5, P6)
+ ]
diff --git a/ros2_ws/src/yolov3_ros/models/hub/yolov5x6.yaml b/ros2_ws/src/yolov3_ros/models/hub/yolov5x6.yaml
new file mode 100644
index 00000000..290da47d
--- /dev/null
+++ b/ros2_ws/src/yolov3_ros/models/hub/yolov5x6.yaml
@@ -0,0 +1,60 @@
+# YOLOv3 🚀 by Ultralytics, GPL-3.0 license
+
+# Parameters
+nc: 80 # number of classes
+depth_multiple: 1.33 # model depth multiple
+width_multiple: 1.25 # layer channel multiple
+anchors:
+ - [19,27, 44,40, 38,94] # P3/8
+ - [96,68, 86,152, 180,137] # P4/16
+ - [140,301, 303,264, 238,542] # P5/32
+ - [436,615, 739,380, 925,792] # P6/64
+
+# YOLOv5 v6.0 backbone
+backbone:
+ # [from, number, module, args]
+ [[-1, 1, Conv, [64, 6, 2, 2]], # 0-P1/2
+ [-1, 1, Conv, [128, 3, 2]], # 1-P2/4
+ [-1, 3, C3, [128]],
+ [-1, 1, Conv, [256, 3, 2]], # 3-P3/8
+ [-1, 6, C3, [256]],
+ [-1, 1, Conv, [512, 3, 2]], # 5-P4/16
+ [-1, 9, C3, [512]],
+ [-1, 1, Conv, [768, 3, 2]], # 7-P5/32
+ [-1, 3, C3, [768]],
+ [-1, 1, Conv, [1024, 3, 2]], # 9-P6/64
+ [-1, 3, C3, [1024]],
+ [-1, 1, SPPF, [1024, 5]], # 11
+ ]
+
+# YOLOv5 v6.0 head
+head:
+ [[-1, 1, Conv, [768, 1, 1]],
+ [-1, 1, nn.Upsample, [None, 2, 'nearest']],
+ [[-1, 8], 1, Concat, [1]], # cat backbone P5
+ [-1, 3, C3, [768, False]], # 15
+
+ [-1, 1, Conv, [512, 1, 1]],
+ [-1, 1, nn.Upsample, [None, 2, 'nearest']],
+ [[-1, 6], 1, Concat, [1]], # cat backbone P4
+ [-1, 3, C3, [512, False]], # 19
+
+ [-1, 1, Conv, [256, 1, 1]],
+ [-1, 1, nn.Upsample, [None, 2, 'nearest']],
+ [[-1, 4], 1, Concat, [1]], # cat backbone P3
+ [-1, 3, C3, [256, False]], # 23 (P3/8-small)
+
+ [-1, 1, Conv, [256, 3, 2]],
+ [[-1, 20], 1, Concat, [1]], # cat head P4
+ [-1, 3, C3, [512, False]], # 26 (P4/16-medium)
+
+ [-1, 1, Conv, [512, 3, 2]],
+ [[-1, 16], 1, Concat, [1]], # cat head P5
+ [-1, 3, C3, [768, False]], # 29 (P5/32-large)
+
+ [-1, 1, Conv, [768, 3, 2]],
+ [[-1, 12], 1, Concat, [1]], # cat head P6
+ [-1, 3, C3, [1024, False]], # 32 (P6/64-xlarge)
+
+ [[23, 26, 29, 32], 1, Detect, [nc, anchors]], # Detect(P3, P4, P5, P6)
+ ]
diff --git a/ros2_ws/src/yolov3_ros/models/segment/yolov5l-seg.yaml b/ros2_ws/src/yolov3_ros/models/segment/yolov5l-seg.yaml
new file mode 100644
index 00000000..ac06eb87
--- /dev/null
+++ b/ros2_ws/src/yolov3_ros/models/segment/yolov5l-seg.yaml
@@ -0,0 +1,48 @@
+# YOLOv3 🚀 by Ultralytics, GPL-3.0 license
+
+# Parameters
+nc: 80 # number of classes
+depth_multiple: 1.0 # model depth multiple
+width_multiple: 1.0 # layer channel multiple
+anchors:
+ - [10,13, 16,30, 33,23] # P3/8
+ - [30,61, 62,45, 59,119] # P4/16
+ - [116,90, 156,198, 373,326] # P5/32
+
+# YOLOv5 v6.0 backbone
+backbone:
+ # [from, number, module, args]
+ [[-1, 1, Conv, [64, 6, 2, 2]], # 0-P1/2
+ [-1, 1, Conv, [128, 3, 2]], # 1-P2/4
+ [-1, 3, C3, [128]],
+ [-1, 1, Conv, [256, 3, 2]], # 3-P3/8
+ [-1, 6, C3, [256]],
+ [-1, 1, Conv, [512, 3, 2]], # 5-P4/16
+ [-1, 9, C3, [512]],
+ [-1, 1, Conv, [1024, 3, 2]], # 7-P5/32
+ [-1, 3, C3, [1024]],
+ [-1, 1, SPPF, [1024, 5]], # 9
+ ]
+
+# YOLOv5 v6.0 head
+head:
+ [[-1, 1, Conv, [512, 1, 1]],
+ [-1, 1, nn.Upsample, [None, 2, 'nearest']],
+ [[-1, 6], 1, Concat, [1]], # cat backbone P4
+ [-1, 3, C3, [512, False]], # 13
+
+ [-1, 1, Conv, [256, 1, 1]],
+ [-1, 1, nn.Upsample, [None, 2, 'nearest']],
+ [[-1, 4], 1, Concat, [1]], # cat backbone P3
+ [-1, 3, C3, [256, False]], # 17 (P3/8-small)
+
+ [-1, 1, Conv, [256, 3, 2]],
+ [[-1, 14], 1, Concat, [1]], # cat head P4
+ [-1, 3, C3, [512, False]], # 20 (P4/16-medium)
+
+ [-1, 1, Conv, [512, 3, 2]],
+ [[-1, 10], 1, Concat, [1]], # cat head P5
+ [-1, 3, C3, [1024, False]], # 23 (P5/32-large)
+
+ [[17, 20, 23], 1, Segment, [nc, anchors, 32, 256]], # Detect(P3, P4, P5)
+ ]
diff --git a/ros2_ws/src/yolov3_ros/models/segment/yolov5m-seg.yaml b/ros2_ws/src/yolov3_ros/models/segment/yolov5m-seg.yaml
new file mode 100644
index 00000000..cafadcd9
--- /dev/null
+++ b/ros2_ws/src/yolov3_ros/models/segment/yolov5m-seg.yaml
@@ -0,0 +1,48 @@
+# YOLOv3 🚀 by Ultralytics, GPL-3.0 license
+
+# Parameters
+nc: 80 # number of classes
+depth_multiple: 0.67 # model depth multiple
+width_multiple: 0.75 # layer channel multiple
+anchors:
+ - [10,13, 16,30, 33,23] # P3/8
+ - [30,61, 62,45, 59,119] # P4/16
+ - [116,90, 156,198, 373,326] # P5/32
+
+# YOLOv5 v6.0 backbone
+backbone:
+ # [from, number, module, args]
+ [[-1, 1, Conv, [64, 6, 2, 2]], # 0-P1/2
+ [-1, 1, Conv, [128, 3, 2]], # 1-P2/4
+ [-1, 3, C3, [128]],
+ [-1, 1, Conv, [256, 3, 2]], # 3-P3/8
+ [-1, 6, C3, [256]],
+ [-1, 1, Conv, [512, 3, 2]], # 5-P4/16
+ [-1, 9, C3, [512]],
+ [-1, 1, Conv, [1024, 3, 2]], # 7-P5/32
+ [-1, 3, C3, [1024]],
+ [-1, 1, SPPF, [1024, 5]], # 9
+ ]
+
+# YOLOv5 v6.0 head
+head:
+ [[-1, 1, Conv, [512, 1, 1]],
+ [-1, 1, nn.Upsample, [None, 2, 'nearest']],
+ [[-1, 6], 1, Concat, [1]], # cat backbone P4
+ [-1, 3, C3, [512, False]], # 13
+
+ [-1, 1, Conv, [256, 1, 1]],
+ [-1, 1, nn.Upsample, [None, 2, 'nearest']],
+ [[-1, 4], 1, Concat, [1]], # cat backbone P3
+ [-1, 3, C3, [256, False]], # 17 (P3/8-small)
+
+ [-1, 1, Conv, [256, 3, 2]],
+ [[-1, 14], 1, Concat, [1]], # cat head P4
+ [-1, 3, C3, [512, False]], # 20 (P4/16-medium)
+
+ [-1, 1, Conv, [512, 3, 2]],
+ [[-1, 10], 1, Concat, [1]], # cat head P5
+ [-1, 3, C3, [1024, False]], # 23 (P5/32-large)
+
+ [[17, 20, 23], 1, Segment, [nc, anchors, 32, 256]], # Detect(P3, P4, P5)
+ ]
diff --git a/ros2_ws/src/yolov3_ros/models/segment/yolov5n-seg.yaml b/ros2_ws/src/yolov3_ros/models/segment/yolov5n-seg.yaml
new file mode 100644
index 00000000..21635c3c
--- /dev/null
+++ b/ros2_ws/src/yolov3_ros/models/segment/yolov5n-seg.yaml
@@ -0,0 +1,48 @@
+# YOLOv3 🚀 by Ultralytics, GPL-3.0 license
+
+# Parameters
+nc: 80 # number of classes
+depth_multiple: 0.33 # model depth multiple
+width_multiple: 0.25 # layer channel multiple
+anchors:
+ - [10,13, 16,30, 33,23] # P3/8
+ - [30,61, 62,45, 59,119] # P4/16
+ - [116,90, 156,198, 373,326] # P5/32
+
+# YOLOv5 v6.0 backbone
+backbone:
+ # [from, number, module, args]
+ [[-1, 1, Conv, [64, 6, 2, 2]], # 0-P1/2
+ [-1, 1, Conv, [128, 3, 2]], # 1-P2/4
+ [-1, 3, C3, [128]],
+ [-1, 1, Conv, [256, 3, 2]], # 3-P3/8
+ [-1, 6, C3, [256]],
+ [-1, 1, Conv, [512, 3, 2]], # 5-P4/16
+ [-1, 9, C3, [512]],
+ [-1, 1, Conv, [1024, 3, 2]], # 7-P5/32
+ [-1, 3, C3, [1024]],
+ [-1, 1, SPPF, [1024, 5]], # 9
+ ]
+
+# YOLOv5 v6.0 head
+head:
+ [[-1, 1, Conv, [512, 1, 1]],
+ [-1, 1, nn.Upsample, [None, 2, 'nearest']],
+ [[-1, 6], 1, Concat, [1]], # cat backbone P4
+ [-1, 3, C3, [512, False]], # 13
+
+ [-1, 1, Conv, [256, 1, 1]],
+ [-1, 1, nn.Upsample, [None, 2, 'nearest']],
+ [[-1, 4], 1, Concat, [1]], # cat backbone P3
+ [-1, 3, C3, [256, False]], # 17 (P3/8-small)
+
+ [-1, 1, Conv, [256, 3, 2]],
+ [[-1, 14], 1, Concat, [1]], # cat head P4
+ [-1, 3, C3, [512, False]], # 20 (P4/16-medium)
+
+ [-1, 1, Conv, [512, 3, 2]],
+ [[-1, 10], 1, Concat, [1]], # cat head P5
+ [-1, 3, C3, [1024, False]], # 23 (P5/32-large)
+
+ [[17, 20, 23], 1, Segment, [nc, anchors, 32, 256]], # Detect(P3, P4, P5)
+ ]
diff --git a/ros2_ws/src/yolov3_ros/models/segment/yolov5s-seg.yaml b/ros2_ws/src/yolov3_ros/models/segment/yolov5s-seg.yaml
new file mode 100644
index 00000000..6018cdb4
--- /dev/null
+++ b/ros2_ws/src/yolov3_ros/models/segment/yolov5s-seg.yaml
@@ -0,0 +1,48 @@
+# YOLOv3 🚀 by Ultralytics, GPL-3.0 license
+
+# Parameters
+nc: 80 # number of classes
+depth_multiple: 0.33 # model depth multiple
+width_multiple: 0.5 # layer channel multiple
+anchors:
+ - [10,13, 16,30, 33,23] # P3/8
+ - [30,61, 62,45, 59,119] # P4/16
+ - [116,90, 156,198, 373,326] # P5/32
+
+# YOLOv5 v6.0 backbone
+backbone:
+ # [from, number, module, args]
+ [[-1, 1, Conv, [64, 6, 2, 2]], # 0-P1/2
+ [-1, 1, Conv, [128, 3, 2]], # 1-P2/4
+ [-1, 3, C3, [128]],
+ [-1, 1, Conv, [256, 3, 2]], # 3-P3/8
+ [-1, 6, C3, [256]],
+ [-1, 1, Conv, [512, 3, 2]], # 5-P4/16
+ [-1, 9, C3, [512]],
+ [-1, 1, Conv, [1024, 3, 2]], # 7-P5/32
+ [-1, 3, C3, [1024]],
+ [-1, 1, SPPF, [1024, 5]], # 9
+ ]
+
+# YOLOv5 v6.0 head
+head:
+ [[-1, 1, Conv, [512, 1, 1]],
+ [-1, 1, nn.Upsample, [None, 2, 'nearest']],
+ [[-1, 6], 1, Concat, [1]], # cat backbone P4
+ [-1, 3, C3, [512, False]], # 13
+
+ [-1, 1, Conv, [256, 1, 1]],
+ [-1, 1, nn.Upsample, [None, 2, 'nearest']],
+ [[-1, 4], 1, Concat, [1]], # cat backbone P3
+ [-1, 3, C3, [256, False]], # 17 (P3/8-small)
+
+ [-1, 1, Conv, [256, 3, 2]],
+ [[-1, 14], 1, Concat, [1]], # cat head P4
+ [-1, 3, C3, [512, False]], # 20 (P4/16-medium)
+
+ [-1, 1, Conv, [512, 3, 2]],
+ [[-1, 10], 1, Concat, [1]], # cat head P5
+ [-1, 3, C3, [1024, False]], # 23 (P5/32-large)
+
+ [[17, 20, 23], 1, Segment, [nc, anchors, 32, 256]], # Detect(P3, P4, P5)
+ ]
diff --git a/ros2_ws/src/yolov3_ros/models/segment/yolov5x-seg.yaml b/ros2_ws/src/yolov3_ros/models/segment/yolov5x-seg.yaml
new file mode 100644
index 00000000..5a95b92f
--- /dev/null
+++ b/ros2_ws/src/yolov3_ros/models/segment/yolov5x-seg.yaml
@@ -0,0 +1,48 @@
+# YOLOv3 🚀 by Ultralytics, GPL-3.0 license
+
+# Parameters
+nc: 80 # number of classes
+depth_multiple: 1.33 # model depth multiple
+width_multiple: 1.25 # layer channel multiple
+anchors:
+ - [10,13, 16,30, 33,23] # P3/8
+ - [30,61, 62,45, 59,119] # P4/16
+ - [116,90, 156,198, 373,326] # P5/32
+
+# YOLOv5 v6.0 backbone
+backbone:
+ # [from, number, module, args]
+ [[-1, 1, Conv, [64, 6, 2, 2]], # 0-P1/2
+ [-1, 1, Conv, [128, 3, 2]], # 1-P2/4
+ [-1, 3, C3, [128]],
+ [-1, 1, Conv, [256, 3, 2]], # 3-P3/8
+ [-1, 6, C3, [256]],
+ [-1, 1, Conv, [512, 3, 2]], # 5-P4/16
+ [-1, 9, C3, [512]],
+ [-1, 1, Conv, [1024, 3, 2]], # 7-P5/32
+ [-1, 3, C3, [1024]],
+ [-1, 1, SPPF, [1024, 5]], # 9
+ ]
+
+# YOLOv5 v6.0 head
+head:
+ [[-1, 1, Conv, [512, 1, 1]],
+ [-1, 1, nn.Upsample, [None, 2, 'nearest']],
+ [[-1, 6], 1, Concat, [1]], # cat backbone P4
+ [-1, 3, C3, [512, False]], # 13
+
+ [-1, 1, Conv, [256, 1, 1]],
+ [-1, 1, nn.Upsample, [None, 2, 'nearest']],
+ [[-1, 4], 1, Concat, [1]], # cat backbone P3
+ [-1, 3, C3, [256, False]], # 17 (P3/8-small)
+
+ [-1, 1, Conv, [256, 3, 2]],
+ [[-1, 14], 1, Concat, [1]], # cat head P4
+ [-1, 3, C3, [512, False]], # 20 (P4/16-medium)
+
+ [-1, 1, Conv, [512, 3, 2]],
+ [[-1, 10], 1, Concat, [1]], # cat head P5
+ [-1, 3, C3, [1024, False]], # 23 (P5/32-large)
+
+ [[17, 20, 23], 1, Segment, [nc, anchors, 32, 256]], # Detect(P3, P4, P5)
+ ]
diff --git a/ros2_ws/src/yolov3_ros/models/tf.py b/ros2_ws/src/yolov3_ros/models/tf.py
new file mode 100644
index 00000000..956ef2bd
--- /dev/null
+++ b/ros2_ws/src/yolov3_ros/models/tf.py
@@ -0,0 +1,628 @@
+# YOLOv3 🚀 by Ultralytics, GPL-3.0 license
+"""
+TensorFlow, Keras and TFLite versions of
+Authored by https://github.com/zldrobit in PR https://github.com/ultralytics/yolov5/pull/1127
+
+Usage:
+ $ python models/tf.py --weights yolov3.pt
+
+Export:
+ $ python path/to/export.py --weights yolov3.pt --include saved_model pb tflite tfjs
+"""
+
+import argparse
+import logging
+import sys
+from copy import deepcopy
+from pathlib import Path
+
+from packaging import version
+
+FILE = Path(__file__).resolve()
+ROOT = FILE.parents[1] # root directory
+if str(ROOT) not in sys.path:
+ sys.path.append(str(ROOT)) # add ROOT to PATH
+# ROOT = ROOT.relative_to(Path.cwd()) # relative
+
+import numpy as np
+import tensorflow as tf
+import torch
+import torch.nn as nn
+from keras import backend
+from keras.engine.base_layer import Layer
+from keras.engine.input_spec import InputSpec
+from keras.utils import conv_utils
+from tensorflow import keras
+
+from models.common import C3, SPP, SPPF, Bottleneck, BottleneckCSP, Concat, Conv, DWConv, Focus, autopad
+from models.experimental import CrossConv, MixConv2d, attempt_load
+from models.yolo import Detect
+from utils.activations import SiLU
+from utils.general import LOGGER, make_divisible, print_args
+
+# isort: off
+from tensorflow.python.util.tf_export import keras_export
+
+
+class TFBN(keras.layers.Layer):
+ # TensorFlow BatchNormalization wrapper
+ def __init__(self, w=None):
+ super().__init__()
+ self.bn = keras.layers.BatchNormalization(
+ beta_initializer=keras.initializers.Constant(w.bias.numpy()),
+ gamma_initializer=keras.initializers.Constant(w.weight.numpy()),
+ moving_mean_initializer=keras.initializers.Constant(w.running_mean.numpy()),
+ moving_variance_initializer=keras.initializers.Constant(w.running_var.numpy()),
+ epsilon=w.eps)
+
+ def call(self, inputs):
+ return self.bn(inputs)
+
+
+class TFMaxPool2d(keras.layers.Layer):
+ # TensorFlow MAX Pooling
+ def __init__(self, k, s, p, w=None):
+ super().__init__()
+ self.pool = keras.layers.MaxPool2D(pool_size=k, strides=s, padding='valid')
+
+ def call(self, inputs):
+ return self.pool(inputs)
+
+
+class TFZeroPad2d(keras.layers.Layer):
+ # TensorFlow MAX Pooling
+ def __init__(self, p, w=None):
+ super().__init__()
+ if version.parse(tf.__version__) < version.parse('2.11.0'):
+ self.zero_pad = ZeroPadding2D(padding=p)
+ else:
+ self.zero_pad = keras.layers.ZeroPadding2D(padding=((p[0], p[1]), (p[2], p[3])))
+
+ def call(self, inputs):
+ return self.zero_pad(inputs)
+
+
+class TFPad(keras.layers.Layer):
+ def __init__(self, pad):
+ super().__init__()
+ self.pad = tf.constant([[0, 0], [pad, pad], [pad, pad], [0, 0]])
+
+ def call(self, inputs):
+ return tf.pad(inputs, self.pad, mode='constant', constant_values=0)
+
+
+class TFConv(keras.layers.Layer):
+ # Standard convolution
+ def __init__(self, c1, c2, k=1, s=1, p=None, g=1, act=True, w=None):
+ # ch_in, ch_out, weights, kernel, stride, padding, groups
+ super().__init__()
+ assert g == 1, "TF v2.2 Conv2D does not support 'groups' argument"
+ assert isinstance(k, int), "Convolution with multiple kernels are not allowed."
+ # TensorFlow convolution padding is inconsistent with PyTorch (e.g. k=3 s=2 'SAME' padding)
+ # see https://stackoverflow.com/questions/52975843/comparing-conv2d-with-padding-between-tensorflow-and-pytorch
+
+ conv = keras.layers.Conv2D(
+ c2, k, s, 'SAME' if s == 1 else 'VALID', use_bias=False if hasattr(w, 'bn') else True,
+ kernel_initializer=keras.initializers.Constant(w.conv.weight.permute(2, 3, 1, 0).numpy()),
+ bias_initializer='zeros' if hasattr(w, 'bn') else keras.initializers.Constant(w.conv.bias.numpy()))
+ self.conv = conv if s == 1 else keras.Sequential([TFPad(autopad(k, p)), conv])
+ self.bn = TFBN(w.bn) if hasattr(w, 'bn') else tf.identity
+
+ # activations
+ if isinstance(w.act, nn.LeakyReLU):
+ self.act = (lambda x: keras.activations.relu(x, alpha=0.1)) if act else tf.identity
+ elif isinstance(w.act, nn.Hardswish):
+ self.act = (lambda x: x * tf.nn.relu6(x + 3) * 0.166666667) if act else tf.identity
+ elif isinstance(w.act, (nn.SiLU, SiLU)):
+ self.act = (lambda x: keras.activations.swish(x)) if act else tf.identity
+ else:
+ raise Exception(f'no matching TensorFlow activation found for {w.act}')
+
+ def call(self, inputs):
+ return self.act(self.bn(self.conv(inputs)))
+
+
+class TFFocus(keras.layers.Layer):
+ # Focus wh information into c-space
+ def __init__(self, c1, c2, k=1, s=1, p=None, g=1, act=True, w=None):
+ # ch_in, ch_out, kernel, stride, padding, groups
+ super().__init__()
+ self.conv = TFConv(c1 * 4, c2, k, s, p, g, act, w.conv)
+
+ def call(self, inputs): # x(b,w,h,c) -> y(b,w/2,h/2,4c)
+ # inputs = inputs / 255 # normalize 0-255 to 0-1
+ return self.conv(tf.concat([inputs[:, ::2, ::2, :],
+ inputs[:, 1::2, ::2, :],
+ inputs[:, ::2, 1::2, :],
+ inputs[:, 1::2, 1::2, :]], 3))
+
+
+class TFBottleneck(keras.layers.Layer):
+ # Standard bottleneck
+ def __init__(self, c1, c2, shortcut=True, g=1, e=0.5, w=None): # ch_in, ch_out, shortcut, groups, expansion
+ super().__init__()
+ c_ = int(c2 * e) # hidden channels
+ self.cv1 = TFConv(c1, c_, 1, 1, w=w.cv1)
+ self.cv2 = TFConv(c_, c2, 3, 1, g=g, w=w.cv2)
+ self.add = shortcut and c1 == c2
+
+ def call(self, inputs):
+ return inputs + self.cv2(self.cv1(inputs)) if self.add else self.cv2(self.cv1(inputs))
+
+
+class TFConv2d(keras.layers.Layer):
+ # Substitution for PyTorch nn.Conv2D
+ def __init__(self, c1, c2, k, s=1, g=1, bias=True, w=None):
+ super().__init__()
+ assert g == 1, "TF v2.2 Conv2D does not support 'groups' argument"
+ self.conv = keras.layers.Conv2D(
+ c2, k, s, 'VALID', use_bias=bias,
+ kernel_initializer=keras.initializers.Constant(w.weight.permute(2, 3, 1, 0).numpy()),
+ bias_initializer=keras.initializers.Constant(w.bias.numpy()) if bias else None, )
+
+ def call(self, inputs):
+ return self.conv(inputs)
+
+
+class TFBottleneckCSP(keras.layers.Layer):
+ # CSP Bottleneck https://github.com/WongKinYiu/CrossStagePartialNetworks
+ def __init__(self, c1, c2, n=1, shortcut=True, g=1, e=0.5, w=None):
+ # ch_in, ch_out, number, shortcut, groups, expansion
+ super().__init__()
+ c_ = int(c2 * e) # hidden channels
+ self.cv1 = TFConv(c1, c_, 1, 1, w=w.cv1)
+ self.cv2 = TFConv2d(c1, c_, 1, 1, bias=False, w=w.cv2)
+ self.cv3 = TFConv2d(c_, c_, 1, 1, bias=False, w=w.cv3)
+ self.cv4 = TFConv(2 * c_, c2, 1, 1, w=w.cv4)
+ self.bn = TFBN(w.bn)
+ self.act = lambda x: keras.activations.relu(x, alpha=0.1)
+ self.m = keras.Sequential([TFBottleneck(c_, c_, shortcut, g, e=1.0, w=w.m[j]) for j in range(n)])
+
+ def call(self, inputs):
+ y1 = self.cv3(self.m(self.cv1(inputs)))
+ y2 = self.cv2(inputs)
+ return self.cv4(self.act(self.bn(tf.concat((y1, y2), axis=3))))
+
+
+class TFC3(keras.layers.Layer):
+ # CSP Bottleneck with 3 convolutions
+ def __init__(self, c1, c2, n=1, shortcut=True, g=1, e=0.5, w=None):
+ # ch_in, ch_out, number, shortcut, groups, expansion
+ super().__init__()
+ c_ = int(c2 * e) # hidden channels
+ self.cv1 = TFConv(c1, c_, 1, 1, w=w.cv1)
+ self.cv2 = TFConv(c1, c_, 1, 1, w=w.cv2)
+ self.cv3 = TFConv(2 * c_, c2, 1, 1, w=w.cv3)
+ self.m = keras.Sequential([TFBottleneck(c_, c_, shortcut, g, e=1.0, w=w.m[j]) for j in range(n)])
+
+ def call(self, inputs):
+ return self.cv3(tf.concat((self.m(self.cv1(inputs)), self.cv2(inputs)), axis=3))
+
+
+class TFSPP(keras.layers.Layer):
+ # Spatial pyramid pooling layer used in YOLOv3-SPP
+ def __init__(self, c1, c2, k=(5, 9, 13), w=None):
+ super().__init__()
+ c_ = c1 // 2 # hidden channels
+ self.cv1 = TFConv(c1, c_, 1, 1, w=w.cv1)
+ self.cv2 = TFConv(c_ * (len(k) + 1), c2, 1, 1, w=w.cv2)
+ self.m = [keras.layers.MaxPool2D(pool_size=x, strides=1, padding='SAME') for x in k]
+
+ def call(self, inputs):
+ x = self.cv1(inputs)
+ return self.cv2(tf.concat([x] + [m(x) for m in self.m], 3))
+
+
+class TFSPPF(keras.layers.Layer):
+ # Spatial pyramid pooling-Fast layer
+ def __init__(self, c1, c2, k=5, w=None):
+ super().__init__()
+ c_ = c1 // 2 # hidden channels
+ self.cv1 = TFConv(c1, c_, 1, 1, w=w.cv1)
+ self.cv2 = TFConv(c_ * 4, c2, 1, 1, w=w.cv2)
+ self.m = keras.layers.MaxPool2D(pool_size=k, strides=1, padding='SAME')
+
+ def call(self, inputs):
+ x = self.cv1(inputs)
+ y1 = self.m(x)
+ y2 = self.m(y1)
+ return self.cv2(tf.concat([x, y1, y2, self.m(y2)], 3))
+
+
+class TFDetect(keras.layers.Layer):
+ def __init__(self, nc=80, anchors=(), ch=(), imgsz=(640, 640), w=None): # detection layer
+ super().__init__()
+ self.stride = tf.convert_to_tensor(w.stride.numpy(), dtype=tf.float32)
+ self.nc = nc # number of classes
+ self.no = nc + 5 # number of outputs per anchor
+ self.nl = len(anchors) # number of detection layers
+ self.na = len(anchors[0]) // 2 # number of anchors
+ self.grid = [tf.zeros(1)] * self.nl # init grid
+ self.anchors = tf.convert_to_tensor(w.anchors.numpy(), dtype=tf.float32)
+ self.anchor_grid = tf.reshape(self.anchors * tf.reshape(self.stride, [self.nl, 1, 1]),
+ [self.nl, 1, -1, 1, 2])
+ self.m = [TFConv2d(x, self.no * self.na, 1, w=w.m[i]) for i, x in enumerate(ch)]
+ self.training = False # set to False after building model
+ self.imgsz = imgsz
+ for i in range(self.nl):
+ ny, nx = self.imgsz[0] // self.stride[i], self.imgsz[1] // self.stride[i]
+ self.grid[i] = self._make_grid(nx, ny)
+
+ def call(self, inputs):
+ z = [] # inference output
+ x = []
+ for i in range(self.nl):
+ x.append(self.m[i](inputs[i]))
+ # x(bs,20,20,255) to x(bs,3,20,20,85)
+ ny, nx = self.imgsz[0] // self.stride[i], self.imgsz[1] // self.stride[i]
+ x[i] = tf.transpose(tf.reshape(x[i], [-1, ny * nx, self.na, self.no]), [0, 2, 1, 3])
+
+ if not self.training: # inference
+ y = tf.sigmoid(x[i])
+ xy = (y[..., 0:2] * 2 - 0.5 + self.grid[i]) * self.stride[i] # xy
+ wh = (y[..., 2:4] * 2) ** 2 * self.anchor_grid[i]
+ # Normalize xywh to 0-1 to reduce calibration error
+ xy /= tf.constant([[self.imgsz[1], self.imgsz[0]]], dtype=tf.float32)
+ wh /= tf.constant([[self.imgsz[1], self.imgsz[0]]], dtype=tf.float32)
+ y = tf.concat([xy, wh, y[..., 4:]], -1)
+ z.append(tf.reshape(y, [-1, 3 * ny * nx, self.no]))
+
+ return x if self.training else (tf.concat(z, 1), x)
+
+ @staticmethod
+ def _make_grid(nx=20, ny=20):
+ # yv, xv = torch.meshgrid([torch.arange(ny), torch.arange(nx)])
+ # return torch.stack((xv, yv), 2).view((1, 1, ny, nx, 2)).float()
+ xv, yv = tf.meshgrid(tf.range(nx), tf.range(ny))
+ return tf.cast(tf.reshape(tf.stack([xv, yv], 2), [1, 1, ny * nx, 2]), dtype=tf.float32)
+
+
+class TFUpsample(keras.layers.Layer):
+ def __init__(self, size, scale_factor, mode, w=None): # warning: all arguments needed including 'w'
+ super().__init__()
+ assert scale_factor == 2, "scale_factor must be 2"
+ self.upsample = lambda x: tf.image.resize(x, (x.shape[1] * 2, x.shape[2] * 2), method=mode)
+ # self.upsample = keras.layers.UpSampling2D(size=scale_factor, interpolation=mode)
+ # with default arguments: align_corners=False, half_pixel_centers=False
+ # self.upsample = lambda x: tf.raw_ops.ResizeNearestNeighbor(images=x,
+ # size=(x.shape[1] * 2, x.shape[2] * 2))
+
+ def call(self, inputs):
+ return self.upsample(inputs)
+
+
+class TFConcat(keras.layers.Layer):
+ def __init__(self, dimension=1, w=None):
+ super().__init__()
+ assert dimension == 1, "convert only NCHW to NHWC concat"
+ self.d = 3
+
+ def call(self, inputs):
+ return tf.concat(inputs, self.d)
+
+
+def parse_model(d, ch, model, imgsz): # model_dict, input_channels(3)
+ LOGGER.info(f"\n{'':>3}{'from':>18}{'n':>3}{'params':>10} {'module':<40}{'arguments':<30}")
+ anchors, nc, gd, gw = d['anchors'], d['nc'], d['depth_multiple'], d['width_multiple']
+ na = (len(anchors[0]) // 2) if isinstance(anchors, list) else anchors # number of anchors
+ no = na * (nc + 5) # number of outputs = anchors * (classes + 5)
+
+ layers, save, c2 = [], [], ch[-1] # layers, savelist, ch out
+ for i, (f, n, m, args) in enumerate(d['backbone'] + d['head']): # from, number, module, args
+ m_str = m
+ m = eval(m) if isinstance(m, str) else m # eval strings
+ for j, a in enumerate(args):
+ try:
+ args[j] = eval(a) if isinstance(a, str) else a # eval strings
+ except NameError:
+ pass
+
+ n = max(round(n * gd), 1) if n > 1 else n # depth gain
+ if m in [nn.Conv2d, Conv, Bottleneck, SPP, SPPF, DWConv, MixConv2d, Focus, CrossConv, BottleneckCSP, C3]:
+ c1, c2 = ch[f], args[0]
+ c2 = make_divisible(c2 * gw, 8) if c2 != no else c2
+
+ args = [c1, c2, *args[1:]]
+ if m in [BottleneckCSP, C3]:
+ args.insert(2, n)
+ n = 1
+ elif m is nn.BatchNorm2d:
+ args = [ch[f]]
+ elif m is Concat:
+ c2 = sum(ch[-1 if x == -1 else x + 1] for x in f)
+ elif m is Detect:
+ args.append([ch[x + 1] for x in f])
+ if isinstance(args[1], int): # number of anchors
+ args[1] = [list(range(args[1] * 2))] * len(f)
+ args.append(imgsz)
+ else:
+ c2 = ch[f]
+
+ tf_m = eval('TF' + m_str.replace('nn.', ''))
+ m_ = keras.Sequential([tf_m(*args, w=model.model[i][j]) for j in range(n)]) if n > 1 \
+ else tf_m(*args, w=model.model[i]) # module
+
+ torch_m_ = nn.Sequential(*(m(*args) for _ in range(n))) if n > 1 else m(*args) # module
+ t = str(m)[8:-2].replace('__main__.', '') # module type
+ np = sum(x.numel() for x in torch_m_.parameters()) # number params
+ m_.i, m_.f, m_.type, m_.np = i, f, t, np # attach index, 'from' index, type, number params
+ LOGGER.info(f'{i:>3}{str(f):>18}{str(n):>3}{np:>10} {t:<40}{str(args):<30}') # print
+ save.extend(x % i for x in ([f] if isinstance(f, int) else f) if x != -1) # append to savelist
+ layers.append(m_)
+ ch.append(c2)
+ return keras.Sequential(layers), sorted(save)
+
+
+class TFModel:
+ def __init__(self, cfg='yolov3.yaml', ch=3, nc=None, model=None, imgsz=(640, 640)): # model, channels, classes
+ super().__init__()
+ if isinstance(cfg, dict):
+ self.yaml = cfg # model dict
+ else: # is *.yaml
+ import yaml # for torch hub
+ self.yaml_file = Path(cfg).name
+ with open(cfg) as f:
+ self.yaml = yaml.load(f, Loader=yaml.FullLoader) # model dict
+
+ # Define model
+ if nc and nc != self.yaml['nc']:
+ LOGGER.info(f"Overriding {cfg} nc={self.yaml['nc']} with nc={nc}")
+ self.yaml['nc'] = nc # override yaml value
+ self.model, self.savelist = parse_model(deepcopy(self.yaml), ch=[ch], model=model, imgsz=imgsz)
+
+ def predict(self, inputs, tf_nms=False, agnostic_nms=False, topk_per_class=100, topk_all=100, iou_thres=0.45,
+ conf_thres=0.25):
+ y = [] # outputs
+ x = inputs
+ for i, m in enumerate(self.model.layers):
+ if m.f != -1: # if not from previous layer
+ x = y[m.f] if isinstance(m.f, int) else [x if j == -1 else y[j] for j in m.f] # from earlier layers
+
+ x = m(x) # run
+ y.append(x if m.i in self.savelist else None) # save output
+
+ # Add TensorFlow NMS
+ if tf_nms:
+ boxes = self._xywh2xyxy(x[0][..., :4])
+ probs = x[0][:, :, 4:5]
+ classes = x[0][:, :, 5:]
+ scores = probs * classes
+ if agnostic_nms:
+ nms = AgnosticNMS()((boxes, classes, scores), topk_all, iou_thres, conf_thres)
+ return nms, x[1]
+ else:
+ boxes = tf.expand_dims(boxes, 2)
+ nms = tf.image.combined_non_max_suppression(
+ boxes, scores, topk_per_class, topk_all, iou_thres, conf_thres, clip_boxes=False)
+ return nms, x[1]
+
+ return x[0] # output only first tensor [1,6300,85] = [xywh, conf, class0, class1, ...]
+ # x = x[0][0] # [x(1,6300,85), ...] to x(6300,85)
+ # xywh = x[..., :4] # x(6300,4) boxes
+ # conf = x[..., 4:5] # x(6300,1) confidences
+ # cls = tf.reshape(tf.cast(tf.argmax(x[..., 5:], axis=1), tf.float32), (-1, 1)) # x(6300,1) classes
+ # return tf.concat([conf, cls, xywh], 1)
+
+ @staticmethod
+ def _xywh2xyxy(xywh):
+ # Convert nx4 boxes from [x, y, w, h] to [x1, y1, x2, y2] where xy1=top-left, xy2=bottom-right
+ x, y, w, h = tf.split(xywh, num_or_size_splits=4, axis=-1)
+ return tf.concat([x - w / 2, y - h / 2, x + w / 2, y + h / 2], axis=-1)
+
+
+class AgnosticNMS(keras.layers.Layer):
+ # TF Agnostic NMS
+ def call(self, input, topk_all, iou_thres, conf_thres):
+ # wrap map_fn to avoid TypeSpec related error https://stackoverflow.com/a/65809989/3036450
+ return tf.map_fn(lambda x: self._nms(x, topk_all, iou_thres, conf_thres), input,
+ fn_output_signature=(tf.float32, tf.float32, tf.float32, tf.int32),
+ name='agnostic_nms')
+
+ @staticmethod
+ def _nms(x, topk_all=100, iou_thres=0.45, conf_thres=0.25): # agnostic NMS
+ boxes, classes, scores = x
+ class_inds = tf.cast(tf.argmax(classes, axis=-1), tf.float32)
+ scores_inp = tf.reduce_max(scores, -1)
+ selected_inds = tf.image.non_max_suppression(
+ boxes, scores_inp, max_output_size=topk_all, iou_threshold=iou_thres, score_threshold=conf_thres)
+ selected_boxes = tf.gather(boxes, selected_inds)
+ padded_boxes = tf.pad(selected_boxes,
+ paddings=[[0, topk_all - tf.shape(selected_boxes)[0]], [0, 0]],
+ mode="CONSTANT", constant_values=0.0)
+ selected_scores = tf.gather(scores_inp, selected_inds)
+ padded_scores = tf.pad(selected_scores,
+ paddings=[[0, topk_all - tf.shape(selected_boxes)[0]]],
+ mode="CONSTANT", constant_values=-1.0)
+ selected_classes = tf.gather(class_inds, selected_inds)
+ padded_classes = tf.pad(selected_classes,
+ paddings=[[0, topk_all - tf.shape(selected_boxes)[0]]],
+ mode="CONSTANT", constant_values=-1.0)
+ valid_detections = tf.shape(selected_inds)[0]
+ return padded_boxes, padded_scores, padded_classes, valid_detections
+
+
+def representative_dataset_gen(dataset, ncalib=100):
+ # Representative dataset generator for use with converter.representative_dataset, returns a generator of np arrays
+ for n, (path, img, im0s, vid_cap, string) in enumerate(dataset):
+ input = np.transpose(img, [1, 2, 0])
+ input = np.expand_dims(input, axis=0).astype(np.float32)
+ input /= 255
+ yield [input]
+ if n >= ncalib:
+ break
+
+
+def run(weights=ROOT / 'yolov3.pt', # weights path
+ imgsz=(640, 640), # inference size h,w
+ batch_size=1, # batch size
+ dynamic=False, # dynamic batch size
+ ):
+ # PyTorch model
+ im = torch.zeros((batch_size, 3, *imgsz)) # BCHW image
+ model = attempt_load(weights, map_location=torch.device('cpu'), inplace=True, fuse=False)
+ y = model(im) # inference
+ model.info()
+
+ # TensorFlow model
+ im = tf.zeros((batch_size, *imgsz, 3)) # BHWC image
+ tf_model = TFModel(cfg=model.yaml, model=model, nc=model.nc, imgsz=imgsz)
+ y = tf_model.predict(im) # inference
+
+ # Keras model
+ im = keras.Input(shape=(*imgsz, 3), batch_size=None if dynamic else batch_size)
+ keras_model = keras.Model(inputs=im, outputs=tf_model.predict(im))
+ keras_model.summary()
+
+ LOGGER.info('PyTorch, TensorFlow and Keras models successfully verified.\nUse export.py for TF model export.')
+
+
+@keras_export("keras.layers.ZeroPadding2D")
+class ZeroPadding2D(Layer):
+ """Zero-padding layer for 2D input (e.g. picture).
+
+ This layer can add rows and columns of zeros
+ at the top, bottom, left and right side of an image tensor.
+
+ Examples:
+
+ >>> input_shape = (1, 1, 2, 2)
+ >>> x = np.arange(np.prod(input_shape)).reshape(input_shape)
+ >>> print(x)
+ [[[[0 1]
+ [2 3]]]]
+ >>> y = tf.keras.layers.ZeroPadding2D(padding=1)(x)
+ >>> print(y)
+ tf.Tensor(
+ [[[[0 0]
+ [0 0]
+ [0 0]
+ [0 0]]
+ [[0 0]
+ [0 1]
+ [2 3]
+ [0 0]]
+ [[0 0]
+ [0 0]
+ [0 0]
+ [0 0]]]], shape=(1, 3, 4, 2), dtype=int64)
+
+ Args:
+ padding: Int, or tuple of 2 ints, or tuple of 2 tuples of 2 ints.
+ - If int: the same symmetric padding
+ is applied to height and width.
+ - If tuple of 2 ints:
+ interpreted as two different
+ symmetric padding values for height and width:
+ `(symmetric_height_pad, symmetric_width_pad)`.
+ - If tuple of 2 tuples of 2 ints:
+ interpreted as
+ `((top_pad, bottom_pad), (left_pad, right_pad))`
+ data_format: A string,
+ one of `channels_last` (default) or `channels_first`.
+ The ordering of the dimensions in the inputs.
+ `channels_last` corresponds to inputs with shape
+ `(batch_size, height, width, channels)` while `channels_first`
+ corresponds to inputs with shape
+ `(batch_size, channels, height, width)`.
+ It defaults to the `image_data_format` value found in your
+ Keras config file at `~/.keras/keras.json`.
+ If you never set it, then it will be "channels_last".
+
+ Input shape:
+ 4D tensor with shape:
+ - If `data_format` is `"channels_last"`:
+ `(batch_size, rows, cols, channels)`
+ - If `data_format` is `"channels_first"`:
+ `(batch_size, channels, rows, cols)`
+
+ Output shape:
+ 4D tensor with shape:
+ - If `data_format` is `"channels_last"`:
+ `(batch_size, padded_rows, padded_cols, channels)`
+ - If `data_format` is `"channels_first"`:
+ `(batch_size, channels, padded_rows, padded_cols)`
+ """
+
+ def __init__(self, padding=(1, 1), data_format=None, **kwargs):
+ super().__init__(**kwargs)
+ self.data_format = conv_utils.normalize_data_format(data_format)
+ if isinstance(padding, int):
+ self.padding = ((padding, padding), (padding, padding))
+ elif hasattr(padding, "__len__"):
+ if len(padding) == 4:
+ padding = ((padding[0], padding[1]), (padding[2], padding[3]))
+ if len(padding) != 2:
+ raise ValueError(
+ f"`padding` should have two elements. Received: {padding}."
+ )
+ height_padding = conv_utils.normalize_tuple(
+ padding[0], 2, "1st entry of padding", allow_zero=True
+ )
+ width_padding = conv_utils.normalize_tuple(
+ padding[1], 2, "2nd entry of padding", allow_zero=True
+ )
+ self.padding = (height_padding, width_padding)
+ else:
+ raise ValueError(
+ "`padding` should be either an int, "
+ "a tuple of 2 ints "
+ "(symmetric_height_pad, symmetric_width_pad), "
+ "or a tuple of 2 tuples of 2 ints "
+ "((top_pad, bottom_pad), (left_pad, right_pad)). "
+ f"Received: {padding}."
+ )
+ self.input_spec = InputSpec(ndim=4)
+
+ def compute_output_shape(self, input_shape):
+ input_shape = tf.TensorShape(input_shape).as_list()
+ if self.data_format == "channels_first":
+ if input_shape[2] is not None:
+ rows = input_shape[2] + self.padding[0][0] + self.padding[0][1]
+ else:
+ rows = None
+ if input_shape[3] is not None:
+ cols = input_shape[3] + self.padding[1][0] + self.padding[1][1]
+ else:
+ cols = None
+ return tf.TensorShape([input_shape[0], input_shape[1], rows, cols])
+ elif self.data_format == "channels_last":
+ if input_shape[1] is not None:
+ rows = input_shape[1] + self.padding[0][0] + self.padding[0][1]
+ else:
+ rows = None
+ if input_shape[2] is not None:
+ cols = input_shape[2] + self.padding[1][0] + self.padding[1][1]
+ else:
+ cols = None
+ return tf.TensorShape([input_shape[0], rows, cols, input_shape[3]])
+
+ def call(self, inputs):
+ return backend.spatial_2d_padding(
+ inputs, padding=self.padding, data_format=self.data_format
+ )
+
+ def get_config(self):
+ config = {"padding": self.padding, "data_format": self.data_format}
+ base_config = super().get_config()
+ return dict(list(base_config.items()) + list(config.items()))
+
+
+def parse_opt():
+ parser = argparse.ArgumentParser()
+ parser.add_argument('--weights', type=str, default=ROOT / 'yolov3.pt', help='weights path')
+ parser.add_argument('--imgsz', '--img', '--img-size', nargs='+', type=int, default=[640], help='inference size h,w')
+ parser.add_argument('--batch-size', type=int, default=1, help='batch size')
+ parser.add_argument('--dynamic', action='store_true', help='dynamic batch size')
+ opt = parser.parse_args()
+ opt.imgsz *= 2 if len(opt.imgsz) == 1 else 1 # expand
+ print_args(FILE.stem, opt)
+ return opt
+
+
+def main(opt):
+ run(**vars(opt))
+
+
+if __name__ == "__main__":
+ opt = parse_opt()
+ main(opt)
diff --git a/ros2_ws/src/yolov3_ros/models/yolo.py b/ros2_ws/src/yolov3_ros/models/yolo.py
new file mode 100644
index 00000000..f398d3f9
--- /dev/null
+++ b/ros2_ws/src/yolov3_ros/models/yolo.py
@@ -0,0 +1,336 @@
+# YOLOv3 🚀 by Ultralytics, GPL-3.0 license
+"""
+YOLO-specific modules
+
+Usage:
+ $ python path/to/models/yolo.py --cfg yolov3.yaml
+"""
+
+import argparse
+import sys
+from copy import deepcopy
+from pathlib import Path
+
+FILE = Path(__file__).resolve()
+ROOT = FILE.parents[1] # root directory
+if str(ROOT) not in sys.path:
+ sys.path.append(str(ROOT)) # add ROOT to PATH
+# ROOT = ROOT.relative_to(Path.cwd()) # relative
+
+from models.common import *
+from models.experimental import *
+from utils.autoanchor import check_anchor_order
+from utils.general import LOGGER, check_version, check_yaml, make_divisible, print_args
+from utils.plots import feature_visualization
+from utils.torch_utils import (copy_attr, fuse_conv_and_bn, initialize_weights, model_info, scale_img, select_device,
+ time_sync)
+
+try:
+ import thop # for FLOPs computation
+except ImportError:
+ thop = None
+
+
+class Detect(nn.Module):
+ stride = None # strides computed during build
+ onnx_dynamic = False # ONNX export parameter
+
+ def __init__(self, nc=80, anchors=(), ch=(), inplace=True): # detection layer
+ super().__init__()
+ self.nc = nc # number of classes
+ self.no = nc + 5 # number of outputs per anchor
+ self.nl = len(anchors) # number of detection layers
+ self.na = len(anchors[0]) // 2 # number of anchors
+ self.grid = [torch.zeros(1)] * self.nl # init grid
+ self.anchor_grid = [torch.zeros(1)] * self.nl # init anchor grid
+ self.register_buffer('anchors', torch.tensor(anchors).float().view(self.nl, -1, 2)) # shape(nl,na,2)
+ self.m = nn.ModuleList(nn.Conv2d(x, self.no * self.na, 1) for x in ch) # output conv
+ self.inplace = inplace # use in-place ops (e.g. slice assignment)
+
+ def forward(self, x):
+ z = [] # inference output
+ for i in range(self.nl):
+ x[i] = self.m[i](x[i]) # conv
+ bs, _, ny, nx = x[i].shape # x(bs,255,20,20) to x(bs,3,20,20,85)
+ x[i] = x[i].view(bs, self.na, self.no, ny, nx).permute(0, 1, 3, 4, 2).contiguous()
+
+ if not self.training: # inference
+ if self.onnx_dynamic or self.grid[i].shape[2:4] != x[i].shape[2:4]:
+ self.grid[i], self.anchor_grid[i] = self._make_grid(nx, ny, i)
+
+ y = x[i].sigmoid()
+ if self.inplace:
+ y[..., 0:2] = (y[..., 0:2] * 2 - 0.5 + self.grid[i]) * self.stride[i] # xy
+ y[..., 2:4] = (y[..., 2:4] * 2) ** 2 * self.anchor_grid[i] # wh
+ else: # for on AWS Inferentia https://github.com/ultralytics/yolov5/pull/2953
+ xy = (y[..., 0:2] * 2 - 0.5 + self.grid[i]) * self.stride[i] # xy
+ wh = (y[..., 2:4] * 2) ** 2 * self.anchor_grid[i] # wh
+ y = torch.cat((xy, wh, y[..., 4:]), -1)
+ z.append(y.view(bs, -1, self.no))
+
+ return x if self.training else (torch.cat(z, 1), x)
+
+ def _make_grid(self, nx=20, ny=20, i=0):
+ d = self.anchors[i].device
+ if check_version(torch.__version__, '1.10.0'): # torch>=1.10.0 meshgrid workaround for torch>=0.7 compatibility
+ yv, xv = torch.meshgrid([torch.arange(ny).to(d), torch.arange(nx).to(d)], indexing='ij')
+ else:
+ yv, xv = torch.meshgrid([torch.arange(ny).to(d), torch.arange(nx).to(d)])
+ grid = torch.stack((xv, yv), 2).expand((1, self.na, ny, nx, 2)).float()
+ anchor_grid = (self.anchors[i].clone() * self.stride[i]) \
+ .view((1, self.na, 1, 1, 2)).expand((1, self.na, ny, nx, 2)).float()
+ return grid, anchor_grid
+
+
+class Model(nn.Module):
+ def __init__(self, cfg='yolov3.yaml', ch=3, nc=None, anchors=None): # model, input channels, number of classes
+ super().__init__()
+ if isinstance(cfg, dict):
+ self.yaml = cfg # model dict
+ else: # is *.yaml
+ import yaml # for torch hub
+ self.yaml_file = Path(cfg).name
+ with open(cfg, encoding='ascii', errors='ignore') as f:
+ self.yaml = yaml.safe_load(f) # model dict
+
+ # Define model
+ ch = self.yaml['ch'] = self.yaml.get('ch', ch) # input channels
+ if nc and nc != self.yaml['nc']:
+ LOGGER.info(f"Overriding model.yaml nc={self.yaml['nc']} with nc={nc}")
+ self.yaml['nc'] = nc # override yaml value
+ if anchors:
+ LOGGER.info(f'Overriding model.yaml anchors with anchors={anchors}')
+ self.yaml['anchors'] = round(anchors) # override yaml value
+ self.model, self.save = parse_model(deepcopy(self.yaml), ch=[ch]) # model, savelist
+ self.names = [str(i) for i in range(self.yaml['nc'])] # default names
+ self.inplace = self.yaml.get('inplace', True)
+
+ # Build strides, anchors
+ m = self.model[-1] # Detect()
+ if isinstance(m, Detect):
+ s = 256 # 2x min stride
+ m.inplace = self.inplace
+ m.stride = torch.tensor([s / x.shape[-2] for x in self.forward(torch.zeros(1, ch, s, s))]) # forward
+ m.anchors /= m.stride.view(-1, 1, 1)
+ check_anchor_order(m)
+ self.stride = m.stride
+ self._initialize_biases() # only run once
+
+ # Init weights, biases
+ initialize_weights(self)
+ self.info()
+ LOGGER.info('')
+
+ def forward(self, x, augment=False, profile=False, visualize=False):
+ if augment:
+ return self._forward_augment(x) # augmented inference, None
+ return self._forward_once(x, profile, visualize) # single-scale inference, train
+
+ def _forward_augment(self, x):
+ img_size = x.shape[-2:] # height, width
+ s = [1, 0.83, 0.67] # scales
+ f = [None, 3, None] # flips (2-ud, 3-lr)
+ y = [] # outputs
+ for si, fi in zip(s, f):
+ xi = scale_img(x.flip(fi) if fi else x, si, gs=int(self.stride.max()))
+ yi = self._forward_once(xi)[0] # forward
+ # cv2.imwrite(f'img_{si}.jpg', 255 * xi[0].cpu().numpy().transpose((1, 2, 0))[:, :, ::-1]) # save
+ yi = self._descale_pred(yi, fi, si, img_size)
+ y.append(yi)
+ y = self._clip_augmented(y) # clip augmented tails
+ return torch.cat(y, 1), None # augmented inference, train
+
+ def _forward_once(self, x, profile=False, visualize=False):
+ y, dt = [], [] # outputs
+ for m in self.model:
+ if m.f != -1: # if not from previous layer
+ x = y[m.f] if isinstance(m.f, int) else [x if j == -1 else y[j] for j in m.f] # from earlier layers
+ if profile:
+ self._profile_one_layer(m, x, dt)
+ x = m(x) # run
+ y.append(x if m.i in self.save else None) # save output
+ if visualize:
+ feature_visualization(x, m.type, m.i, save_dir=visualize)
+ return x
+
+ def _descale_pred(self, p, flips, scale, img_size):
+ # de-scale predictions following augmented inference (inverse operation)
+ if self.inplace:
+ p[..., :4] /= scale # de-scale
+ if flips == 2:
+ p[..., 1] = img_size[0] - p[..., 1] # de-flip ud
+ elif flips == 3:
+ p[..., 0] = img_size[1] - p[..., 0] # de-flip lr
+ else:
+ x, y, wh = p[..., 0:1] / scale, p[..., 1:2] / scale, p[..., 2:4] / scale # de-scale
+ if flips == 2:
+ y = img_size[0] - y # de-flip ud
+ elif flips == 3:
+ x = img_size[1] - x # de-flip lr
+ p = torch.cat((x, y, wh, p[..., 4:]), -1)
+ return p
+
+ def _clip_augmented(self, y):
+ # Clip augmented inference tails
+ nl = self.model[-1].nl # number of detection layers (P3-P5)
+ g = sum(4 ** x for x in range(nl)) # grid points
+ e = 1 # exclude layer count
+ i = (y[0].shape[1] // g) * sum(4 ** x for x in range(e)) # indices
+ y[0] = y[0][:, :-i] # large
+ i = (y[-1].shape[1] // g) * sum(4 ** (nl - 1 - x) for x in range(e)) # indices
+ y[-1] = y[-1][:, i:] # small
+ return y
+
+ def _profile_one_layer(self, m, x, dt):
+ c = isinstance(m, Detect) # is final layer, copy input as inplace fix
+ o = thop.profile(m, inputs=(x.copy() if c else x,), verbose=False)[0] / 1E9 * 2 if thop else 0 # FLOPs
+ t = time_sync()
+ for _ in range(10):
+ m(x.copy() if c else x)
+ dt.append((time_sync() - t) * 100)
+ if m == self.model[0]:
+ LOGGER.info(f"{'time (ms)':>10s} {'GFLOPs':>10s} {'params':>10s} {'module'}")
+ LOGGER.info(f'{dt[-1]:10.2f} {o:10.2f} {m.np:10.0f} {m.type}')
+ if c:
+ LOGGER.info(f"{sum(dt):10.2f} {'-':>10s} {'-':>10s} Total")
+
+ def _initialize_biases(self, cf=None): # initialize biases into Detect(), cf is class frequency
+ # https://arxiv.org/abs/1708.02002 section 3.3
+ # cf = torch.bincount(torch.tensor(np.concatenate(dataset.labels, 0)[:, 0]).long(), minlength=nc) + 1.
+ m = self.model[-1] # Detect() module
+ for mi, s in zip(m.m, m.stride): # from
+ b = mi.bias.view(m.na, -1) # conv.bias(255) to (3,85)
+ b.data[:, 4] += math.log(8 / (640 / s) ** 2) # obj (8 objects per 640 image)
+ b.data[:, 5:] += math.log(0.6 / (m.nc - 0.999999)) if cf is None else torch.log(cf / cf.sum()) # cls
+ mi.bias = torch.nn.Parameter(b.view(-1), requires_grad=True)
+
+ def _print_biases(self):
+ m = self.model[-1] # Detect() module
+ for mi in m.m: # from
+ b = mi.bias.detach().view(m.na, -1).T # conv.bias(255) to (3,85)
+ LOGGER.info(
+ ('%6g Conv2d.bias:' + '%10.3g' * 6) % (mi.weight.shape[1], *b[:5].mean(1).tolist(), b[5:].mean()))
+
+ # def _print_weights(self):
+ # for m in self.model.modules():
+ # if type(m) is Bottleneck:
+ # LOGGER.info('%10.3g' % (m.w.detach().sigmoid() * 2)) # shortcut weights
+
+ def fuse(self): # fuse model Conv2d() + BatchNorm2d() layers
+ LOGGER.info('Fusing layers... ')
+ for m in self.model.modules():
+ if isinstance(m, (Conv, DWConv)) and hasattr(m, 'bn'):
+ m.conv = fuse_conv_and_bn(m.conv, m.bn) # update conv
+ delattr(m, 'bn') # remove batchnorm
+ m.forward = m.forward_fuse # update forward
+ self.info()
+ return self
+
+ def autoshape(self): # add AutoShape module
+ LOGGER.info('Adding AutoShape... ')
+ m = AutoShape(self) # wrap model
+ copy_attr(m, self, include=('yaml', 'nc', 'hyp', 'names', 'stride'), exclude=()) # copy attributes
+ return m
+
+ def info(self, verbose=False, img_size=640): # print model information
+ model_info(self, verbose, img_size)
+
+ def _apply(self, fn):
+ # Apply to(), cpu(), cuda(), half() to model tensors that are not parameters or registered buffers
+ self = super()._apply(fn)
+ m = self.model[-1] # Detect()
+ if isinstance(m, Detect):
+ m.stride = fn(m.stride)
+ m.grid = list(map(fn, m.grid))
+ if isinstance(m.anchor_grid, list):
+ m.anchor_grid = list(map(fn, m.anchor_grid))
+ return self
+
+
+def parse_model(d, ch): # model_dict, input_channels(3)
+ LOGGER.info(f"\n{'':>3}{'from':>18}{'n':>3}{'params':>10} {'module':<40}{'arguments':<30}")
+ anchors, nc, gd, gw = d['anchors'], d['nc'], d['depth_multiple'], d['width_multiple']
+ na = (len(anchors[0]) // 2) if isinstance(anchors, list) else anchors # number of anchors
+ no = na * (nc + 5) # number of outputs = anchors * (classes + 5)
+
+ layers, save, c2 = [], [], ch[-1] # layers, savelist, ch out
+ for i, (f, n, m, args) in enumerate(d['backbone'] + d['head']): # from, number, module, args
+ m = eval(m) if isinstance(m, str) else m # eval strings
+ for j, a in enumerate(args):
+ try:
+ args[j] = eval(a) if isinstance(a, str) else a # eval strings
+ except NameError:
+ pass
+
+ n = n_ = max(round(n * gd), 1) if n > 1 else n # depth gain
+ if m in [Conv, GhostConv, Bottleneck, GhostBottleneck, SPP, SPPF, DWConv, MixConv2d, Focus, CrossConv,
+ BottleneckCSP, C3, C3TR, C3SPP, C3Ghost]:
+ c1, c2 = ch[f], args[0]
+ if c2 != no: # if not output
+ c2 = make_divisible(c2 * gw, 8)
+
+ args = [c1, c2, *args[1:]]
+ if m in [BottleneckCSP, C3, C3TR, C3Ghost]:
+ args.insert(2, n) # number of repeats
+ n = 1
+ elif m is nn.BatchNorm2d:
+ args = [ch[f]]
+ elif m is Concat:
+ c2 = sum(ch[x] for x in f)
+ elif m is Detect:
+ args.append([ch[x] for x in f])
+ if isinstance(args[1], int): # number of anchors
+ args[1] = [list(range(args[1] * 2))] * len(f)
+ elif m is Contract:
+ c2 = ch[f] * args[0] ** 2
+ elif m is Expand:
+ c2 = ch[f] // args[0] ** 2
+ else:
+ c2 = ch[f]
+
+ m_ = nn.Sequential(*(m(*args) for _ in range(n))) if n > 1 else m(*args) # module
+ t = str(m)[8:-2].replace('__main__.', '') # module type
+ np = sum(x.numel() for x in m_.parameters()) # number params
+ m_.i, m_.f, m_.type, m_.np = i, f, t, np # attach index, 'from' index, type, number params
+ LOGGER.info(f'{i:>3}{str(f):>18}{n_:>3}{np:10.0f} {t:<40}{str(args):<30}') # print
+ save.extend(x % i for x in ([f] if isinstance(f, int) else f) if x != -1) # append to savelist
+ layers.append(m_)
+ if i == 0:
+ ch = []
+ ch.append(c2)
+ return nn.Sequential(*layers), sorted(save)
+
+
+if __name__ == '__main__':
+ parser = argparse.ArgumentParser()
+ parser.add_argument('--cfg', type=str, default='yolov3yaml', help='model.yaml')
+ parser.add_argument('--device', default='', help='cuda device, i.e. 0 or 0,1,2,3 or cpu')
+ parser.add_argument('--profile', action='store_true', help='profile model speed')
+ parser.add_argument('--test', action='store_true', help='test all yolo*.yaml')
+ opt = parser.parse_args()
+ opt.cfg = check_yaml(opt.cfg) # check YAML
+ print_args(FILE.stem, opt)
+ device = select_device(opt.device)
+
+ # Create model
+ model = Model(opt.cfg).to(device)
+ model.train()
+
+ # Profile
+ if opt.profile:
+ img = torch.rand(8 if torch.cuda.is_available() else 1, 3, 640, 640).to(device)
+ y = model(img, profile=True)
+
+ # Test all models
+ if opt.test:
+ for cfg in Path(ROOT / 'models').rglob('yolo*.yaml'):
+ try:
+ _ = Model(cfg)
+ except Exception as e:
+ print(f'Error in {cfg}: {e}')
+
+ # Tensorboard (not working https://github.com/ultralytics/yolov5/issues/2898)
+ # from torch.utils.tensorboard import SummaryWriter
+ # tb_writer = SummaryWriter('.')
+ # LOGGER.info("Run 'tensorboard --logdir=models' to view tensorboard at http://localhost:6006/")
+ # tb_writer.add_graph(torch.jit.trace(model, img, strict=False), []) # add model graph
diff --git a/ros2_ws/src/yolov3_ros/models/yolov3-spp.yaml b/ros2_ws/src/yolov3_ros/models/yolov3-spp.yaml
new file mode 100644
index 00000000..04593a47
--- /dev/null
+++ b/ros2_ws/src/yolov3_ros/models/yolov3-spp.yaml
@@ -0,0 +1,51 @@
+# YOLOv3 🚀 by Ultralytics, GPL-3.0 license
+
+# Parameters
+nc: 80 # number of classes
+depth_multiple: 1.0 # model depth multiple
+width_multiple: 1.0 # layer channel multiple
+anchors:
+ - [10,13, 16,30, 33,23] # P3/8
+ - [30,61, 62,45, 59,119] # P4/16
+ - [116,90, 156,198, 373,326] # P5/32
+
+# darknet53 backbone
+backbone:
+ # [from, number, module, args]
+ [[-1, 1, Conv, [32, 3, 1]], # 0
+ [-1, 1, Conv, [64, 3, 2]], # 1-P1/2
+ [-1, 1, Bottleneck, [64]],
+ [-1, 1, Conv, [128, 3, 2]], # 3-P2/4
+ [-1, 2, Bottleneck, [128]],
+ [-1, 1, Conv, [256, 3, 2]], # 5-P3/8
+ [-1, 8, Bottleneck, [256]],
+ [-1, 1, Conv, [512, 3, 2]], # 7-P4/16
+ [-1, 8, Bottleneck, [512]],
+ [-1, 1, Conv, [1024, 3, 2]], # 9-P5/32
+ [-1, 4, Bottleneck, [1024]], # 10
+ ]
+
+# YOLOv3-SPP head
+head:
+ [[-1, 1, Bottleneck, [1024, False]],
+ [-1, 1, SPP, [512, [5, 9, 13]]],
+ [-1, 1, Conv, [1024, 3, 1]],
+ [-1, 1, Conv, [512, 1, 1]],
+ [-1, 1, Conv, [1024, 3, 1]], # 15 (P5/32-large)
+
+ [-2, 1, Conv, [256, 1, 1]],
+ [-1, 1, nn.Upsample, [None, 2, 'nearest']],
+ [[-1, 8], 1, Concat, [1]], # cat backbone P4
+ [-1, 1, Bottleneck, [512, False]],
+ [-1, 1, Bottleneck, [512, False]],
+ [-1, 1, Conv, [256, 1, 1]],
+ [-1, 1, Conv, [512, 3, 1]], # 22 (P4/16-medium)
+
+ [-2, 1, Conv, [128, 1, 1]],
+ [-1, 1, nn.Upsample, [None, 2, 'nearest']],
+ [[-1, 6], 1, Concat, [1]], # cat backbone P3
+ [-1, 1, Bottleneck, [256, False]],
+ [-1, 2, Bottleneck, [256, False]], # 27 (P3/8-small)
+
+ [[27, 22, 15], 1, Detect, [nc, anchors]], # Detect(P3, P4, P5)
+ ]
diff --git a/ros2_ws/src/yolov3_ros/models/yolov3-tiny.yaml b/ros2_ws/src/yolov3_ros/models/yolov3-tiny.yaml
new file mode 100644
index 00000000..04f9b446
--- /dev/null
+++ b/ros2_ws/src/yolov3_ros/models/yolov3-tiny.yaml
@@ -0,0 +1,41 @@
+# YOLOv3 🚀 by Ultralytics, GPL-3.0 license
+
+# Parameters
+nc: 80 # number of classes
+depth_multiple: 1.0 # model depth multiple
+width_multiple: 1.0 # layer channel multiple
+anchors:
+ - [10,14, 23,27, 37,58] # P4/16
+ - [81,82, 135,169, 344,319] # P5/32
+
+# YOLOv3-tiny backbone
+backbone:
+ # [from, number, module, args]
+ [[-1, 1, Conv, [16, 3, 1]], # 0
+ [-1, 1, nn.MaxPool2d, [2, 2, 0]], # 1-P1/2
+ [-1, 1, Conv, [32, 3, 1]],
+ [-1, 1, nn.MaxPool2d, [2, 2, 0]], # 3-P2/4
+ [-1, 1, Conv, [64, 3, 1]],
+ [-1, 1, nn.MaxPool2d, [2, 2, 0]], # 5-P3/8
+ [-1, 1, Conv, [128, 3, 1]],
+ [-1, 1, nn.MaxPool2d, [2, 2, 0]], # 7-P4/16
+ [-1, 1, Conv, [256, 3, 1]],
+ [-1, 1, nn.MaxPool2d, [2, 2, 0]], # 9-P5/32
+ [-1, 1, Conv, [512, 3, 1]],
+ [-1, 1, nn.ZeroPad2d, [[0, 1, 0, 1]]], # 11
+ [-1, 1, nn.MaxPool2d, [2, 1, 0]], # 12
+ ]
+
+# YOLOv3-tiny head
+head:
+ [[-1, 1, Conv, [1024, 3, 1]],
+ [-1, 1, Conv, [256, 1, 1]],
+ [-1, 1, Conv, [512, 3, 1]], # 15 (P5/32-large)
+
+ [-2, 1, Conv, [128, 1, 1]],
+ [-1, 1, nn.Upsample, [None, 2, 'nearest']],
+ [[-1, 8], 1, Concat, [1]], # cat backbone P4
+ [-1, 1, Conv, [256, 3, 1]], # 19 (P4/16-medium)
+
+ [[19, 15], 1, Detect, [nc, anchors]], # Detect(P4, P5)
+ ]
diff --git a/ros2_ws/src/yolov3_ros/models/yolov3.yaml b/ros2_ws/src/yolov3_ros/models/yolov3.yaml
new file mode 100644
index 00000000..22259434
--- /dev/null
+++ b/ros2_ws/src/yolov3_ros/models/yolov3.yaml
@@ -0,0 +1,51 @@
+# YOLOv3 🚀 by Ultralytics, GPL-3.0 license
+
+# Parameters
+nc: 4 # number of classes
+depth_multiple: 1.0 # model depth multiple
+width_multiple: 1.0 # layer channel multiple
+anchors:
+ - [10,13, 16,30, 33,23] # P3/8
+ - [30,61, 62,45, 59,119] # P4/16
+ - [116,90, 156,198, 373,326] # P5/32
+
+# darknet53 backbone
+backbone:
+ # [from, number, module, args]
+ [[-1, 1, Conv, [32, 3, 1]], # 0
+ [-1, 1, Conv, [64, 3, 2]], # 1-P1/2
+ [-1, 1, Bottleneck, [64]],
+ [-1, 1, Conv, [128, 3, 2]], # 3-P2/4
+ [-1, 2, Bottleneck, [128]],
+ [-1, 1, Conv, [256, 3, 2]], # 5-P3/8
+ [-1, 8, Bottleneck, [256]],
+ [-1, 1, Conv, [512, 3, 2]], # 7-P4/16
+ [-1, 8, Bottleneck, [512]],
+ [-1, 1, Conv, [1024, 3, 2]], # 9-P5/32
+ [-1, 4, Bottleneck, [1024]], # 10
+ ]
+
+# YOLOv3 head
+head:
+ [[-1, 1, Bottleneck, [1024, False]],
+ [-1, 1, Conv, [512, 1, 1]],
+ [-1, 1, Conv, [1024, 3, 1]],
+ [-1, 1, Conv, [512, 1, 1]],
+ [-1, 1, Conv, [1024, 3, 1]], # 15 (P5/32-large)
+
+ [-2, 1, Conv, [256, 1, 1]],
+ [-1, 1, nn.Upsample, [None, 2, 'nearest']],
+ [[-1, 8], 1, Concat, [1]], # cat backbone P4
+ [-1, 1, Bottleneck, [512, False]],
+ [-1, 1, Bottleneck, [512, False]],
+ [-1, 1, Conv, [256, 1, 1]],
+ [-1, 1, Conv, [512, 3, 1]], # 22 (P4/16-medium)
+
+ [-2, 1, Conv, [128, 1, 1]],
+ [-1, 1, nn.Upsample, [None, 2, 'nearest']],
+ [[-1, 6], 1, Concat, [1]], # cat backbone P3
+ [-1, 1, Bottleneck, [256, False]],
+ [-1, 2, Bottleneck, [256, False]], # 27 (P3/8-small)
+
+ [[27, 22, 15], 1, Detect, [nc, anchors]], # Detect(P3, P4, P5)
+ ]
\ No newline at end of file
diff --git a/ros2_ws/src/yolov3_ros/models/yolov5l.yaml b/ros2_ws/src/yolov3_ros/models/yolov5l.yaml
new file mode 100644
index 00000000..2c3a7c17
--- /dev/null
+++ b/ros2_ws/src/yolov3_ros/models/yolov5l.yaml
@@ -0,0 +1,48 @@
+# YOLOv3 🚀 by Ultralytics, GPL-3.0 license
+
+# Parameters
+nc: 80 # number of classes
+depth_multiple: 1.0 # model depth multiple
+width_multiple: 1.0 # layer channel multiple
+anchors:
+ - [10,13, 16,30, 33,23] # P3/8
+ - [30,61, 62,45, 59,119] # P4/16
+ - [116,90, 156,198, 373,326] # P5/32
+
+# YOLOv5 v6.0 backbone
+backbone:
+ # [from, number, module, args]
+ [[-1, 1, Conv, [64, 6, 2, 2]], # 0-P1/2
+ [-1, 1, Conv, [128, 3, 2]], # 1-P2/4
+ [-1, 3, C3, [128]],
+ [-1, 1, Conv, [256, 3, 2]], # 3-P3/8
+ [-1, 6, C3, [256]],
+ [-1, 1, Conv, [512, 3, 2]], # 5-P4/16
+ [-1, 9, C3, [512]],
+ [-1, 1, Conv, [1024, 3, 2]], # 7-P5/32
+ [-1, 3, C3, [1024]],
+ [-1, 1, SPPF, [1024, 5]], # 9
+ ]
+
+# YOLOv5 v6.0 head
+head:
+ [[-1, 1, Conv, [512, 1, 1]],
+ [-1, 1, nn.Upsample, [None, 2, 'nearest']],
+ [[-1, 6], 1, Concat, [1]], # cat backbone P4
+ [-1, 3, C3, [512, False]], # 13
+
+ [-1, 1, Conv, [256, 1, 1]],
+ [-1, 1, nn.Upsample, [None, 2, 'nearest']],
+ [[-1, 4], 1, Concat, [1]], # cat backbone P3
+ [-1, 3, C3, [256, False]], # 17 (P3/8-small)
+
+ [-1, 1, Conv, [256, 3, 2]],
+ [[-1, 14], 1, Concat, [1]], # cat head P4
+ [-1, 3, C3, [512, False]], # 20 (P4/16-medium)
+
+ [-1, 1, Conv, [512, 3, 2]],
+ [[-1, 10], 1, Concat, [1]], # cat head P5
+ [-1, 3, C3, [1024, False]], # 23 (P5/32-large)
+
+ [[17, 20, 23], 1, Detect, [nc, anchors]], # Detect(P3, P4, P5)
+ ]
diff --git a/ros2_ws/src/yolov3_ros/models/yolov5m.yaml b/ros2_ws/src/yolov3_ros/models/yolov5m.yaml
new file mode 100644
index 00000000..f0ee2907
--- /dev/null
+++ b/ros2_ws/src/yolov3_ros/models/yolov5m.yaml
@@ -0,0 +1,48 @@
+# YOLOv3 🚀 by Ultralytics, GPL-3.0 license
+
+# Parameters
+nc: 80 # number of classes
+depth_multiple: 0.67 # model depth multiple
+width_multiple: 0.75 # layer channel multiple
+anchors:
+ - [10,13, 16,30, 33,23] # P3/8
+ - [30,61, 62,45, 59,119] # P4/16
+ - [116,90, 156,198, 373,326] # P5/32
+
+# YOLOv5 v6.0 backbone
+backbone:
+ # [from, number, module, args]
+ [[-1, 1, Conv, [64, 6, 2, 2]], # 0-P1/2
+ [-1, 1, Conv, [128, 3, 2]], # 1-P2/4
+ [-1, 3, C3, [128]],
+ [-1, 1, Conv, [256, 3, 2]], # 3-P3/8
+ [-1, 6, C3, [256]],
+ [-1, 1, Conv, [512, 3, 2]], # 5-P4/16
+ [-1, 9, C3, [512]],
+ [-1, 1, Conv, [1024, 3, 2]], # 7-P5/32
+ [-1, 3, C3, [1024]],
+ [-1, 1, SPPF, [1024, 5]], # 9
+ ]
+
+# YOLOv5 v6.0 head
+head:
+ [[-1, 1, Conv, [512, 1, 1]],
+ [-1, 1, nn.Upsample, [None, 2, 'nearest']],
+ [[-1, 6], 1, Concat, [1]], # cat backbone P4
+ [-1, 3, C3, [512, False]], # 13
+
+ [-1, 1, Conv, [256, 1, 1]],
+ [-1, 1, nn.Upsample, [None, 2, 'nearest']],
+ [[-1, 4], 1, Concat, [1]], # cat backbone P3
+ [-1, 3, C3, [256, False]], # 17 (P3/8-small)
+
+ [-1, 1, Conv, [256, 3, 2]],
+ [[-1, 14], 1, Concat, [1]], # cat head P4
+ [-1, 3, C3, [512, False]], # 20 (P4/16-medium)
+
+ [-1, 1, Conv, [512, 3, 2]],
+ [[-1, 10], 1, Concat, [1]], # cat head P5
+ [-1, 3, C3, [1024, False]], # 23 (P5/32-large)
+
+ [[17, 20, 23], 1, Detect, [nc, anchors]], # Detect(P3, P4, P5)
+ ]
diff --git a/ros2_ws/src/yolov3_ros/models/yolov5n.yaml b/ros2_ws/src/yolov3_ros/models/yolov5n.yaml
new file mode 100644
index 00000000..a4b72660
--- /dev/null
+++ b/ros2_ws/src/yolov3_ros/models/yolov5n.yaml
@@ -0,0 +1,48 @@
+# YOLOv3 🚀 by Ultralytics, GPL-3.0 license
+
+# Parameters
+nc: 80 # number of classes
+depth_multiple: 0.33 # model depth multiple
+width_multiple: 0.25 # layer channel multiple
+anchors:
+ - [10,13, 16,30, 33,23] # P3/8
+ - [30,61, 62,45, 59,119] # P4/16
+ - [116,90, 156,198, 373,326] # P5/32
+
+# YOLOv5 v6.0 backbone
+backbone:
+ # [from, number, module, args]
+ [[-1, 1, Conv, [64, 6, 2, 2]], # 0-P1/2
+ [-1, 1, Conv, [128, 3, 2]], # 1-P2/4
+ [-1, 3, C3, [128]],
+ [-1, 1, Conv, [256, 3, 2]], # 3-P3/8
+ [-1, 6, C3, [256]],
+ [-1, 1, Conv, [512, 3, 2]], # 5-P4/16
+ [-1, 9, C3, [512]],
+ [-1, 1, Conv, [1024, 3, 2]], # 7-P5/32
+ [-1, 3, C3, [1024]],
+ [-1, 1, SPPF, [1024, 5]], # 9
+ ]
+
+# YOLOv5 v6.0 head
+head:
+ [[-1, 1, Conv, [512, 1, 1]],
+ [-1, 1, nn.Upsample, [None, 2, 'nearest']],
+ [[-1, 6], 1, Concat, [1]], # cat backbone P4
+ [-1, 3, C3, [512, False]], # 13
+
+ [-1, 1, Conv, [256, 1, 1]],
+ [-1, 1, nn.Upsample, [None, 2, 'nearest']],
+ [[-1, 4], 1, Concat, [1]], # cat backbone P3
+ [-1, 3, C3, [256, False]], # 17 (P3/8-small)
+
+ [-1, 1, Conv, [256, 3, 2]],
+ [[-1, 14], 1, Concat, [1]], # cat head P4
+ [-1, 3, C3, [512, False]], # 20 (P4/16-medium)
+
+ [-1, 1, Conv, [512, 3, 2]],
+ [[-1, 10], 1, Concat, [1]], # cat head P5
+ [-1, 3, C3, [1024, False]], # 23 (P5/32-large)
+
+ [[17, 20, 23], 1, Detect, [nc, anchors]], # Detect(P3, P4, P5)
+ ]
diff --git a/ros2_ws/src/yolov3_ros/models/yolov5s.yaml b/ros2_ws/src/yolov3_ros/models/yolov5s.yaml
new file mode 100644
index 00000000..b3edebe9
--- /dev/null
+++ b/ros2_ws/src/yolov3_ros/models/yolov5s.yaml
@@ -0,0 +1,48 @@
+# YOLOv3 🚀 by Ultralytics, GPL-3.0 license
+
+# Parameters
+nc: 80 # number of classes
+depth_multiple: 0.33 # model depth multiple
+width_multiple: 0.50 # layer channel multiple
+anchors:
+ - [10,13, 16,30, 33,23] # P3/8
+ - [30,61, 62,45, 59,119] # P4/16
+ - [116,90, 156,198, 373,326] # P5/32
+
+# YOLOv5 v6.0 backbone
+backbone:
+ # [from, number, module, args]
+ [[-1, 1, Conv, [64, 6, 2, 2]], # 0-P1/2
+ [-1, 1, Conv, [128, 3, 2]], # 1-P2/4
+ [-1, 3, C3, [128]],
+ [-1, 1, Conv, [256, 3, 2]], # 3-P3/8
+ [-1, 6, C3, [256]],
+ [-1, 1, Conv, [512, 3, 2]], # 5-P4/16
+ [-1, 9, C3, [512]],
+ [-1, 1, Conv, [1024, 3, 2]], # 7-P5/32
+ [-1, 3, C3, [1024]],
+ [-1, 1, SPPF, [1024, 5]], # 9
+ ]
+
+# YOLOv5 v6.0 head
+head:
+ [[-1, 1, Conv, [512, 1, 1]],
+ [-1, 1, nn.Upsample, [None, 2, 'nearest']],
+ [[-1, 6], 1, Concat, [1]], # cat backbone P4
+ [-1, 3, C3, [512, False]], # 13
+
+ [-1, 1, Conv, [256, 1, 1]],
+ [-1, 1, nn.Upsample, [None, 2, 'nearest']],
+ [[-1, 4], 1, Concat, [1]], # cat backbone P3
+ [-1, 3, C3, [256, False]], # 17 (P3/8-small)
+
+ [-1, 1, Conv, [256, 3, 2]],
+ [[-1, 14], 1, Concat, [1]], # cat head P4
+ [-1, 3, C3, [512, False]], # 20 (P4/16-medium)
+
+ [-1, 1, Conv, [512, 3, 2]],
+ [[-1, 10], 1, Concat, [1]], # cat head P5
+ [-1, 3, C3, [1024, False]], # 23 (P5/32-large)
+
+ [[17, 20, 23], 1, Detect, [nc, anchors]], # Detect(P3, P4, P5)
+ ]
diff --git a/ros2_ws/src/yolov3_ros/models/yolov5x.yaml b/ros2_ws/src/yolov3_ros/models/yolov5x.yaml
new file mode 100644
index 00000000..d8c7dd78
--- /dev/null
+++ b/ros2_ws/src/yolov3_ros/models/yolov5x.yaml
@@ -0,0 +1,48 @@
+# YOLOv3 🚀 by Ultralytics, GPL-3.0 license
+
+# Parameters
+nc: 80 # number of classes
+depth_multiple: 1.33 # model depth multiple
+width_multiple: 1.25 # layer channel multiple
+anchors:
+ - [10,13, 16,30, 33,23] # P3/8
+ - [30,61, 62,45, 59,119] # P4/16
+ - [116,90, 156,198, 373,326] # P5/32
+
+# YOLOv5 v6.0 backbone
+backbone:
+ # [from, number, module, args]
+ [[-1, 1, Conv, [64, 6, 2, 2]], # 0-P1/2
+ [-1, 1, Conv, [128, 3, 2]], # 1-P2/4
+ [-1, 3, C3, [128]],
+ [-1, 1, Conv, [256, 3, 2]], # 3-P3/8
+ [-1, 6, C3, [256]],
+ [-1, 1, Conv, [512, 3, 2]], # 5-P4/16
+ [-1, 9, C3, [512]],
+ [-1, 1, Conv, [1024, 3, 2]], # 7-P5/32
+ [-1, 3, C3, [1024]],
+ [-1, 1, SPPF, [1024, 5]], # 9
+ ]
+
+# YOLOv5 v6.0 head
+head:
+ [[-1, 1, Conv, [512, 1, 1]],
+ [-1, 1, nn.Upsample, [None, 2, 'nearest']],
+ [[-1, 6], 1, Concat, [1]], # cat backbone P4
+ [-1, 3, C3, [512, False]], # 13
+
+ [-1, 1, Conv, [256, 1, 1]],
+ [-1, 1, nn.Upsample, [None, 2, 'nearest']],
+ [[-1, 4], 1, Concat, [1]], # cat backbone P3
+ [-1, 3, C3, [256, False]], # 17 (P3/8-small)
+
+ [-1, 1, Conv, [256, 3, 2]],
+ [[-1, 14], 1, Concat, [1]], # cat head P4
+ [-1, 3, C3, [512, False]], # 20 (P4/16-medium)
+
+ [-1, 1, Conv, [512, 3, 2]],
+ [[-1, 10], 1, Concat, [1]], # cat head P5
+ [-1, 3, C3, [1024, False]], # 23 (P5/32-large)
+
+ [[17, 20, 23], 1, Detect, [nc, anchors]], # Detect(P3, P4, P5)
+ ]
diff --git a/ros2_ws/src/yolov3_ros/package.xml b/ros2_ws/src/yolov3_ros/package.xml
new file mode 100644
index 00000000..2aa233c3
--- /dev/null
+++ b/ros2_ws/src/yolov3_ros/package.xml
@@ -0,0 +1,18 @@
+
+
+
+ yolov3_ros
+ 0.0.0
+ TODO: Package description
+ parallels
+ TODO: License declaration
+
+ ament_copyright
+ ament_flake8
+ ament_pep257
+ python3-pytest
+
+
+ ament_python
+
+
diff --git a/ros2_ws/src/yolov3_ros/resource/yolov3_ros b/ros2_ws/src/yolov3_ros/resource/yolov3_ros
new file mode 100644
index 00000000..e69de29b
diff --git a/ros2_ws/src/yolov3_ros/setup.cfg b/ros2_ws/src/yolov3_ros/setup.cfg
new file mode 100644
index 00000000..bbbb66ea
--- /dev/null
+++ b/ros2_ws/src/yolov3_ros/setup.cfg
@@ -0,0 +1,4 @@
+[develop]
+script_dir=$base/lib/yolov3_ros
+[install]
+install_scripts=$base/lib/yolov3_ros
diff --git a/ros2_ws/src/yolov3_ros/setup.py b/ros2_ws/src/yolov3_ros/setup.py
new file mode 100644
index 00000000..4fe99b79
--- /dev/null
+++ b/ros2_ws/src/yolov3_ros/setup.py
@@ -0,0 +1,43 @@
+from setuptools import setup
+import os
+from glob import glob
+
+package_name = 'yolov3_ros'
+
+setup(
+ name=package_name,
+ version='0.0.0',
+ packages=[
+ package_name
+ ],
+ data_files=[
+ ('share/ament_index/resource_index/packages',
+ ['resource/' + package_name]),
+ ('share/' + package_name, ['package.xml']),
+ (os.path.join('lib', package_name, 'models'), glob('models/*.py')),
+ (os.path.join('lib', package_name, 'models'), glob('models/segment/*')),
+ (os.path.join('lib', package_name, 'models'), glob('models/hub/*')),
+ (os.path.join('lib', package_name, 'utils'), glob('utils/*.py')),
+ (os.path.join('lib', package_name, 'utils'), glob('utils/aws/*')),
+ (os.path.join('lib', package_name, 'utils'), glob('utils/docker/*')),
+ (os.path.join('lib', package_name, 'utils'), glob('utils/flask_rest_api/*')),
+ (os.path.join('lib', package_name, 'utils'), glob('utils/google_app_engine/*')),
+ (os.path.join('lib', package_name, 'utils'), glob('utils/loggers/comet/*')),
+ (os.path.join('lib', package_name, 'utils'), glob('utils/loggers/wandb/*')),
+ (os.path.join('lib', package_name, 'utils'), glob('utils/loggers/clearml/*')),
+ (os.path.join('lib', package_name, 'utils'), glob('utils/segment/*')),
+ (os.path.join('share', package_name, 'launch'), glob('launch/*.launch.py')),
+ ],
+ install_requires=['setuptools'],
+ zip_safe=True,
+ maintainer='parallels',
+ maintainer_email='eic.apoorva@gmail.com',
+ description='TODO: Package description',
+ license='TODO: License declaration',
+ tests_require=['pytest'],
+ entry_points={
+ 'console_scripts': [
+ 'yolov3_ros_node = yolov3_ros.yolov3_ros_node:main'
+ ],
+ },
+)
diff --git a/ros2_ws/src/yolov3_ros/test/test_copyright.py b/ros2_ws/src/yolov3_ros/test/test_copyright.py
new file mode 100644
index 00000000..97a39196
--- /dev/null
+++ b/ros2_ws/src/yolov3_ros/test/test_copyright.py
@@ -0,0 +1,25 @@
+# Copyright 2015 Open Source Robotics Foundation, Inc.
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+# http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+
+from ament_copyright.main import main
+import pytest
+
+
+# Remove the `skip` decorator once the source file(s) have a copyright header
+@pytest.mark.skip(reason='No copyright header has been placed in the generated source file.')
+@pytest.mark.copyright
+@pytest.mark.linter
+def test_copyright():
+ rc = main(argv=['.', 'test'])
+ assert rc == 0, 'Found errors'
diff --git a/ros2_ws/src/yolov3_ros/test/test_flake8.py b/ros2_ws/src/yolov3_ros/test/test_flake8.py
new file mode 100644
index 00000000..27ee1078
--- /dev/null
+++ b/ros2_ws/src/yolov3_ros/test/test_flake8.py
@@ -0,0 +1,25 @@
+# Copyright 2017 Open Source Robotics Foundation, Inc.
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+# http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+
+from ament_flake8.main import main_with_errors
+import pytest
+
+
+@pytest.mark.flake8
+@pytest.mark.linter
+def test_flake8():
+ rc, errors = main_with_errors(argv=[])
+ assert rc == 0, \
+ 'Found %d code style errors / warnings:\n' % len(errors) + \
+ '\n'.join(errors)
diff --git a/ros2_ws/src/yolov3_ros/test/test_pep257.py b/ros2_ws/src/yolov3_ros/test/test_pep257.py
new file mode 100644
index 00000000..b234a384
--- /dev/null
+++ b/ros2_ws/src/yolov3_ros/test/test_pep257.py
@@ -0,0 +1,23 @@
+# Copyright 2015 Open Source Robotics Foundation, Inc.
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+# http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+
+from ament_pep257.main import main
+import pytest
+
+
+@pytest.mark.linter
+@pytest.mark.pep257
+def test_pep257():
+ rc = main(argv=['.', 'test'])
+ assert rc == 0, 'Found code style errors / warnings'
diff --git a/ros2_ws/src/yolov3_ros/utils/__init__.py b/ros2_ws/src/yolov3_ros/utils/__init__.py
new file mode 100644
index 00000000..309830c8
--- /dev/null
+++ b/ros2_ws/src/yolov3_ros/utils/__init__.py
@@ -0,0 +1,18 @@
+# YOLOv3 🚀 by Ultralytics, GPL-3.0 license
+"""
+utils/initialization
+"""
+
+
+def notebook_init():
+ # For notebooks
+ print('Checking setup...')
+ from IPython import display # to display images and clear console output
+
+ from utils.general import emojis
+ from utils.torch_utils import select_device # imports
+
+ display.clear_output()
+ select_device(newline=False)
+ print(emojis('Setup complete ✅'))
+ return display
diff --git a/ros2_ws/src/yolov3_ros/utils/__pycache__/__init__.cpython-310.pyc b/ros2_ws/src/yolov3_ros/utils/__pycache__/__init__.cpython-310.pyc
new file mode 100644
index 00000000..4e11931a
Binary files /dev/null and b/ros2_ws/src/yolov3_ros/utils/__pycache__/__init__.cpython-310.pyc differ
diff --git a/ros2_ws/src/yolov3_ros/utils/__pycache__/augmentations.cpython-310.pyc b/ros2_ws/src/yolov3_ros/utils/__pycache__/augmentations.cpython-310.pyc
new file mode 100644
index 00000000..cfc64bae
Binary files /dev/null and b/ros2_ws/src/yolov3_ros/utils/__pycache__/augmentations.cpython-310.pyc differ
diff --git a/ros2_ws/src/yolov3_ros/utils/__pycache__/autoanchor.cpython-310.pyc b/ros2_ws/src/yolov3_ros/utils/__pycache__/autoanchor.cpython-310.pyc
new file mode 100644
index 00000000..ee7ba84b
Binary files /dev/null and b/ros2_ws/src/yolov3_ros/utils/__pycache__/autoanchor.cpython-310.pyc differ
diff --git a/ros2_ws/src/yolov3_ros/utils/__pycache__/datasets.cpython-310.pyc b/ros2_ws/src/yolov3_ros/utils/__pycache__/datasets.cpython-310.pyc
new file mode 100644
index 00000000..f665aba3
Binary files /dev/null and b/ros2_ws/src/yolov3_ros/utils/__pycache__/datasets.cpython-310.pyc differ
diff --git a/ros2_ws/src/yolov3_ros/utils/__pycache__/downloads.cpython-310.pyc b/ros2_ws/src/yolov3_ros/utils/__pycache__/downloads.cpython-310.pyc
new file mode 100644
index 00000000..6cbc4ee7
Binary files /dev/null and b/ros2_ws/src/yolov3_ros/utils/__pycache__/downloads.cpython-310.pyc differ
diff --git a/ros2_ws/src/yolov3_ros/utils/__pycache__/general.cpython-310.pyc b/ros2_ws/src/yolov3_ros/utils/__pycache__/general.cpython-310.pyc
new file mode 100644
index 00000000..686278f2
Binary files /dev/null and b/ros2_ws/src/yolov3_ros/utils/__pycache__/general.cpython-310.pyc differ
diff --git a/ros2_ws/src/yolov3_ros/utils/__pycache__/metrics.cpython-310.pyc b/ros2_ws/src/yolov3_ros/utils/__pycache__/metrics.cpython-310.pyc
new file mode 100644
index 00000000..fcc5114f
Binary files /dev/null and b/ros2_ws/src/yolov3_ros/utils/__pycache__/metrics.cpython-310.pyc differ
diff --git a/ros2_ws/src/yolov3_ros/utils/__pycache__/plots.cpython-310.pyc b/ros2_ws/src/yolov3_ros/utils/__pycache__/plots.cpython-310.pyc
new file mode 100644
index 00000000..df8a251a
Binary files /dev/null and b/ros2_ws/src/yolov3_ros/utils/__pycache__/plots.cpython-310.pyc differ
diff --git a/ros2_ws/src/yolov3_ros/utils/__pycache__/torch_utils.cpython-310.pyc b/ros2_ws/src/yolov3_ros/utils/__pycache__/torch_utils.cpython-310.pyc
new file mode 100644
index 00000000..526d3864
Binary files /dev/null and b/ros2_ws/src/yolov3_ros/utils/__pycache__/torch_utils.cpython-310.pyc differ
diff --git a/ros2_ws/src/yolov3_ros/utils/activations.py b/ros2_ws/src/yolov3_ros/utils/activations.py
new file mode 100644
index 00000000..ae2fef1c
--- /dev/null
+++ b/ros2_ws/src/yolov3_ros/utils/activations.py
@@ -0,0 +1,101 @@
+# YOLOv3 🚀 by Ultralytics, GPL-3.0 license
+"""
+Activation functions
+"""
+
+import torch
+import torch.nn as nn
+import torch.nn.functional as F
+
+
+# SiLU https://arxiv.org/pdf/1606.08415.pdf ----------------------------------------------------------------------------
+class SiLU(nn.Module): # export-friendly version of nn.SiLU()
+ @staticmethod
+ def forward(x):
+ return x * torch.sigmoid(x)
+
+
+class Hardswish(nn.Module): # export-friendly version of nn.Hardswish()
+ @staticmethod
+ def forward(x):
+ # return x * F.hardsigmoid(x) # for torchscript and CoreML
+ return x * F.hardtanh(x + 3, 0.0, 6.0) / 6.0 # for torchscript, CoreML and ONNX
+
+
+# Mish https://github.com/digantamisra98/Mish --------------------------------------------------------------------------
+class Mish(nn.Module):
+ @staticmethod
+ def forward(x):
+ return x * F.softplus(x).tanh()
+
+
+class MemoryEfficientMish(nn.Module):
+ class F(torch.autograd.Function):
+ @staticmethod
+ def forward(ctx, x):
+ ctx.save_for_backward(x)
+ return x.mul(torch.tanh(F.softplus(x))) # x * tanh(ln(1 + exp(x)))
+
+ @staticmethod
+ def backward(ctx, grad_output):
+ x = ctx.saved_tensors[0]
+ sx = torch.sigmoid(x)
+ fx = F.softplus(x).tanh()
+ return grad_output * (fx + x * sx * (1 - fx * fx))
+
+ def forward(self, x):
+ return self.F.apply(x)
+
+
+# FReLU https://arxiv.org/abs/2007.11824 -------------------------------------------------------------------------------
+class FReLU(nn.Module):
+ def __init__(self, c1, k=3): # ch_in, kernel
+ super().__init__()
+ self.conv = nn.Conv2d(c1, c1, k, 1, 1, groups=c1, bias=False)
+ self.bn = nn.BatchNorm2d(c1)
+
+ def forward(self, x):
+ return torch.max(x, self.bn(self.conv(x)))
+
+
+# ACON https://arxiv.org/pdf/2009.04759.pdf ----------------------------------------------------------------------------
+class AconC(nn.Module):
+ r""" ACON activation (activate or not).
+ AconC: (p1*x-p2*x) * sigmoid(beta*(p1*x-p2*x)) + p2*x, beta is a learnable parameter
+ according to "Activate or Not: Learning Customized Activation" .
+ """
+
+ def __init__(self, c1):
+ super().__init__()
+ self.p1 = nn.Parameter(torch.randn(1, c1, 1, 1))
+ self.p2 = nn.Parameter(torch.randn(1, c1, 1, 1))
+ self.beta = nn.Parameter(torch.ones(1, c1, 1, 1))
+
+ def forward(self, x):
+ dpx = (self.p1 - self.p2) * x
+ return dpx * torch.sigmoid(self.beta * dpx) + self.p2 * x
+
+
+class MetaAconC(nn.Module):
+ r""" ACON activation (activate or not).
+ MetaAconC: (p1*x-p2*x) * sigmoid(beta*(p1*x-p2*x)) + p2*x, beta is generated by a small network
+ according to "Activate or Not: Learning Customized Activation" .
+ """
+
+ def __init__(self, c1, k=1, s=1, r=16): # ch_in, kernel, stride, r
+ super().__init__()
+ c2 = max(r, c1 // r)
+ self.p1 = nn.Parameter(torch.randn(1, c1, 1, 1))
+ self.p2 = nn.Parameter(torch.randn(1, c1, 1, 1))
+ self.fc1 = nn.Conv2d(c1, c2, k, s, bias=True)
+ self.fc2 = nn.Conv2d(c2, c1, k, s, bias=True)
+ # self.bn1 = nn.BatchNorm2d(c2)
+ # self.bn2 = nn.BatchNorm2d(c1)
+
+ def forward(self, x):
+ y = x.mean(dim=2, keepdims=True).mean(dim=3, keepdims=True)
+ # batch-size 1 bug/instabilities https://github.com/ultralytics/yolov5/issues/2891
+ # beta = torch.sigmoid(self.bn2(self.fc2(self.bn1(self.fc1(y))))) # bug/unstable
+ beta = torch.sigmoid(self.fc2(self.fc1(y))) # bug patch BN layers removed
+ dpx = (self.p1 - self.p2) * x
+ return dpx * torch.sigmoid(beta * dpx) + self.p2 * x
diff --git a/ros2_ws/src/yolov3_ros/utils/augmentations.py b/ros2_ws/src/yolov3_ros/utils/augmentations.py
new file mode 100644
index 00000000..16685044
--- /dev/null
+++ b/ros2_ws/src/yolov3_ros/utils/augmentations.py
@@ -0,0 +1,277 @@
+# YOLOv3 🚀 by Ultralytics, GPL-3.0 license
+"""
+Image augmentation functions
+"""
+
+import math
+import random
+
+import cv2
+import numpy as np
+
+from utils.general import LOGGER, check_version, colorstr, resample_segments, segment2box
+from utils.metrics import bbox_ioa
+
+
+class Albumentations:
+ # Albumentations class (optional, only used if package is installed)
+ def __init__(self):
+ self.transform = None
+ try:
+ import albumentations as A
+ check_version(A.__version__, '1.0.3', hard=True) # version requirement
+
+ self.transform = A.Compose([
+ A.Blur(p=0.01),
+ A.MedianBlur(p=0.01),
+ A.ToGray(p=0.01),
+ A.CLAHE(p=0.01),
+ A.RandomBrightnessContrast(p=0.0),
+ A.RandomGamma(p=0.0),
+ A.ImageCompression(quality_lower=75, p=0.0)],
+ bbox_params=A.BboxParams(format='yolo', label_fields=['class_labels']))
+
+ LOGGER.info(colorstr('albumentations: ') + ', '.join(f'{x}' for x in self.transform.transforms if x.p))
+ except ImportError: # package not installed, skip
+ pass
+ except Exception as e:
+ LOGGER.info(colorstr('albumentations: ') + f'{e}')
+
+ def __call__(self, im, labels, p=1.0):
+ if self.transform and random.random() < p:
+ new = self.transform(image=im, bboxes=labels[:, 1:], class_labels=labels[:, 0]) # transformed
+ im, labels = new['image'], np.array([[c, *b] for c, b in zip(new['class_labels'], new['bboxes'])])
+ return im, labels
+
+
+def augment_hsv(im, hgain=0.5, sgain=0.5, vgain=0.5):
+ # HSV color-space augmentation
+ if hgain or sgain or vgain:
+ r = np.random.uniform(-1, 1, 3) * [hgain, sgain, vgain] + 1 # random gains
+ hue, sat, val = cv2.split(cv2.cvtColor(im, cv2.COLOR_BGR2HSV))
+ dtype = im.dtype # uint8
+
+ x = np.arange(0, 256, dtype=r.dtype)
+ lut_hue = ((x * r[0]) % 180).astype(dtype)
+ lut_sat = np.clip(x * r[1], 0, 255).astype(dtype)
+ lut_val = np.clip(x * r[2], 0, 255).astype(dtype)
+
+ im_hsv = cv2.merge((cv2.LUT(hue, lut_hue), cv2.LUT(sat, lut_sat), cv2.LUT(val, lut_val)))
+ cv2.cvtColor(im_hsv, cv2.COLOR_HSV2BGR, dst=im) # no return needed
+
+
+def hist_equalize(im, clahe=True, bgr=False):
+ # Equalize histogram on BGR image 'im' with im.shape(n,m,3) and range 0-255
+ yuv = cv2.cvtColor(im, cv2.COLOR_BGR2YUV if bgr else cv2.COLOR_RGB2YUV)
+ if clahe:
+ c = cv2.createCLAHE(clipLimit=2.0, tileGridSize=(8, 8))
+ yuv[:, :, 0] = c.apply(yuv[:, :, 0])
+ else:
+ yuv[:, :, 0] = cv2.equalizeHist(yuv[:, :, 0]) # equalize Y channel histogram
+ return cv2.cvtColor(yuv, cv2.COLOR_YUV2BGR if bgr else cv2.COLOR_YUV2RGB) # convert YUV image to RGB
+
+
+def replicate(im, labels):
+ # Replicate labels
+ h, w = im.shape[:2]
+ boxes = labels[:, 1:].astype(int)
+ x1, y1, x2, y2 = boxes.T
+ s = ((x2 - x1) + (y2 - y1)) / 2 # side length (pixels)
+ for i in s.argsort()[:round(s.size * 0.5)]: # smallest indices
+ x1b, y1b, x2b, y2b = boxes[i]
+ bh, bw = y2b - y1b, x2b - x1b
+ yc, xc = int(random.uniform(0, h - bh)), int(random.uniform(0, w - bw)) # offset x, y
+ x1a, y1a, x2a, y2a = [xc, yc, xc + bw, yc + bh]
+ im[y1a:y2a, x1a:x2a] = im[y1b:y2b, x1b:x2b] # im4[ymin:ymax, xmin:xmax]
+ labels = np.append(labels, [[labels[i, 0], x1a, y1a, x2a, y2a]], axis=0)
+
+ return im, labels
+
+
+def letterbox(im, new_shape=(640, 640), color=(114, 114, 114), auto=True, scaleFill=False, scaleup=True, stride=32):
+ # Resize and pad image while meeting stride-multiple constraints
+ shape = im.shape[:2] # current shape [height, width]
+ if isinstance(new_shape, int):
+ new_shape = (new_shape, new_shape)
+
+ # Scale ratio (new / old)
+ r = min(new_shape[0] / shape[0], new_shape[1] / shape[1])
+ if not scaleup: # only scale down, do not scale up (for better val mAP)
+ r = min(r, 1.0)
+
+ # Compute padding
+ ratio = r, r # width, height ratios
+ new_unpad = int(round(shape[1] * r)), int(round(shape[0] * r))
+ dw, dh = new_shape[1] - new_unpad[0], new_shape[0] - new_unpad[1] # wh padding
+ if auto: # minimum rectangle
+ dw, dh = np.mod(dw, stride), np.mod(dh, stride) # wh padding
+ elif scaleFill: # stretch
+ dw, dh = 0.0, 0.0
+ new_unpad = (new_shape[1], new_shape[0])
+ ratio = new_shape[1] / shape[1], new_shape[0] / shape[0] # width, height ratios
+
+ dw /= 2 # divide padding into 2 sides
+ dh /= 2
+
+ if shape[::-1] != new_unpad: # resize
+ im = cv2.resize(im, new_unpad, interpolation=cv2.INTER_LINEAR)
+ top, bottom = int(round(dh - 0.1)), int(round(dh + 0.1))
+ left, right = int(round(dw - 0.1)), int(round(dw + 0.1))
+ im = cv2.copyMakeBorder(im, top, bottom, left, right, cv2.BORDER_CONSTANT, value=color) # add border
+ return im, ratio, (dw, dh)
+
+
+def random_perspective(im, targets=(), segments=(), degrees=10, translate=.1, scale=.1, shear=10, perspective=0.0,
+ border=(0, 0)):
+ # torchvision.transforms.RandomAffine(degrees=(-10, 10), translate=(0.1, 0.1), scale=(0.9, 1.1), shear=(-10, 10))
+ # targets = [cls, xyxy]
+
+ height = im.shape[0] + border[0] * 2 # shape(h,w,c)
+ width = im.shape[1] + border[1] * 2
+
+ # Center
+ C = np.eye(3)
+ C[0, 2] = -im.shape[1] / 2 # x translation (pixels)
+ C[1, 2] = -im.shape[0] / 2 # y translation (pixels)
+
+ # Perspective
+ P = np.eye(3)
+ P[2, 0] = random.uniform(-perspective, perspective) # x perspective (about y)
+ P[2, 1] = random.uniform(-perspective, perspective) # y perspective (about x)
+
+ # Rotation and Scale
+ R = np.eye(3)
+ a = random.uniform(-degrees, degrees)
+ # a += random.choice([-180, -90, 0, 90]) # add 90deg rotations to small rotations
+ s = random.uniform(1 - scale, 1 + scale)
+ # s = 2 ** random.uniform(-scale, scale)
+ R[:2] = cv2.getRotationMatrix2D(angle=a, center=(0, 0), scale=s)
+
+ # Shear
+ S = np.eye(3)
+ S[0, 1] = math.tan(random.uniform(-shear, shear) * math.pi / 180) # x shear (deg)
+ S[1, 0] = math.tan(random.uniform(-shear, shear) * math.pi / 180) # y shear (deg)
+
+ # Translation
+ T = np.eye(3)
+ T[0, 2] = random.uniform(0.5 - translate, 0.5 + translate) * width # x translation (pixels)
+ T[1, 2] = random.uniform(0.5 - translate, 0.5 + translate) * height # y translation (pixels)
+
+ # Combined rotation matrix
+ M = T @ S @ R @ P @ C # order of operations (right to left) is IMPORTANT
+ if (border[0] != 0) or (border[1] != 0) or (M != np.eye(3)).any(): # image changed
+ if perspective:
+ im = cv2.warpPerspective(im, M, dsize=(width, height), borderValue=(114, 114, 114))
+ else: # affine
+ im = cv2.warpAffine(im, M[:2], dsize=(width, height), borderValue=(114, 114, 114))
+
+ # Visualize
+ # import matplotlib.pyplot as plt
+ # ax = plt.subplots(1, 2, figsize=(12, 6))[1].ravel()
+ # ax[0].imshow(im[:, :, ::-1]) # base
+ # ax[1].imshow(im2[:, :, ::-1]) # warped
+
+ # Transform label coordinates
+ n = len(targets)
+ if n:
+ use_segments = any(x.any() for x in segments)
+ new = np.zeros((n, 4))
+ if use_segments: # warp segments
+ segments = resample_segments(segments) # upsample
+ for i, segment in enumerate(segments):
+ xy = np.ones((len(segment), 3))
+ xy[:, :2] = segment
+ xy = xy @ M.T # transform
+ xy = xy[:, :2] / xy[:, 2:3] if perspective else xy[:, :2] # perspective rescale or affine
+
+ # clip
+ new[i] = segment2box(xy, width, height)
+
+ else: # warp boxes
+ xy = np.ones((n * 4, 3))
+ xy[:, :2] = targets[:, [1, 2, 3, 4, 1, 4, 3, 2]].reshape(n * 4, 2) # x1y1, x2y2, x1y2, x2y1
+ xy = xy @ M.T # transform
+ xy = (xy[:, :2] / xy[:, 2:3] if perspective else xy[:, :2]).reshape(n, 8) # perspective rescale or affine
+
+ # create new boxes
+ x = xy[:, [0, 2, 4, 6]]
+ y = xy[:, [1, 3, 5, 7]]
+ new = np.concatenate((x.min(1), y.min(1), x.max(1), y.max(1))).reshape(4, n).T
+
+ # clip
+ new[:, [0, 2]] = new[:, [0, 2]].clip(0, width)
+ new[:, [1, 3]] = new[:, [1, 3]].clip(0, height)
+
+ # filter candidates
+ i = box_candidates(box1=targets[:, 1:5].T * s, box2=new.T, area_thr=0.01 if use_segments else 0.10)
+ targets = targets[i]
+ targets[:, 1:5] = new[i]
+
+ return im, targets
+
+
+def copy_paste(im, labels, segments, p=0.5):
+ # Implement Copy-Paste augmentation https://arxiv.org/abs/2012.07177, labels as nx5 np.array(cls, xyxy)
+ n = len(segments)
+ if p and n:
+ h, w, c = im.shape # height, width, channels
+ im_new = np.zeros(im.shape, np.uint8)
+ for j in random.sample(range(n), k=round(p * n)):
+ l, s = labels[j], segments[j]
+ box = w - l[3], l[2], w - l[1], l[4]
+ ioa = bbox_ioa(box, labels[:, 1:5]) # intersection over area
+ if (ioa < 0.30).all(): # allow 30% obscuration of existing labels
+ labels = np.concatenate((labels, [[l[0], *box]]), 0)
+ segments.append(np.concatenate((w - s[:, 0:1], s[:, 1:2]), 1))
+ cv2.drawContours(im_new, [segments[j].astype(np.int32)], -1, (255, 255, 255), cv2.FILLED)
+
+ result = cv2.bitwise_and(src1=im, src2=im_new)
+ result = cv2.flip(result, 1) # augment segments (flip left-right)
+ i = result > 0 # pixels to replace
+ # i[:, :] = result.max(2).reshape(h, w, 1) # act over ch
+ im[i] = result[i] # cv2.imwrite('debug.jpg', im) # debug
+
+ return im, labels, segments
+
+
+def cutout(im, labels, p=0.5):
+ # Applies image cutout augmentation https://arxiv.org/abs/1708.04552
+ if random.random() < p:
+ h, w = im.shape[:2]
+ scales = [0.5] * 1 + [0.25] * 2 + [0.125] * 4 + [0.0625] * 8 + [0.03125] * 16 # image size fraction
+ for s in scales:
+ mask_h = random.randint(1, int(h * s)) # create random masks
+ mask_w = random.randint(1, int(w * s))
+
+ # box
+ xmin = max(0, random.randint(0, w) - mask_w // 2)
+ ymin = max(0, random.randint(0, h) - mask_h // 2)
+ xmax = min(w, xmin + mask_w)
+ ymax = min(h, ymin + mask_h)
+
+ # apply random color mask
+ im[ymin:ymax, xmin:xmax] = [random.randint(64, 191) for _ in range(3)]
+
+ # return unobscured labels
+ if len(labels) and s > 0.03:
+ box = np.array([xmin, ymin, xmax, ymax], dtype=np.float32)
+ ioa = bbox_ioa(box, labels[:, 1:5]) # intersection over area
+ labels = labels[ioa < 0.60] # remove >60% obscured labels
+
+ return labels
+
+
+def mixup(im, labels, im2, labels2):
+ # Applies MixUp augmentation https://arxiv.org/pdf/1710.09412.pdf
+ r = np.random.beta(32.0, 32.0) # mixup ratio, alpha=beta=32.0
+ im = (im * r + im2 * (1 - r)).astype(np.uint8)
+ labels = np.concatenate((labels, labels2), 0)
+ return im, labels
+
+
+def box_candidates(box1, box2, wh_thr=2, ar_thr=20, area_thr=0.1, eps=1e-16): # box1(4,n), box2(4,n)
+ # Compute candidate boxes: box1 before augment, box2 after augment, wh_thr (pixels), aspect_ratio_thr, area_ratio
+ w1, h1 = box1[2] - box1[0], box1[3] - box1[1]
+ w2, h2 = box2[2] - box2[0], box2[3] - box2[1]
+ ar = np.maximum(w2 / (h2 + eps), h2 / (w2 + eps)) # aspect ratio
+ return (w2 > wh_thr) & (h2 > wh_thr) & (w2 * h2 / (w1 * h1 + eps) > area_thr) & (ar < ar_thr) # candidates
diff --git a/ros2_ws/src/yolov3_ros/utils/autoanchor.py b/ros2_ws/src/yolov3_ros/utils/autoanchor.py
new file mode 100644
index 00000000..0c202c49
--- /dev/null
+++ b/ros2_ws/src/yolov3_ros/utils/autoanchor.py
@@ -0,0 +1,164 @@
+# YOLOv3 🚀 by Ultralytics, GPL-3.0 license
+"""
+Auto-anchor utils
+"""
+
+import random
+
+import numpy as np
+import torch
+import yaml
+from tqdm import tqdm
+
+from utils.general import LOGGER, colorstr, emojis
+
+PREFIX = colorstr('AutoAnchor: ')
+
+
+def check_anchor_order(m):
+ # Check anchor order against stride order for Detect() module m, and correct if necessary
+ a = m.anchors.prod(-1).view(-1) # anchor area
+ da = a[-1] - a[0] # delta a
+ ds = m.stride[-1] - m.stride[0] # delta s
+ if da.sign() != ds.sign(): # same order
+ LOGGER.info(f'{PREFIX}Reversing anchor order')
+ m.anchors[:] = m.anchors.flip(0)
+
+
+def check_anchors(dataset, model, thr=4.0, imgsz=640):
+ # Check anchor fit to data, recompute if necessary
+ m = model.module.model[-1] if hasattr(model, 'module') else model.model[-1] # Detect()
+ shapes = imgsz * dataset.shapes / dataset.shapes.max(1, keepdims=True)
+ scale = np.random.uniform(0.9, 1.1, size=(shapes.shape[0], 1)) # augment scale
+ wh = torch.tensor(np.concatenate([l[:, 3:5] * s for s, l in zip(shapes * scale, dataset.labels)])).float() # wh
+
+ def metric(k): # compute metric
+ r = wh[:, None] / k[None]
+ x = torch.min(r, 1 / r).min(2)[0] # ratio metric
+ best = x.max(1)[0] # best_x
+ aat = (x > 1 / thr).float().sum(1).mean() # anchors above threshold
+ bpr = (best > 1 / thr).float().mean() # best possible recall
+ return bpr, aat
+
+ anchors = m.anchors.clone() * m.stride.to(m.anchors.device).view(-1, 1, 1) # current anchors
+ bpr, aat = metric(anchors.cpu().view(-1, 2))
+ s = f'\n{PREFIX}{aat:.2f} anchors/target, {bpr:.3f} Best Possible Recall (BPR). '
+ if bpr > 0.98: # threshold to recompute
+ LOGGER.info(emojis(f'{s}Current anchors are a good fit to dataset ✅'))
+ else:
+ LOGGER.info(emojis(f'{s}Anchors are a poor fit to dataset ⚠️, attempting to improve...'))
+ na = m.anchors.numel() // 2 # number of anchors
+ try:
+ anchors = kmean_anchors(dataset, n=na, img_size=imgsz, thr=thr, gen=1000, verbose=False)
+ except Exception as e:
+ LOGGER.info(f'{PREFIX}ERROR: {e}')
+ new_bpr = metric(anchors)[0]
+ if new_bpr > bpr: # replace anchors
+ anchors = torch.tensor(anchors, device=m.anchors.device).type_as(m.anchors)
+ m.anchors[:] = anchors.clone().view_as(m.anchors) / m.stride.to(m.anchors.device).view(-1, 1, 1) # loss
+ check_anchor_order(m)
+ LOGGER.info(f'{PREFIX}New anchors saved to model. Update model *.yaml to use these anchors in the future.')
+ else:
+ LOGGER.info(f'{PREFIX}Original anchors better than new anchors. Proceeding with original anchors.')
+
+
+def kmean_anchors(dataset='./data/coco128.yaml', n=9, img_size=640, thr=4.0, gen=1000, verbose=True):
+ """ Creates kmeans-evolved anchors from training dataset
+
+ Arguments:
+ dataset: path to data.yaml, or a loaded dataset
+ n: number of anchors
+ img_size: image size used for training
+ thr: anchor-label wh ratio threshold hyperparameter hyp['anchor_t'] used for training, default=4.0
+ gen: generations to evolve anchors using genetic algorithm
+ verbose: print all results
+
+ Return:
+ k: kmeans evolved anchors
+
+ Usage:
+ from utils.autoanchor import *; _ = kmean_anchors()
+ """
+ from scipy.cluster.vq import kmeans
+
+ thr = 1 / thr
+
+ def metric(k, wh): # compute metrics
+ r = wh[:, None] / k[None]
+ x = torch.min(r, 1 / r).min(2)[0] # ratio metric
+ # x = wh_iou(wh, torch.tensor(k)) # iou metric
+ return x, x.max(1)[0] # x, best_x
+
+ def anchor_fitness(k): # mutation fitness
+ _, best = metric(torch.tensor(k, dtype=torch.float32), wh)
+ return (best * (best > thr).float()).mean() # fitness
+
+ def print_results(k, verbose=True):
+ k = k[np.argsort(k.prod(1))] # sort small to large
+ x, best = metric(k, wh0)
+ bpr, aat = (best > thr).float().mean(), (x > thr).float().mean() * n # best possible recall, anch > thr
+ s = f'{PREFIX}thr={thr:.2f}: {bpr:.4f} best possible recall, {aat:.2f} anchors past thr\n' \
+ f'{PREFIX}n={n}, img_size={img_size}, metric_all={x.mean():.3f}/{best.mean():.3f}-mean/best, ' \
+ f'past_thr={x[x > thr].mean():.3f}-mean: '
+ for i, x in enumerate(k):
+ s += '%i,%i, ' % (round(x[0]), round(x[1]))
+ if verbose:
+ LOGGER.info(s[:-2])
+ return k
+
+ if isinstance(dataset, str): # *.yaml file
+ with open(dataset, errors='ignore') as f:
+ data_dict = yaml.safe_load(f) # model dict
+ from utils.datasets import LoadImagesAndLabels
+ dataset = LoadImagesAndLabels(data_dict['train'], augment=True, rect=True)
+
+ # Get label wh
+ shapes = img_size * dataset.shapes / dataset.shapes.max(1, keepdims=True)
+ wh0 = np.concatenate([l[:, 3:5] * s for s, l in zip(shapes, dataset.labels)]) # wh
+
+ # Filter
+ i = (wh0 < 3.0).any(1).sum()
+ if i:
+ LOGGER.info(f'{PREFIX}WARNING: Extremely small objects found. {i} of {len(wh0)} labels are < 3 pixels in size.')
+ wh = wh0[(wh0 >= 2.0).any(1)] # filter > 2 pixels
+ # wh = wh * (np.random.rand(wh.shape[0], 1) * 0.9 + 0.1) # multiply by random scale 0-1
+
+ # Kmeans calculation
+ LOGGER.info(f'{PREFIX}Running kmeans for {n} anchors on {len(wh)} points...')
+ s = wh.std(0) # sigmas for whitening
+ k, dist = kmeans(wh / s, n, iter=30) # points, mean distance
+ assert len(k) == n, f'{PREFIX}ERROR: scipy.cluster.vq.kmeans requested {n} points but returned only {len(k)}'
+ k *= s
+ wh = torch.tensor(wh, dtype=torch.float32) # filtered
+ wh0 = torch.tensor(wh0, dtype=torch.float32) # unfiltered
+ k = print_results(k, verbose=False)
+
+ # Plot
+ # k, d = [None] * 20, [None] * 20
+ # for i in tqdm(range(1, 21)):
+ # k[i-1], d[i-1] = kmeans(wh / s, i) # points, mean distance
+ # fig, ax = plt.subplots(1, 2, figsize=(14, 7), tight_layout=True)
+ # ax = ax.ravel()
+ # ax[0].plot(np.arange(1, 21), np.array(d) ** 2, marker='.')
+ # fig, ax = plt.subplots(1, 2, figsize=(14, 7)) # plot wh
+ # ax[0].hist(wh[wh[:, 0]<100, 0],400)
+ # ax[1].hist(wh[wh[:, 1]<100, 1],400)
+ # fig.savefig('wh.png', dpi=200)
+
+ # Evolve
+ npr = np.random
+ f, sh, mp, s = anchor_fitness(k), k.shape, 0.9, 0.1 # fitness, generations, mutation prob, sigma
+ pbar = tqdm(range(gen), desc=f'{PREFIX}Evolving anchors with Genetic Algorithm:') # progress bar
+ for _ in pbar:
+ v = np.ones(sh)
+ while (v == 1).all(): # mutate until a change occurs (prevent duplicates)
+ v = ((npr.random(sh) < mp) * random.random() * npr.randn(*sh) * s + 1).clip(0.3, 3.0)
+ kg = (k.copy() * v).clip(min=2.0)
+ fg = anchor_fitness(kg)
+ if fg > f:
+ f, k = fg, kg.copy()
+ pbar.desc = f'{PREFIX}Evolving anchors with Genetic Algorithm: fitness = {f:.4f}'
+ if verbose:
+ print_results(k, verbose)
+
+ return print_results(k)
diff --git a/ros2_ws/src/yolov3_ros/utils/autobatch.py b/ros2_ws/src/yolov3_ros/utils/autobatch.py
new file mode 100644
index 00000000..4fbf32bc
--- /dev/null
+++ b/ros2_ws/src/yolov3_ros/utils/autobatch.py
@@ -0,0 +1,57 @@
+# YOLOv3 🚀 by Ultralytics, GPL-3.0 license
+"""
+Auto-batch utils
+"""
+
+from copy import deepcopy
+
+import numpy as np
+import torch
+from torch.cuda import amp
+
+from utils.general import LOGGER, colorstr
+from utils.torch_utils import profile
+
+
+def check_train_batch_size(model, imgsz=640):
+ # Check training batch size
+ with amp.autocast():
+ return autobatch(deepcopy(model).train(), imgsz) # compute optimal batch size
+
+
+def autobatch(model, imgsz=640, fraction=0.9, batch_size=16):
+ # Automatically estimate best batch size to use `fraction` of available CUDA memory
+ # Usage:
+ # import torch
+ # from utils.autobatch import autobatch
+ # model = torch.hub.load('ultralytics/yolov3', 'yolov3', autoshape=False)
+ # print(autobatch(model))
+
+ prefix = colorstr('AutoBatch: ')
+ LOGGER.info(f'{prefix}Computing optimal batch size for --imgsz {imgsz}')
+ device = next(model.parameters()).device # get model device
+ if device.type == 'cpu':
+ LOGGER.info(f'{prefix}CUDA not detected, using default CPU batch-size {batch_size}')
+ return batch_size
+
+ d = str(device).upper() # 'CUDA:0'
+ properties = torch.cuda.get_device_properties(device) # device properties
+ t = properties.total_memory / 1024 ** 3 # (GiB)
+ r = torch.cuda.memory_reserved(device) / 1024 ** 3 # (GiB)
+ a = torch.cuda.memory_allocated(device) / 1024 ** 3 # (GiB)
+ f = t - (r + a) # free inside reserved
+ LOGGER.info(f'{prefix}{d} ({properties.name}) {t:.2f}G total, {r:.2f}G reserved, {a:.2f}G allocated, {f:.2f}G free')
+
+ batch_sizes = [1, 2, 4, 8, 16]
+ try:
+ img = [torch.zeros(b, 3, imgsz, imgsz) for b in batch_sizes]
+ y = profile(img, model, n=3, device=device)
+ except Exception as e:
+ LOGGER.warning(f'{prefix}{e}')
+
+ y = [x[2] for x in y if x] # memory [2]
+ batch_sizes = batch_sizes[:len(y)]
+ p = np.polyfit(batch_sizes, y, deg=1) # first degree polynomial fit
+ b = int((f * fraction - p[1]) / p[0]) # y intercept (optimal batch size)
+ LOGGER.info(f'{prefix}Using batch-size {b} for {d} {t * fraction:.2f}G/{t:.2f}G ({fraction * 100:.0f}%)')
+ return b
diff --git a/ros2_ws/src/yolov3_ros/utils/aws/__init__.py b/ros2_ws/src/yolov3_ros/utils/aws/__init__.py
new file mode 100644
index 00000000..e69de29b
diff --git a/ros2_ws/src/yolov3_ros/utils/aws/mime.sh b/ros2_ws/src/yolov3_ros/utils/aws/mime.sh
new file mode 100644
index 00000000..c319a83c
--- /dev/null
+++ b/ros2_ws/src/yolov3_ros/utils/aws/mime.sh
@@ -0,0 +1,26 @@
+# AWS EC2 instance startup 'MIME' script https://aws.amazon.com/premiumsupport/knowledge-center/execute-user-data-ec2/
+# This script will run on every instance restart, not only on first start
+# --- DO NOT COPY ABOVE COMMENTS WHEN PASTING INTO USERDATA ---
+
+Content-Type: multipart/mixed; boundary="//"
+MIME-Version: 1.0
+
+--//
+Content-Type: text/cloud-config; charset="us-ascii"
+MIME-Version: 1.0
+Content-Transfer-Encoding: 7bit
+Content-Disposition: attachment; filename="cloud-config.txt"
+
+#cloud-config
+cloud_final_modules:
+- [scripts-user, always]
+
+--//
+Content-Type: text/x-shellscript; charset="us-ascii"
+MIME-Version: 1.0
+Content-Transfer-Encoding: 7bit
+Content-Disposition: attachment; filename="userdata.txt"
+
+#!/bin/bash
+# --- paste contents of userdata.sh here ---
+--//
diff --git a/ros2_ws/src/yolov3_ros/utils/aws/resume.py b/ros2_ws/src/yolov3_ros/utils/aws/resume.py
new file mode 100644
index 00000000..b21731c9
--- /dev/null
+++ b/ros2_ws/src/yolov3_ros/utils/aws/resume.py
@@ -0,0 +1,40 @@
+# Resume all interrupted trainings in yolov5/ dir including DDP trainings
+# Usage: $ python utils/aws/resume.py
+
+import os
+import sys
+from pathlib import Path
+
+import torch
+import yaml
+
+FILE = Path(__file__).resolve()
+ROOT = FILE.parents[2] # YOLOv5 root directory
+if str(ROOT) not in sys.path:
+ sys.path.append(str(ROOT)) # add ROOT to PATH
+
+port = 0 # --master_port
+path = Path('').resolve()
+for last in path.rglob('*/**/last.pt'):
+ ckpt = torch.load(last)
+ if ckpt['optimizer'] is None:
+ continue
+
+ # Load opt.yaml
+ with open(last.parent.parent / 'opt.yaml', errors='ignore') as f:
+ opt = yaml.safe_load(f)
+
+ # Get device count
+ d = opt['device'].split(',') # devices
+ nd = len(d) # number of devices
+ ddp = nd > 1 or (nd == 0 and torch.cuda.device_count() > 1) # distributed data parallel
+
+ if ddp: # multi-GPU
+ port += 1
+ cmd = f'python -m torch.distributed.run --nproc_per_node {nd} --master_port {port} train.py --resume {last}'
+ else: # single-GPU
+ cmd = f'python train.py --resume {last}'
+
+ cmd += ' > /dev/null 2>&1 &' # redirect output to dev/null and run in daemon thread
+ print(cmd)
+ os.system(cmd)
diff --git a/ros2_ws/src/yolov3_ros/utils/aws/userdata.sh b/ros2_ws/src/yolov3_ros/utils/aws/userdata.sh
new file mode 100644
index 00000000..5fc1332a
--- /dev/null
+++ b/ros2_ws/src/yolov3_ros/utils/aws/userdata.sh
@@ -0,0 +1,27 @@
+#!/bin/bash
+# AWS EC2 instance startup script https://docs.aws.amazon.com/AWSEC2/latest/UserGuide/user-data.html
+# This script will run only once on first instance start (for a re-start script see mime.sh)
+# /home/ubuntu (ubuntu) or /home/ec2-user (amazon-linux) is working dir
+# Use >300 GB SSD
+
+cd home/ubuntu
+if [ ! -d yolov5 ]; then
+ echo "Running first-time script." # install dependencies, download COCO, pull Docker
+ git clone https://github.com/ultralytics/yolov5 -b master && sudo chmod -R 777 yolov5
+ cd yolov5
+ bash data/scripts/get_coco.sh && echo "COCO done." &
+ sudo docker pull ultralytics/yolov5:latest && echo "Docker done." &
+ python -m pip install --upgrade pip && pip install -r requirements.txt && python detect.py && echo "Requirements done." &
+ wait && echo "All tasks done." # finish background tasks
+else
+ echo "Running re-start script." # resume interrupted runs
+ i=0
+ list=$(sudo docker ps -qa) # container list i.e. $'one\ntwo\nthree\nfour'
+ while IFS= read -r id; do
+ ((i++))
+ echo "restarting container $i: $id"
+ sudo docker start $id
+ # sudo docker exec -it $id python train.py --resume # single-GPU
+ sudo docker exec -d $id python utils/aws/resume.py # multi-scenario
+ done <<<"$list"
+fi
diff --git a/ros2_ws/src/yolov3_ros/utils/callbacks.py b/ros2_ws/src/yolov3_ros/utils/callbacks.py
new file mode 100644
index 00000000..43e81a7c
--- /dev/null
+++ b/ros2_ws/src/yolov3_ros/utils/callbacks.py
@@ -0,0 +1,76 @@
+# YOLOv3 🚀 by Ultralytics, GPL-3.0 license
+"""
+Callback utils
+"""
+
+
+class Callbacks:
+ """"
+ Handles all registered callbacks for Hooks
+ """
+
+ # Define the available callbacks
+ _callbacks = {
+ 'on_pretrain_routine_start': [],
+ 'on_pretrain_routine_end': [],
+
+ 'on_train_start': [],
+ 'on_train_epoch_start': [],
+ 'on_train_batch_start': [],
+ 'optimizer_step': [],
+ 'on_before_zero_grad': [],
+ 'on_train_batch_end': [],
+ 'on_train_epoch_end': [],
+
+ 'on_val_start': [],
+ 'on_val_batch_start': [],
+ 'on_val_image_end': [],
+ 'on_val_batch_end': [],
+ 'on_val_end': [],
+
+ 'on_fit_epoch_end': [], # fit = train + val
+ 'on_model_save': [],
+ 'on_train_end': [],
+
+ 'teardown': [],
+ }
+
+ def register_action(self, hook, name='', callback=None):
+ """
+ Register a new action to a callback hook
+
+ Args:
+ hook The callback hook name to register the action to
+ name The name of the action for later reference
+ callback The callback to fire
+ """
+ assert hook in self._callbacks, f"hook '{hook}' not found in callbacks {self._callbacks}"
+ assert callable(callback), f"callback '{callback}' is not callable"
+ self._callbacks[hook].append({'name': name, 'callback': callback})
+
+ def get_registered_actions(self, hook=None):
+ """"
+ Returns all the registered actions by callback hook
+
+ Args:
+ hook The name of the hook to check, defaults to all
+ """
+ if hook:
+ return self._callbacks[hook]
+ else:
+ return self._callbacks
+
+ def run(self, hook, *args, **kwargs):
+ """
+ Loop through the registered actions and fire all callbacks
+
+ Args:
+ hook The name of the hook to check, defaults to all
+ args Arguments to receive from
+ kwargs Keyword Arguments to receive from
+ """
+
+ assert hook in self._callbacks, f"hook '{hook}' not found in callbacks {self._callbacks}"
+
+ for logger in self._callbacks[hook]:
+ logger['callback'](*args, **kwargs)
diff --git a/ros2_ws/src/yolov3_ros/utils/dataloaders.py b/ros2_ws/src/yolov3_ros/utils/dataloaders.py
new file mode 100644
index 00000000..2a038d1a
--- /dev/null
+++ b/ros2_ws/src/yolov3_ros/utils/dataloaders.py
@@ -0,0 +1,1221 @@
+# YOLOv3 🚀 by Ultralytics, GPL-3.0 license
+"""
+Dataloaders and dataset utils
+"""
+
+import contextlib
+import glob
+import hashlib
+import json
+import math
+import os
+import random
+import shutil
+import time
+from itertools import repeat
+from multiprocessing.pool import Pool, ThreadPool
+from pathlib import Path
+from threading import Thread
+from urllib.parse import urlparse
+
+import numpy as np
+import psutil
+import torch
+import torch.nn.functional as F
+import torchvision
+import yaml
+from PIL import ExifTags, Image, ImageOps
+from torch.utils.data import DataLoader, Dataset, dataloader, distributed
+from tqdm import tqdm
+
+from utils.augmentations import (Albumentations, augment_hsv, classify_albumentations, classify_transforms, copy_paste,
+ letterbox, mixup, random_perspective)
+from utils.general import (DATASETS_DIR, LOGGER, NUM_THREADS, TQDM_BAR_FORMAT, check_dataset, check_requirements,
+ check_yaml, clean_str, cv2, is_colab, is_kaggle, segments2boxes, unzip_file, xyn2xy,
+ xywh2xyxy, xywhn2xyxy, xyxy2xywhn)
+from utils.torch_utils import torch_distributed_zero_first
+
+# Parameters
+HELP_URL = 'See https://github.com/ultralytics/yolov5/wiki/Train-Custom-Data'
+IMG_FORMATS = 'bmp', 'dng', 'jpeg', 'jpg', 'mpo', 'png', 'tif', 'tiff', 'webp', 'pfm' # include image suffixes
+VID_FORMATS = 'asf', 'avi', 'gif', 'm4v', 'mkv', 'mov', 'mp4', 'mpeg', 'mpg', 'ts', 'wmv' # include video suffixes
+LOCAL_RANK = int(os.getenv('LOCAL_RANK', -1)) # https://pytorch.org/docs/stable/elastic/run.html
+RANK = int(os.getenv('RANK', -1))
+PIN_MEMORY = str(os.getenv('PIN_MEMORY', True)).lower() == 'true' # global pin_memory for dataloaders
+
+# Get orientation exif tag
+for orientation in ExifTags.TAGS.keys():
+ if ExifTags.TAGS[orientation] == 'Orientation':
+ break
+
+
+def get_hash(paths):
+ # Returns a single hash value of a list of paths (files or dirs)
+ size = sum(os.path.getsize(p) for p in paths if os.path.exists(p)) # sizes
+ h = hashlib.sha256(str(size).encode()) # hash sizes
+ h.update(''.join(paths).encode()) # hash paths
+ return h.hexdigest() # return hash
+
+
+def exif_size(img):
+ # Returns exif-corrected PIL size
+ s = img.size # (width, height)
+ with contextlib.suppress(Exception):
+ rotation = dict(img._getexif().items())[orientation]
+ if rotation in [6, 8]: # rotation 270 or 90
+ s = (s[1], s[0])
+ return s
+
+
+def exif_transpose(image):
+ """
+ Transpose a PIL image accordingly if it has an EXIF Orientation tag.
+ Inplace version of https://github.com/python-pillow/Pillow/blob/master/src/PIL/ImageOps.py exif_transpose()
+
+ :param image: The image to transpose.
+ :return: An image.
+ """
+ exif = image.getexif()
+ orientation = exif.get(0x0112, 1) # default 1
+ if orientation > 1:
+ method = {
+ 2: Image.FLIP_LEFT_RIGHT,
+ 3: Image.ROTATE_180,
+ 4: Image.FLIP_TOP_BOTTOM,
+ 5: Image.TRANSPOSE,
+ 6: Image.ROTATE_270,
+ 7: Image.TRANSVERSE,
+ 8: Image.ROTATE_90}.get(orientation)
+ if method is not None:
+ image = image.transpose(method)
+ del exif[0x0112]
+ image.info['exif'] = exif.tobytes()
+ return image
+
+
+def seed_worker(worker_id):
+ # Set dataloader worker seed https://pytorch.org/docs/stable/notes/randomness.html#dataloader
+ worker_seed = torch.initial_seed() % 2 ** 32
+ np.random.seed(worker_seed)
+ random.seed(worker_seed)
+
+
+def create_dataloader(path,
+ imgsz,
+ batch_size,
+ stride,
+ single_cls=False,
+ hyp=None,
+ augment=False,
+ cache=False,
+ pad=0.0,
+ rect=False,
+ rank=-1,
+ workers=8,
+ image_weights=False,
+ quad=False,
+ prefix='',
+ shuffle=False,
+ seed=0):
+ if rect and shuffle:
+ LOGGER.warning('WARNING ⚠️ --rect is incompatible with DataLoader shuffle, setting shuffle=False')
+ shuffle = False
+ with torch_distributed_zero_first(rank): # init dataset *.cache only once if DDP
+ dataset = LoadImagesAndLabels(
+ path,
+ imgsz,
+ batch_size,
+ augment=augment, # augmentation
+ hyp=hyp, # hyperparameters
+ rect=rect, # rectangular batches
+ cache_images=cache,
+ single_cls=single_cls,
+ stride=int(stride),
+ pad=pad,
+ image_weights=image_weights,
+ prefix=prefix)
+
+ batch_size = min(batch_size, len(dataset))
+ nd = torch.cuda.device_count() # number of CUDA devices
+ nw = min([os.cpu_count() // max(nd, 1), batch_size if batch_size > 1 else 0, workers]) # number of workers
+ sampler = None if rank == -1 else distributed.DistributedSampler(dataset, shuffle=shuffle)
+ loader = DataLoader if image_weights else InfiniteDataLoader # only DataLoader allows for attribute updates
+ generator = torch.Generator()
+ generator.manual_seed(6148914691236517205 + seed + RANK)
+ return loader(dataset,
+ batch_size=batch_size,
+ shuffle=shuffle and sampler is None,
+ num_workers=nw,
+ sampler=sampler,
+ pin_memory=PIN_MEMORY,
+ collate_fn=LoadImagesAndLabels.collate_fn4 if quad else LoadImagesAndLabels.collate_fn,
+ worker_init_fn=seed_worker,
+ generator=generator), dataset
+
+
+class InfiniteDataLoader(dataloader.DataLoader):
+ """ Dataloader that reuses workers
+
+ Uses same syntax as vanilla DataLoader
+ """
+
+ def __init__(self, *args, **kwargs):
+ super().__init__(*args, **kwargs)
+ object.__setattr__(self, 'batch_sampler', _RepeatSampler(self.batch_sampler))
+ self.iterator = super().__iter__()
+
+ def __len__(self):
+ return len(self.batch_sampler.sampler)
+
+ def __iter__(self):
+ for _ in range(len(self)):
+ yield next(self.iterator)
+
+
+class _RepeatSampler:
+ """ Sampler that repeats forever
+
+ Args:
+ sampler (Sampler)
+ """
+
+ def __init__(self, sampler):
+ self.sampler = sampler
+
+ def __iter__(self):
+ while True:
+ yield from iter(self.sampler)
+
+
+class LoadScreenshots:
+ # YOLOv5 screenshot dataloader, i.e. `python detect.py --source "screen 0 100 100 512 256"`
+ def __init__(self, source, img_size=640, stride=32, auto=True, transforms=None):
+ # source = [screen_number left top width height] (pixels)
+ check_requirements('mss')
+ import mss
+
+ source, *params = source.split()
+ self.screen, left, top, width, height = 0, None, None, None, None # default to full screen 0
+ if len(params) == 1:
+ self.screen = int(params[0])
+ elif len(params) == 4:
+ left, top, width, height = (int(x) for x in params)
+ elif len(params) == 5:
+ self.screen, left, top, width, height = (int(x) for x in params)
+ self.img_size = img_size
+ self.stride = stride
+ self.transforms = transforms
+ self.auto = auto
+ self.mode = 'stream'
+ self.frame = 0
+ self.sct = mss.mss()
+
+ # Parse monitor shape
+ monitor = self.sct.monitors[self.screen]
+ self.top = monitor['top'] if top is None else (monitor['top'] + top)
+ self.left = monitor['left'] if left is None else (monitor['left'] + left)
+ self.width = width or monitor['width']
+ self.height = height or monitor['height']
+ self.monitor = {'left': self.left, 'top': self.top, 'width': self.width, 'height': self.height}
+
+ def __iter__(self):
+ return self
+
+ def __next__(self):
+ # mss screen capture: get raw pixels from the screen as np array
+ im0 = np.array(self.sct.grab(self.monitor))[:, :, :3] # [:, :, :3] BGRA to BGR
+ s = f'screen {self.screen} (LTWH): {self.left},{self.top},{self.width},{self.height}: '
+
+ if self.transforms:
+ im = self.transforms(im0) # transforms
+ else:
+ im = letterbox(im0, self.img_size, stride=self.stride, auto=self.auto)[0] # padded resize
+ im = im.transpose((2, 0, 1))[::-1] # HWC to CHW, BGR to RGB
+ im = np.ascontiguousarray(im) # contiguous
+ self.frame += 1
+ return str(self.screen), im, im0, None, s # screen, img, original img, im0s, s
+
+
+class LoadImages:
+ # YOLOv5 image/video dataloader, i.e. `python detect.py --source image.jpg/vid.mp4`
+ def __init__(self, path, img_size=640, stride=32, auto=True, transforms=None, vid_stride=1):
+ if isinstance(path, str) and Path(path).suffix == '.txt': # *.txt file with img/vid/dir on each line
+ path = Path(path).read_text().rsplit()
+ files = []
+ for p in sorted(path) if isinstance(path, (list, tuple)) else [path]:
+ p = str(Path(p).resolve())
+ if '*' in p:
+ files.extend(sorted(glob.glob(p, recursive=True))) # glob
+ elif os.path.isdir(p):
+ files.extend(sorted(glob.glob(os.path.join(p, '*.*')))) # dir
+ elif os.path.isfile(p):
+ files.append(p) # files
+ else:
+ raise FileNotFoundError(f'{p} does not exist')
+
+ images = [x for x in files if x.split('.')[-1].lower() in IMG_FORMATS]
+ videos = [x for x in files if x.split('.')[-1].lower() in VID_FORMATS]
+ ni, nv = len(images), len(videos)
+
+ self.img_size = img_size
+ self.stride = stride
+ self.files = images + videos
+ self.nf = ni + nv # number of files
+ self.video_flag = [False] * ni + [True] * nv
+ self.mode = 'image'
+ self.auto = auto
+ self.transforms = transforms # optional
+ self.vid_stride = vid_stride # video frame-rate stride
+ if any(videos):
+ self._new_video(videos[0]) # new video
+ else:
+ self.cap = None
+ assert self.nf > 0, f'No images or videos found in {p}. ' \
+ f'Supported formats are:\nimages: {IMG_FORMATS}\nvideos: {VID_FORMATS}'
+
+ def __iter__(self):
+ self.count = 0
+ return self
+
+ def __next__(self):
+ if self.count == self.nf:
+ raise StopIteration
+ path = self.files[self.count]
+
+ if self.video_flag[self.count]:
+ # Read video
+ self.mode = 'video'
+ for _ in range(self.vid_stride):
+ self.cap.grab()
+ ret_val, im0 = self.cap.retrieve()
+ while not ret_val:
+ self.count += 1
+ self.cap.release()
+ if self.count == self.nf: # last video
+ raise StopIteration
+ path = self.files[self.count]
+ self._new_video(path)
+ ret_val, im0 = self.cap.read()
+
+ self.frame += 1
+ # im0 = self._cv2_rotate(im0) # for use if cv2 autorotation is False
+ s = f'video {self.count + 1}/{self.nf} ({self.frame}/{self.frames}) {path}: '
+
+ else:
+ # Read image
+ self.count += 1
+ im0 = cv2.imread(path) # BGR
+ assert im0 is not None, f'Image Not Found {path}'
+ s = f'image {self.count}/{self.nf} {path}: '
+
+ if self.transforms:
+ im = self.transforms(im0) # transforms
+ else:
+ im = letterbox(im0, self.img_size, stride=self.stride, auto=self.auto)[0] # padded resize
+ im = im.transpose((2, 0, 1))[::-1] # HWC to CHW, BGR to RGB
+ im = np.ascontiguousarray(im) # contiguous
+
+ return path, im, im0, self.cap, s
+
+ def _new_video(self, path):
+ # Create a new video capture object
+ self.frame = 0
+ self.cap = cv2.VideoCapture(path)
+ self.frames = int(self.cap.get(cv2.CAP_PROP_FRAME_COUNT) / self.vid_stride)
+ self.orientation = int(self.cap.get(cv2.CAP_PROP_ORIENTATION_META)) # rotation degrees
+ # self.cap.set(cv2.CAP_PROP_ORIENTATION_AUTO, 0) # disable https://github.com/ultralytics/yolov5/issues/8493
+
+ def _cv2_rotate(self, im):
+ # Rotate a cv2 video manually
+ if self.orientation == 0:
+ return cv2.rotate(im, cv2.ROTATE_90_CLOCKWISE)
+ elif self.orientation == 180:
+ return cv2.rotate(im, cv2.ROTATE_90_COUNTERCLOCKWISE)
+ elif self.orientation == 90:
+ return cv2.rotate(im, cv2.ROTATE_180)
+ return im
+
+ def __len__(self):
+ return self.nf # number of files
+
+
+class LoadStreams:
+ # YOLOv5 streamloader, i.e. `python detect.py --source 'rtsp://example.com/media.mp4' # RTSP, RTMP, HTTP streams`
+ def __init__(self, sources='file.streams', img_size=640, stride=32, auto=True, transforms=None, vid_stride=1):
+ torch.backends.cudnn.benchmark = True # faster for fixed-size inference
+ self.mode = 'stream'
+ self.img_size = img_size
+ self.stride = stride
+ self.vid_stride = vid_stride # video frame-rate stride
+ sources = Path(sources).read_text().rsplit() if os.path.isfile(sources) else [sources]
+ n = len(sources)
+ self.sources = [clean_str(x) for x in sources] # clean source names for later
+ self.imgs, self.fps, self.frames, self.threads = [None] * n, [0] * n, [0] * n, [None] * n
+ for i, s in enumerate(sources): # index, source
+ # Start thread to read frames from video stream
+ st = f'{i + 1}/{n}: {s}... '
+ if urlparse(s).hostname in ('www.youtube.com', 'youtube.com', 'youtu.be'): # if source is YouTube video
+ # YouTube format i.e. 'https://www.youtube.com/watch?v=Zgi9g1ksQHc' or 'https://youtu.be/Zgi9g1ksQHc'
+ check_requirements(('pafy', 'youtube_dl==2020.12.2'))
+ import pafy
+ s = pafy.new(s).getbest(preftype='mp4').url # YouTube URL
+ s = eval(s) if s.isnumeric() else s # i.e. s = '0' local webcam
+ if s == 0:
+ assert not is_colab(), '--source 0 webcam unsupported on Colab. Rerun command in a local environment.'
+ assert not is_kaggle(), '--source 0 webcam unsupported on Kaggle. Rerun command in a local environment.'
+ cap = cv2.VideoCapture(s)
+ assert cap.isOpened(), f'{st}Failed to open {s}'
+ w = int(cap.get(cv2.CAP_PROP_FRAME_WIDTH))
+ h = int(cap.get(cv2.CAP_PROP_FRAME_HEIGHT))
+ fps = cap.get(cv2.CAP_PROP_FPS) # warning: may return 0 or nan
+ self.frames[i] = max(int(cap.get(cv2.CAP_PROP_FRAME_COUNT)), 0) or float('inf') # infinite stream fallback
+ self.fps[i] = max((fps if math.isfinite(fps) else 0) % 100, 0) or 30 # 30 FPS fallback
+
+ _, self.imgs[i] = cap.read() # guarantee first frame
+ self.threads[i] = Thread(target=self.update, args=([i, cap, s]), daemon=True)
+ LOGGER.info(f'{st} Success ({self.frames[i]} frames {w}x{h} at {self.fps[i]:.2f} FPS)')
+ self.threads[i].start()
+ LOGGER.info('') # newline
+
+ # check for common shapes
+ s = np.stack([letterbox(x, img_size, stride=stride, auto=auto)[0].shape for x in self.imgs])
+ self.rect = np.unique(s, axis=0).shape[0] == 1 # rect inference if all shapes equal
+ self.auto = auto and self.rect
+ self.transforms = transforms # optional
+ if not self.rect:
+ LOGGER.warning('WARNING ⚠️ Stream shapes differ. For optimal performance supply similarly-shaped streams.')
+
+ def update(self, i, cap, stream):
+ # Read stream `i` frames in daemon thread
+ n, f = 0, self.frames[i] # frame number, frame array
+ while cap.isOpened() and n < f:
+ n += 1
+ cap.grab() # .read() = .grab() followed by .retrieve()
+ if n % self.vid_stride == 0:
+ success, im = cap.retrieve()
+ if success:
+ self.imgs[i] = im
+ else:
+ LOGGER.warning('WARNING ⚠️ Video stream unresponsive, please check your IP camera connection.')
+ self.imgs[i] = np.zeros_like(self.imgs[i])
+ cap.open(stream) # re-open stream if signal was lost
+ time.sleep(0.0) # wait time
+
+ def __iter__(self):
+ self.count = -1
+ return self
+
+ def __next__(self):
+ self.count += 1
+ if not all(x.is_alive() for x in self.threads) or cv2.waitKey(1) == ord('q'): # q to quit
+ cv2.destroyAllWindows()
+ raise StopIteration
+
+ im0 = self.imgs.copy()
+ if self.transforms:
+ im = np.stack([self.transforms(x) for x in im0]) # transforms
+ else:
+ im = np.stack([letterbox(x, self.img_size, stride=self.stride, auto=self.auto)[0] for x in im0]) # resize
+ im = im[..., ::-1].transpose((0, 3, 1, 2)) # BGR to RGB, BHWC to BCHW
+ im = np.ascontiguousarray(im) # contiguous
+
+ return self.sources, im, im0, None, ''
+
+ def __len__(self):
+ return len(self.sources) # 1E12 frames = 32 streams at 30 FPS for 30 years
+
+
+def img2label_paths(img_paths):
+ # Define label paths as a function of image paths
+ sa, sb = f'{os.sep}images{os.sep}', f'{os.sep}labels{os.sep}' # /images/, /labels/ substrings
+ return [sb.join(x.rsplit(sa, 1)).rsplit('.', 1)[0] + '.txt' for x in img_paths]
+
+
+class LoadImagesAndLabels(Dataset):
+ # YOLOv5 train_loader/val_loader, loads images and labels for training and validation
+ cache_version = 0.6 # dataset labels *.cache version
+ rand_interp_methods = [cv2.INTER_NEAREST, cv2.INTER_LINEAR, cv2.INTER_CUBIC, cv2.INTER_AREA, cv2.INTER_LANCZOS4]
+
+ def __init__(self,
+ path,
+ img_size=640,
+ batch_size=16,
+ augment=False,
+ hyp=None,
+ rect=False,
+ image_weights=False,
+ cache_images=False,
+ single_cls=False,
+ stride=32,
+ pad=0.0,
+ min_items=0,
+ prefix=''):
+ self.img_size = img_size
+ self.augment = augment
+ self.hyp = hyp
+ self.image_weights = image_weights
+ self.rect = False if image_weights else rect
+ self.mosaic = self.augment and not self.rect # load 4 images at a time into a mosaic (only during training)
+ self.mosaic_border = [-img_size // 2, -img_size // 2]
+ self.stride = stride
+ self.path = path
+ self.albumentations = Albumentations(size=img_size) if augment else None
+
+ try:
+ f = [] # image files
+ for p in path if isinstance(path, list) else [path]:
+ p = Path(p) # os-agnostic
+ if p.is_dir(): # dir
+ f += glob.glob(str(p / '**' / '*.*'), recursive=True)
+ # f = list(p.rglob('*.*')) # pathlib
+ elif p.is_file(): # file
+ with open(p) as t:
+ t = t.read().strip().splitlines()
+ parent = str(p.parent) + os.sep
+ f += [x.replace('./', parent, 1) if x.startswith('./') else x for x in t] # to global path
+ # f += [p.parent / x.lstrip(os.sep) for x in t] # to global path (pathlib)
+ else:
+ raise FileNotFoundError(f'{prefix}{p} does not exist')
+ self.im_files = sorted(x.replace('/', os.sep) for x in f if x.split('.')[-1].lower() in IMG_FORMATS)
+ # self.img_files = sorted([x for x in f if x.suffix[1:].lower() in IMG_FORMATS]) # pathlib
+ assert self.im_files, f'{prefix}No images found'
+ except Exception as e:
+ raise Exception(f'{prefix}Error loading data from {path}: {e}\n{HELP_URL}') from e
+
+ # Check cache
+ self.label_files = img2label_paths(self.im_files) # labels
+ cache_path = (p if p.is_file() else Path(self.label_files[0]).parent).with_suffix('.cache')
+ try:
+ cache, exists = np.load(cache_path, allow_pickle=True).item(), True # load dict
+ assert cache['version'] == self.cache_version # matches current version
+ assert cache['hash'] == get_hash(self.label_files + self.im_files) # identical hash
+ except Exception:
+ cache, exists = self.cache_labels(cache_path, prefix), False # run cache ops
+
+ # Display cache
+ nf, nm, ne, nc, n = cache.pop('results') # found, missing, empty, corrupt, total
+ if exists and LOCAL_RANK in {-1, 0}:
+ d = f'Scanning {cache_path}... {nf} images, {nm + ne} backgrounds, {nc} corrupt'
+ tqdm(None, desc=prefix + d, total=n, initial=n, bar_format=TQDM_BAR_FORMAT) # display cache results
+ if cache['msgs']:
+ LOGGER.info('\n'.join(cache['msgs'])) # display warnings
+ assert nf > 0 or not augment, f'{prefix}No labels found in {cache_path}, can not start training. {HELP_URL}'
+
+ # Read cache
+ [cache.pop(k) for k in ('hash', 'version', 'msgs')] # remove items
+ labels, shapes, self.segments = zip(*cache.values())
+ nl = len(np.concatenate(labels, 0)) # number of labels
+ assert nl > 0 or not augment, f'{prefix}All labels empty in {cache_path}, can not start training. {HELP_URL}'
+ self.labels = list(labels)
+ self.shapes = np.array(shapes)
+ self.im_files = list(cache.keys()) # update
+ self.label_files = img2label_paths(cache.keys()) # update
+
+ # Filter images
+ if min_items:
+ include = np.array([len(x) >= min_items for x in self.labels]).nonzero()[0].astype(int)
+ LOGGER.info(f'{prefix}{n - len(include)}/{n} images filtered from dataset')
+ self.im_files = [self.im_files[i] for i in include]
+ self.label_files = [self.label_files[i] for i in include]
+ self.labels = [self.labels[i] for i in include]
+ self.segments = [self.segments[i] for i in include]
+ self.shapes = self.shapes[include] # wh
+
+ # Create indices
+ n = len(self.shapes) # number of images
+ bi = np.floor(np.arange(n) / batch_size).astype(int) # batch index
+ nb = bi[-1] + 1 # number of batches
+ self.batch = bi # batch index of image
+ self.n = n
+ self.indices = range(n)
+
+ # Update labels
+ include_class = [] # filter labels to include only these classes (optional)
+ include_class_array = np.array(include_class).reshape(1, -1)
+ for i, (label, segment) in enumerate(zip(self.labels, self.segments)):
+ if include_class:
+ j = (label[:, 0:1] == include_class_array).any(1)
+ self.labels[i] = label[j]
+ if segment:
+ self.segments[i] = segment[j]
+ if single_cls: # single-class training, merge all classes into 0
+ self.labels[i][:, 0] = 0
+
+ # Rectangular Training
+ if self.rect:
+ # Sort by aspect ratio
+ s = self.shapes # wh
+ ar = s[:, 1] / s[:, 0] # aspect ratio
+ irect = ar.argsort()
+ self.im_files = [self.im_files[i] for i in irect]
+ self.label_files = [self.label_files[i] for i in irect]
+ self.labels = [self.labels[i] for i in irect]
+ self.segments = [self.segments[i] for i in irect]
+ self.shapes = s[irect] # wh
+ ar = ar[irect]
+
+ # Set training image shapes
+ shapes = [[1, 1]] * nb
+ for i in range(nb):
+ ari = ar[bi == i]
+ mini, maxi = ari.min(), ari.max()
+ if maxi < 1:
+ shapes[i] = [maxi, 1]
+ elif mini > 1:
+ shapes[i] = [1, 1 / mini]
+
+ self.batch_shapes = np.ceil(np.array(shapes) * img_size / stride + pad).astype(int) * stride
+
+ # Cache images into RAM/disk for faster training
+ if cache_images == 'ram' and not self.check_cache_ram(prefix=prefix):
+ cache_images = False
+ self.ims = [None] * n
+ self.npy_files = [Path(f).with_suffix('.npy') for f in self.im_files]
+ if cache_images:
+ b, gb = 0, 1 << 30 # bytes of cached images, bytes per gigabytes
+ self.im_hw0, self.im_hw = [None] * n, [None] * n
+ fcn = self.cache_images_to_disk if cache_images == 'disk' else self.load_image
+ results = ThreadPool(NUM_THREADS).imap(fcn, range(n))
+ pbar = tqdm(enumerate(results), total=n, bar_format=TQDM_BAR_FORMAT, disable=LOCAL_RANK > 0)
+ for i, x in pbar:
+ if cache_images == 'disk':
+ b += self.npy_files[i].stat().st_size
+ else: # 'ram'
+ self.ims[i], self.im_hw0[i], self.im_hw[i] = x # im, hw_orig, hw_resized = load_image(self, i)
+ b += self.ims[i].nbytes
+ pbar.desc = f'{prefix}Caching images ({b / gb:.1f}GB {cache_images})'
+ pbar.close()
+
+ def check_cache_ram(self, safety_margin=0.1, prefix=''):
+ # Check image caching requirements vs available memory
+ b, gb = 0, 1 << 30 # bytes of cached images, bytes per gigabytes
+ n = min(self.n, 30) # extrapolate from 30 random images
+ for _ in range(n):
+ im = cv2.imread(random.choice(self.im_files)) # sample image
+ ratio = self.img_size / max(im.shape[0], im.shape[1]) # max(h, w) # ratio
+ b += im.nbytes * ratio ** 2
+ mem_required = b * self.n / n # GB required to cache dataset into RAM
+ mem = psutil.virtual_memory()
+ cache = mem_required * (1 + safety_margin) < mem.available # to cache or not to cache, that is the question
+ if not cache:
+ LOGGER.info(f'{prefix}{mem_required / gb:.1f}GB RAM required, '
+ f'{mem.available / gb:.1f}/{mem.total / gb:.1f}GB available, '
+ f"{'caching images ✅' if cache else 'not caching images ⚠️'}")
+ return cache
+
+ def cache_labels(self, path=Path('./labels.cache'), prefix=''):
+ # Cache dataset labels, check images and read shapes
+ x = {} # dict
+ nm, nf, ne, nc, msgs = 0, 0, 0, 0, [] # number missing, found, empty, corrupt, messages
+ desc = f'{prefix}Scanning {path.parent / path.stem}...'
+ with Pool(NUM_THREADS) as pool:
+ pbar = tqdm(pool.imap(verify_image_label, zip(self.im_files, self.label_files, repeat(prefix))),
+ desc=desc,
+ total=len(self.im_files),
+ bar_format=TQDM_BAR_FORMAT)
+ for im_file, lb, shape, segments, nm_f, nf_f, ne_f, nc_f, msg in pbar:
+ nm += nm_f
+ nf += nf_f
+ ne += ne_f
+ nc += nc_f
+ if im_file:
+ x[im_file] = [lb, shape, segments]
+ if msg:
+ msgs.append(msg)
+ pbar.desc = f'{desc} {nf} images, {nm + ne} backgrounds, {nc} corrupt'
+
+ pbar.close()
+ if msgs:
+ LOGGER.info('\n'.join(msgs))
+ if nf == 0:
+ LOGGER.warning(f'{prefix}WARNING ⚠️ No labels found in {path}. {HELP_URL}')
+ x['hash'] = get_hash(self.label_files + self.im_files)
+ x['results'] = nf, nm, ne, nc, len(self.im_files)
+ x['msgs'] = msgs # warnings
+ x['version'] = self.cache_version # cache version
+ try:
+ np.save(path, x) # save cache for next time
+ path.with_suffix('.cache.npy').rename(path) # remove .npy suffix
+ LOGGER.info(f'{prefix}New cache created: {path}')
+ except Exception as e:
+ LOGGER.warning(f'{prefix}WARNING ⚠️ Cache directory {path.parent} is not writeable: {e}') # not writeable
+ return x
+
+ def __len__(self):
+ return len(self.im_files)
+
+ # def __iter__(self):
+ # self.count = -1
+ # print('ran dataset iter')
+ # #self.shuffled_vector = np.random.permutation(self.nF) if self.augment else np.arange(self.nF)
+ # return self
+
+ def __getitem__(self, index):
+ index = self.indices[index] # linear, shuffled, or image_weights
+
+ hyp = self.hyp
+ mosaic = self.mosaic and random.random() < hyp['mosaic']
+ if mosaic:
+ # Load mosaic
+ img, labels = self.load_mosaic(index)
+ shapes = None
+
+ # MixUp augmentation
+ if random.random() < hyp['mixup']:
+ img, labels = mixup(img, labels, *self.load_mosaic(random.randint(0, self.n - 1)))
+
+ else:
+ # Load image
+ img, (h0, w0), (h, w) = self.load_image(index)
+
+ # Letterbox
+ shape = self.batch_shapes[self.batch[index]] if self.rect else self.img_size # final letterboxed shape
+ img, ratio, pad = letterbox(img, shape, auto=False, scaleup=self.augment)
+ shapes = (h0, w0), ((h / h0, w / w0), pad) # for COCO mAP rescaling
+
+ labels = self.labels[index].copy()
+ if labels.size: # normalized xywh to pixel xyxy format
+ labels[:, 1:] = xywhn2xyxy(labels[:, 1:], ratio[0] * w, ratio[1] * h, padw=pad[0], padh=pad[1])
+
+ if self.augment:
+ img, labels = random_perspective(img,
+ labels,
+ degrees=hyp['degrees'],
+ translate=hyp['translate'],
+ scale=hyp['scale'],
+ shear=hyp['shear'],
+ perspective=hyp['perspective'])
+
+ nl = len(labels) # number of labels
+ if nl:
+ labels[:, 1:5] = xyxy2xywhn(labels[:, 1:5], w=img.shape[1], h=img.shape[0], clip=True, eps=1E-3)
+
+ if self.augment:
+ # Albumentations
+ img, labels = self.albumentations(img, labels)
+ nl = len(labels) # update after albumentations
+
+ # HSV color-space
+ augment_hsv(img, hgain=hyp['hsv_h'], sgain=hyp['hsv_s'], vgain=hyp['hsv_v'])
+
+ # Flip up-down
+ if random.random() < hyp['flipud']:
+ img = np.flipud(img)
+ if nl:
+ labels[:, 2] = 1 - labels[:, 2]
+
+ # Flip left-right
+ if random.random() < hyp['fliplr']:
+ img = np.fliplr(img)
+ if nl:
+ labels[:, 1] = 1 - labels[:, 1]
+
+ # Cutouts
+ # labels = cutout(img, labels, p=0.5)
+ # nl = len(labels) # update after cutout
+
+ labels_out = torch.zeros((nl, 6))
+ if nl:
+ labels_out[:, 1:] = torch.from_numpy(labels)
+
+ # Convert
+ img = img.transpose((2, 0, 1))[::-1] # HWC to CHW, BGR to RGB
+ img = np.ascontiguousarray(img)
+
+ return torch.from_numpy(img), labels_out, self.im_files[index], shapes
+
+ def load_image(self, i):
+ # Loads 1 image from dataset index 'i', returns (im, original hw, resized hw)
+ im, f, fn = self.ims[i], self.im_files[i], self.npy_files[i],
+ if im is None: # not cached in RAM
+ if fn.exists(): # load npy
+ im = np.load(fn)
+ else: # read image
+ im = cv2.imread(f) # BGR
+ assert im is not None, f'Image Not Found {f}'
+ h0, w0 = im.shape[:2] # orig hw
+ r = self.img_size / max(h0, w0) # ratio
+ if r != 1: # if sizes are not equal
+ interp = cv2.INTER_LINEAR if (self.augment or r > 1) else cv2.INTER_AREA
+ im = cv2.resize(im, (math.ceil(w0 * r), math.ceil(h0 * r)), interpolation=interp)
+ return im, (h0, w0), im.shape[:2] # im, hw_original, hw_resized
+ return self.ims[i], self.im_hw0[i], self.im_hw[i] # im, hw_original, hw_resized
+
+ def cache_images_to_disk(self, i):
+ # Saves an image as an *.npy file for faster loading
+ f = self.npy_files[i]
+ if not f.exists():
+ np.save(f.as_posix(), cv2.imread(self.im_files[i]))
+
+ def load_mosaic(self, index):
+ # YOLOv5 4-mosaic loader. Loads 1 image + 3 random images into a 4-image mosaic
+ labels4, segments4 = [], []
+ s = self.img_size
+ yc, xc = (int(random.uniform(-x, 2 * s + x)) for x in self.mosaic_border) # mosaic center x, y
+ indices = [index] + random.choices(self.indices, k=3) # 3 additional image indices
+ random.shuffle(indices)
+ for i, index in enumerate(indices):
+ # Load image
+ img, _, (h, w) = self.load_image(index)
+
+ # place img in img4
+ if i == 0: # top left
+ img4 = np.full((s * 2, s * 2, img.shape[2]), 114, dtype=np.uint8) # base image with 4 tiles
+ x1a, y1a, x2a, y2a = max(xc - w, 0), max(yc - h, 0), xc, yc # xmin, ymin, xmax, ymax (large image)
+ x1b, y1b, x2b, y2b = w - (x2a - x1a), h - (y2a - y1a), w, h # xmin, ymin, xmax, ymax (small image)
+ elif i == 1: # top right
+ x1a, y1a, x2a, y2a = xc, max(yc - h, 0), min(xc + w, s * 2), yc
+ x1b, y1b, x2b, y2b = 0, h - (y2a - y1a), min(w, x2a - x1a), h
+ elif i == 2: # bottom left
+ x1a, y1a, x2a, y2a = max(xc - w, 0), yc, xc, min(s * 2, yc + h)
+ x1b, y1b, x2b, y2b = w - (x2a - x1a), 0, w, min(y2a - y1a, h)
+ elif i == 3: # bottom right
+ x1a, y1a, x2a, y2a = xc, yc, min(xc + w, s * 2), min(s * 2, yc + h)
+ x1b, y1b, x2b, y2b = 0, 0, min(w, x2a - x1a), min(y2a - y1a, h)
+
+ img4[y1a:y2a, x1a:x2a] = img[y1b:y2b, x1b:x2b] # img4[ymin:ymax, xmin:xmax]
+ padw = x1a - x1b
+ padh = y1a - y1b
+
+ # Labels
+ labels, segments = self.labels[index].copy(), self.segments[index].copy()
+ if labels.size:
+ labels[:, 1:] = xywhn2xyxy(labels[:, 1:], w, h, padw, padh) # normalized xywh to pixel xyxy format
+ segments = [xyn2xy(x, w, h, padw, padh) for x in segments]
+ labels4.append(labels)
+ segments4.extend(segments)
+
+ # Concat/clip labels
+ labels4 = np.concatenate(labels4, 0)
+ for x in (labels4[:, 1:], *segments4):
+ np.clip(x, 0, 2 * s, out=x) # clip when using random_perspective()
+ # img4, labels4 = replicate(img4, labels4) # replicate
+
+ # Augment
+ img4, labels4, segments4 = copy_paste(img4, labels4, segments4, p=self.hyp['copy_paste'])
+ img4, labels4 = random_perspective(img4,
+ labels4,
+ segments4,
+ degrees=self.hyp['degrees'],
+ translate=self.hyp['translate'],
+ scale=self.hyp['scale'],
+ shear=self.hyp['shear'],
+ perspective=self.hyp['perspective'],
+ border=self.mosaic_border) # border to remove
+
+ return img4, labels4
+
+ def load_mosaic9(self, index):
+ # YOLOv5 9-mosaic loader. Loads 1 image + 8 random images into a 9-image mosaic
+ labels9, segments9 = [], []
+ s = self.img_size
+ indices = [index] + random.choices(self.indices, k=8) # 8 additional image indices
+ random.shuffle(indices)
+ hp, wp = -1, -1 # height, width previous
+ for i, index in enumerate(indices):
+ # Load image
+ img, _, (h, w) = self.load_image(index)
+
+ # place img in img9
+ if i == 0: # center
+ img9 = np.full((s * 3, s * 3, img.shape[2]), 114, dtype=np.uint8) # base image with 4 tiles
+ h0, w0 = h, w
+ c = s, s, s + w, s + h # xmin, ymin, xmax, ymax (base) coordinates
+ elif i == 1: # top
+ c = s, s - h, s + w, s
+ elif i == 2: # top right
+ c = s + wp, s - h, s + wp + w, s
+ elif i == 3: # right
+ c = s + w0, s, s + w0 + w, s + h
+ elif i == 4: # bottom right
+ c = s + w0, s + hp, s + w0 + w, s + hp + h
+ elif i == 5: # bottom
+ c = s + w0 - w, s + h0, s + w0, s + h0 + h
+ elif i == 6: # bottom left
+ c = s + w0 - wp - w, s + h0, s + w0 - wp, s + h0 + h
+ elif i == 7: # left
+ c = s - w, s + h0 - h, s, s + h0
+ elif i == 8: # top left
+ c = s - w, s + h0 - hp - h, s, s + h0 - hp
+
+ padx, pady = c[:2]
+ x1, y1, x2, y2 = (max(x, 0) for x in c) # allocate coords
+
+ # Labels
+ labels, segments = self.labels[index].copy(), self.segments[index].copy()
+ if labels.size:
+ labels[:, 1:] = xywhn2xyxy(labels[:, 1:], w, h, padx, pady) # normalized xywh to pixel xyxy format
+ segments = [xyn2xy(x, w, h, padx, pady) for x in segments]
+ labels9.append(labels)
+ segments9.extend(segments)
+
+ # Image
+ img9[y1:y2, x1:x2] = img[y1 - pady:, x1 - padx:] # img9[ymin:ymax, xmin:xmax]
+ hp, wp = h, w # height, width previous
+
+ # Offset
+ yc, xc = (int(random.uniform(0, s)) for _ in self.mosaic_border) # mosaic center x, y
+ img9 = img9[yc:yc + 2 * s, xc:xc + 2 * s]
+
+ # Concat/clip labels
+ labels9 = np.concatenate(labels9, 0)
+ labels9[:, [1, 3]] -= xc
+ labels9[:, [2, 4]] -= yc
+ c = np.array([xc, yc]) # centers
+ segments9 = [x - c for x in segments9]
+
+ for x in (labels9[:, 1:], *segments9):
+ np.clip(x, 0, 2 * s, out=x) # clip when using random_perspective()
+ # img9, labels9 = replicate(img9, labels9) # replicate
+
+ # Augment
+ img9, labels9, segments9 = copy_paste(img9, labels9, segments9, p=self.hyp['copy_paste'])
+ img9, labels9 = random_perspective(img9,
+ labels9,
+ segments9,
+ degrees=self.hyp['degrees'],
+ translate=self.hyp['translate'],
+ scale=self.hyp['scale'],
+ shear=self.hyp['shear'],
+ perspective=self.hyp['perspective'],
+ border=self.mosaic_border) # border to remove
+
+ return img9, labels9
+
+ @staticmethod
+ def collate_fn(batch):
+ im, label, path, shapes = zip(*batch) # transposed
+ for i, lb in enumerate(label):
+ lb[:, 0] = i # add target image index for build_targets()
+ return torch.stack(im, 0), torch.cat(label, 0), path, shapes
+
+ @staticmethod
+ def collate_fn4(batch):
+ im, label, path, shapes = zip(*batch) # transposed
+ n = len(shapes) // 4
+ im4, label4, path4, shapes4 = [], [], path[:n], shapes[:n]
+
+ ho = torch.tensor([[0.0, 0, 0, 1, 0, 0]])
+ wo = torch.tensor([[0.0, 0, 1, 0, 0, 0]])
+ s = torch.tensor([[1, 1, 0.5, 0.5, 0.5, 0.5]]) # scale
+ for i in range(n): # zidane torch.zeros(16,3,720,1280) # BCHW
+ i *= 4
+ if random.random() < 0.5:
+ im1 = F.interpolate(im[i].unsqueeze(0).float(), scale_factor=2.0, mode='bilinear',
+ align_corners=False)[0].type(im[i].type())
+ lb = label[i]
+ else:
+ im1 = torch.cat((torch.cat((im[i], im[i + 1]), 1), torch.cat((im[i + 2], im[i + 3]), 1)), 2)
+ lb = torch.cat((label[i], label[i + 1] + ho, label[i + 2] + wo, label[i + 3] + ho + wo), 0) * s
+ im4.append(im1)
+ label4.append(lb)
+
+ for i, lb in enumerate(label4):
+ lb[:, 0] = i # add target image index for build_targets()
+
+ return torch.stack(im4, 0), torch.cat(label4, 0), path4, shapes4
+
+
+# Ancillary functions --------------------------------------------------------------------------------------------------
+def flatten_recursive(path=DATASETS_DIR / 'coco128'):
+ # Flatten a recursive directory by bringing all files to top level
+ new_path = Path(f'{str(path)}_flat')
+ if os.path.exists(new_path):
+ shutil.rmtree(new_path) # delete output folder
+ os.makedirs(new_path) # make new output folder
+ for file in tqdm(glob.glob(f'{str(Path(path))}/**/*.*', recursive=True)):
+ shutil.copyfile(file, new_path / Path(file).name)
+
+
+def extract_boxes(path=DATASETS_DIR / 'coco128'): # from utils.dataloaders import *; extract_boxes()
+ # Convert detection dataset into classification dataset, with one directory per class
+ path = Path(path) # images dir
+ shutil.rmtree(path / 'classification') if (path / 'classification').is_dir() else None # remove existing
+ files = list(path.rglob('*.*'))
+ n = len(files) # number of files
+ for im_file in tqdm(files, total=n):
+ if im_file.suffix[1:] in IMG_FORMATS:
+ # image
+ im = cv2.imread(str(im_file))[..., ::-1] # BGR to RGB
+ h, w = im.shape[:2]
+
+ # labels
+ lb_file = Path(img2label_paths([str(im_file)])[0])
+ if Path(lb_file).exists():
+ with open(lb_file) as f:
+ lb = np.array([x.split() for x in f.read().strip().splitlines()], dtype=np.float32) # labels
+
+ for j, x in enumerate(lb):
+ c = int(x[0]) # class
+ f = (path / 'classifier') / f'{c}' / f'{path.stem}_{im_file.stem}_{j}.jpg' # new filename
+ if not f.parent.is_dir():
+ f.parent.mkdir(parents=True)
+
+ b = x[1:] * [w, h, w, h] # box
+ # b[2:] = b[2:].max() # rectangle to square
+ b[2:] = b[2:] * 1.2 + 3 # pad
+ b = xywh2xyxy(b.reshape(-1, 4)).ravel().astype(int)
+
+ b[[0, 2]] = np.clip(b[[0, 2]], 0, w) # clip boxes outside of image
+ b[[1, 3]] = np.clip(b[[1, 3]], 0, h)
+ assert cv2.imwrite(str(f), im[b[1]:b[3], b[0]:b[2]]), f'box failure in {f}'
+
+
+def autosplit(path=DATASETS_DIR / 'coco128/images', weights=(0.9, 0.1, 0.0), annotated_only=False):
+ """ Autosplit a dataset into train/val/test splits and save path/autosplit_*.txt files
+ Usage: from utils.dataloaders import *; autosplit()
+ Arguments
+ path: Path to images directory
+ weights: Train, val, test weights (list, tuple)
+ annotated_only: Only use images with an annotated txt file
+ """
+ path = Path(path) # images dir
+ files = sorted(x for x in path.rglob('*.*') if x.suffix[1:].lower() in IMG_FORMATS) # image files only
+ n = len(files) # number of files
+ random.seed(0) # for reproducibility
+ indices = random.choices([0, 1, 2], weights=weights, k=n) # assign each image to a split
+
+ txt = ['autosplit_train.txt', 'autosplit_val.txt', 'autosplit_test.txt'] # 3 txt files
+ for x in txt:
+ if (path.parent / x).exists():
+ (path.parent / x).unlink() # remove existing
+
+ print(f'Autosplitting images from {path}' + ', using *.txt labeled images only' * annotated_only)
+ for i, img in tqdm(zip(indices, files), total=n):
+ if not annotated_only or Path(img2label_paths([str(img)])[0]).exists(): # check label
+ with open(path.parent / txt[i], 'a') as f:
+ f.write(f'./{img.relative_to(path.parent).as_posix()}' + '\n') # add image to txt file
+
+
+def verify_image_label(args):
+ # Verify one image-label pair
+ im_file, lb_file, prefix = args
+ nm, nf, ne, nc, msg, segments = 0, 0, 0, 0, '', [] # number (missing, found, empty, corrupt), message, segments
+ try:
+ # verify images
+ im = Image.open(im_file)
+ im.verify() # PIL verify
+ shape = exif_size(im) # image size
+ assert (shape[0] > 9) & (shape[1] > 9), f'image size {shape} <10 pixels'
+ assert im.format.lower() in IMG_FORMATS, f'invalid image format {im.format}'
+ if im.format.lower() in ('jpg', 'jpeg'):
+ with open(im_file, 'rb') as f:
+ f.seek(-2, 2)
+ if f.read() != b'\xff\xd9': # corrupt JPEG
+ ImageOps.exif_transpose(Image.open(im_file)).save(im_file, 'JPEG', subsampling=0, quality=100)
+ msg = f'{prefix}WARNING ⚠️ {im_file}: corrupt JPEG restored and saved'
+
+ # verify labels
+ if os.path.isfile(lb_file):
+ nf = 1 # label found
+ with open(lb_file) as f:
+ lb = [x.split() for x in f.read().strip().splitlines() if len(x)]
+ if any(len(x) > 6 for x in lb): # is segment
+ classes = np.array([x[0] for x in lb], dtype=np.float32)
+ segments = [np.array(x[1:], dtype=np.float32).reshape(-1, 2) for x in lb] # (cls, xy1...)
+ lb = np.concatenate((classes.reshape(-1, 1), segments2boxes(segments)), 1) # (cls, xywh)
+ lb = np.array(lb, dtype=np.float32)
+ nl = len(lb)
+ if nl:
+ assert lb.shape[1] == 5, f'labels require 5 columns, {lb.shape[1]} columns detected'
+ assert (lb >= 0).all(), f'negative label values {lb[lb < 0]}'
+ assert (lb[:, 1:] <= 1).all(), f'non-normalized or out of bounds coordinates {lb[:, 1:][lb[:, 1:] > 1]}'
+ _, i = np.unique(lb, axis=0, return_index=True)
+ if len(i) < nl: # duplicate row check
+ lb = lb[i] # remove duplicates
+ if segments:
+ segments = [segments[x] for x in i]
+ msg = f'{prefix}WARNING ⚠️ {im_file}: {nl - len(i)} duplicate labels removed'
+ else:
+ ne = 1 # label empty
+ lb = np.zeros((0, 5), dtype=np.float32)
+ else:
+ nm = 1 # label missing
+ lb = np.zeros((0, 5), dtype=np.float32)
+ return im_file, lb, shape, segments, nm, nf, ne, nc, msg
+ except Exception as e:
+ nc = 1
+ msg = f'{prefix}WARNING ⚠️ {im_file}: ignoring corrupt image/label: {e}'
+ return [None, None, None, None, nm, nf, ne, nc, msg]
+
+
+class HUBDatasetStats():
+ """ Class for generating HUB dataset JSON and `-hub` dataset directory
+
+ Arguments
+ path: Path to data.yaml or data.zip (with data.yaml inside data.zip)
+ autodownload: Attempt to download dataset if not found locally
+
+ Usage
+ from utils.dataloaders import HUBDatasetStats
+ stats = HUBDatasetStats('coco128.yaml', autodownload=True) # usage 1
+ stats = HUBDatasetStats('path/to/coco128.zip') # usage 2
+ stats.get_json(save=False)
+ stats.process_images()
+ """
+
+ def __init__(self, path='coco128.yaml', autodownload=False):
+ # Initialize class
+ zipped, data_dir, yaml_path = self._unzip(Path(path))
+ try:
+ with open(check_yaml(yaml_path), errors='ignore') as f:
+ data = yaml.safe_load(f) # data dict
+ if zipped:
+ data['path'] = data_dir
+ except Exception as e:
+ raise Exception('error/HUB/dataset_stats/yaml_load') from e
+
+ check_dataset(data, autodownload) # download dataset if missing
+ self.hub_dir = Path(data['path'] + '-hub')
+ self.im_dir = self.hub_dir / 'images'
+ self.im_dir.mkdir(parents=True, exist_ok=True) # makes /images
+ self.stats = {'nc': data['nc'], 'names': list(data['names'].values())} # statistics dictionary
+ self.data = data
+
+ @staticmethod
+ def _find_yaml(dir):
+ # Return data.yaml file
+ files = list(dir.glob('*.yaml')) or list(dir.rglob('*.yaml')) # try root level first and then recursive
+ assert files, f'No *.yaml file found in {dir}'
+ if len(files) > 1:
+ files = [f for f in files if f.stem == dir.stem] # prefer *.yaml files that match dir name
+ assert files, f'Multiple *.yaml files found in {dir}, only 1 *.yaml file allowed'
+ assert len(files) == 1, f'Multiple *.yaml files found: {files}, only 1 *.yaml file allowed in {dir}'
+ return files[0]
+
+ def _unzip(self, path):
+ # Unzip data.zip
+ if not str(path).endswith('.zip'): # path is data.yaml
+ return False, None, path
+ assert Path(path).is_file(), f'Error unzipping {path}, file not found'
+ unzip_file(path, path=path.parent)
+ dir = path.with_suffix('') # dataset directory == zip name
+ assert dir.is_dir(), f'Error unzipping {path}, {dir} not found. path/to/abc.zip MUST unzip to path/to/abc/'
+ return True, str(dir), self._find_yaml(dir) # zipped, data_dir, yaml_path
+
+ def _hub_ops(self, f, max_dim=1920):
+ # HUB ops for 1 image 'f': resize and save at reduced quality in /dataset-hub for web/app viewing
+ f_new = self.im_dir / Path(f).name # dataset-hub image filename
+ try: # use PIL
+ im = Image.open(f)
+ r = max_dim / max(im.height, im.width) # ratio
+ if r < 1.0: # image too large
+ im = im.resize((int(im.width * r), int(im.height * r)))
+ im.save(f_new, 'JPEG', quality=50, optimize=True) # save
+ except Exception as e: # use OpenCV
+ LOGGER.info(f'WARNING ⚠️ HUB ops PIL failure {f}: {e}')
+ im = cv2.imread(f)
+ im_height, im_width = im.shape[:2]
+ r = max_dim / max(im_height, im_width) # ratio
+ if r < 1.0: # image too large
+ im = cv2.resize(im, (int(im_width * r), int(im_height * r)), interpolation=cv2.INTER_AREA)
+ cv2.imwrite(str(f_new), im)
+
+ def get_json(self, save=False, verbose=False):
+ # Return dataset JSON for Ultralytics HUB
+ def _round(labels):
+ # Update labels to integer class and 6 decimal place floats
+ return [[int(c), *(round(x, 4) for x in points)] for c, *points in labels]
+
+ for split in 'train', 'val', 'test':
+ if self.data.get(split) is None:
+ self.stats[split] = None # i.e. no test set
+ continue
+ dataset = LoadImagesAndLabels(self.data[split]) # load dataset
+ x = np.array([
+ np.bincount(label[:, 0].astype(int), minlength=self.data['nc'])
+ for label in tqdm(dataset.labels, total=dataset.n, desc='Statistics')]) # shape(128x80)
+ self.stats[split] = {
+ 'instance_stats': {
+ 'total': int(x.sum()),
+ 'per_class': x.sum(0).tolist()},
+ 'image_stats': {
+ 'total': dataset.n,
+ 'unlabelled': int(np.all(x == 0, 1).sum()),
+ 'per_class': (x > 0).sum(0).tolist()},
+ 'labels': [{
+ str(Path(k).name): _round(v.tolist())} for k, v in zip(dataset.im_files, dataset.labels)]}
+
+ # Save, print and return
+ if save:
+ stats_path = self.hub_dir / 'stats.json'
+ print(f'Saving {stats_path.resolve()}...')
+ with open(stats_path, 'w') as f:
+ json.dump(self.stats, f) # save stats.json
+ if verbose:
+ print(json.dumps(self.stats, indent=2, sort_keys=False))
+ return self.stats
+
+ def process_images(self):
+ # Compress images for Ultralytics HUB
+ for split in 'train', 'val', 'test':
+ if self.data.get(split) is None:
+ continue
+ dataset = LoadImagesAndLabels(self.data[split]) # load dataset
+ desc = f'{split} images'
+ for _ in tqdm(ThreadPool(NUM_THREADS).imap(self._hub_ops, dataset.im_files), total=dataset.n, desc=desc):
+ pass
+ print(f'Done. All images saved to {self.im_dir}')
+ return self.im_dir
+
+
+# Classification dataloaders -------------------------------------------------------------------------------------------
+class ClassificationDataset(torchvision.datasets.ImageFolder):
+ """
+ YOLOv5 Classification Dataset.
+ Arguments
+ root: Dataset path
+ transform: torchvision transforms, used by default
+ album_transform: Albumentations transforms, used if installed
+ """
+
+ def __init__(self, root, augment, imgsz, cache=False):
+ super().__init__(root=root)
+ self.torch_transforms = classify_transforms(imgsz)
+ self.album_transforms = classify_albumentations(augment, imgsz) if augment else None
+ self.cache_ram = cache is True or cache == 'ram'
+ self.cache_disk = cache == 'disk'
+ self.samples = [list(x) + [Path(x[0]).with_suffix('.npy'), None] for x in self.samples] # file, index, npy, im
+
+ def __getitem__(self, i):
+ f, j, fn, im = self.samples[i] # filename, index, filename.with_suffix('.npy'), image
+ if self.cache_ram and im is None:
+ im = self.samples[i][3] = cv2.imread(f)
+ elif self.cache_disk:
+ if not fn.exists(): # load npy
+ np.save(fn.as_posix(), cv2.imread(f))
+ im = np.load(fn)
+ else: # read image
+ im = cv2.imread(f) # BGR
+ if self.album_transforms:
+ sample = self.album_transforms(image=cv2.cvtColor(im, cv2.COLOR_BGR2RGB))['image']
+ else:
+ sample = self.torch_transforms(im)
+ return sample, j
+
+
+def create_classification_dataloader(path,
+ imgsz=224,
+ batch_size=16,
+ augment=True,
+ cache=False,
+ rank=-1,
+ workers=8,
+ shuffle=True):
+ # Returns Dataloader object to be used with YOLOv5 Classifier
+ with torch_distributed_zero_first(rank): # init dataset *.cache only once if DDP
+ dataset = ClassificationDataset(root=path, imgsz=imgsz, augment=augment, cache=cache)
+ batch_size = min(batch_size, len(dataset))
+ nd = torch.cuda.device_count()
+ nw = min([os.cpu_count() // max(nd, 1), batch_size if batch_size > 1 else 0, workers])
+ sampler = None if rank == -1 else distributed.DistributedSampler(dataset, shuffle=shuffle)
+ generator = torch.Generator()
+ generator.manual_seed(6148914691236517205 + RANK)
+ return InfiniteDataLoader(dataset,
+ batch_size=batch_size,
+ shuffle=shuffle and sampler is None,
+ num_workers=nw,
+ sampler=sampler,
+ pin_memory=PIN_MEMORY,
+ worker_init_fn=seed_worker,
+ generator=generator) # or DataLoader(persistent_workers=True)
diff --git a/ros2_ws/src/yolov3_ros/utils/datasets.py b/ros2_ws/src/yolov3_ros/utils/datasets.py
new file mode 100755
index 00000000..462d561a
--- /dev/null
+++ b/ros2_ws/src/yolov3_ros/utils/datasets.py
@@ -0,0 +1,1036 @@
+# YOLOv3 🚀 by Ultralytics, GPL-3.0 license
+"""
+Dataloaders and dataset utils
+"""
+
+import glob
+import hashlib
+import json
+import os
+import random
+import shutil
+import time
+from itertools import repeat
+from multiprocessing.pool import Pool, ThreadPool
+from pathlib import Path
+from threading import Thread
+from zipfile import ZipFile
+
+import cv2
+import numpy as np
+import torch
+import torch.nn.functional as F
+import yaml
+from PIL import ExifTags, Image, ImageOps
+from torch.utils.data import DataLoader, Dataset, dataloader, distributed
+from tqdm import tqdm
+
+from utils.augmentations import Albumentations, augment_hsv, copy_paste, letterbox, mixup, random_perspective
+from utils.general import (LOGGER, check_dataset, check_requirements, check_yaml, clean_str, segments2boxes, xyn2xy,
+ xywh2xyxy, xywhn2xyxy, xyxy2xywhn)
+from utils.torch_utils import torch_distributed_zero_first
+
+# Parameters
+HELP_URL = 'https://github.com/ultralytics/yolov3/wiki/Train-Custom-Data'
+IMG_FORMATS = ['bmp', 'jpg', 'jpeg', 'png', 'tif', 'tiff', 'dng', 'webp', 'mpo'] # acceptable image suffixes
+VID_FORMATS = ['mov', 'avi', 'mp4', 'mpg', 'mpeg', 'm4v', 'wmv', 'mkv'] # acceptable video suffixes
+WORLD_SIZE = int(os.getenv('WORLD_SIZE', 1)) # DPP
+NUM_THREADS = min(8, os.cpu_count()) # number of multiprocessing threads
+
+# Get orientation exif tag
+for orientation in ExifTags.TAGS.keys():
+ if ExifTags.TAGS[orientation] == 'Orientation':
+ break
+
+
+def get_hash(paths):
+ # Returns a single hash value of a list of paths (files or dirs)
+ size = sum(os.path.getsize(p) for p in paths if os.path.exists(p)) # sizes
+ h = hashlib.md5(str(size).encode()) # hash sizes
+ h.update(''.join(paths).encode()) # hash paths
+ return h.hexdigest() # return hash
+
+
+def exif_size(img):
+ # Returns exif-corrected PIL size
+ s = img.size # (width, height)
+ try:
+ rotation = dict(img._getexif().items())[orientation]
+ if rotation == 6: # rotation 270
+ s = (s[1], s[0])
+ elif rotation == 8: # rotation 90
+ s = (s[1], s[0])
+ except:
+ pass
+
+ return s
+
+
+def exif_transpose(image):
+ """
+ Transpose a PIL image accordingly if it has an EXIF Orientation tag.
+ Inplace version of https://github.com/python-pillow/Pillow/blob/master/src/PIL/ImageOps.py exif_transpose()
+
+ :param image: The image to transpose.
+ :return: An image.
+ """
+ exif = image.getexif()
+ orientation = exif.get(0x0112, 1) # default 1
+ if orientation > 1:
+ method = {2: Image.FLIP_LEFT_RIGHT,
+ 3: Image.ROTATE_180,
+ 4: Image.FLIP_TOP_BOTTOM,
+ 5: Image.TRANSPOSE,
+ 6: Image.ROTATE_270,
+ 7: Image.TRANSVERSE,
+ 8: Image.ROTATE_90,
+ }.get(orientation)
+ if method is not None:
+ image = image.transpose(method)
+ del exif[0x0112]
+ image.info["exif"] = exif.tobytes()
+ return image
+
+
+def create_dataloader(path, imgsz, batch_size, stride, single_cls=False, hyp=None, augment=False, cache=False, pad=0.0,
+ rect=False, rank=-1, workers=8, image_weights=False, quad=False, prefix='', shuffle=False):
+ if rect and shuffle:
+ LOGGER.warning('WARNING: --rect is incompatible with DataLoader shuffle, setting shuffle=False')
+ shuffle = False
+ with torch_distributed_zero_first(rank): # init dataset *.cache only once if DDP
+ dataset = LoadImagesAndLabels(path, imgsz, batch_size,
+ augment=augment, # augmentation
+ hyp=hyp, # hyperparameters
+ rect=rect, # rectangular batches
+ cache_images=cache,
+ single_cls=single_cls,
+ stride=int(stride),
+ pad=pad,
+ image_weights=image_weights,
+ prefix=prefix)
+
+ batch_size = min(batch_size, len(dataset))
+ nw = min([os.cpu_count() // WORLD_SIZE, batch_size if batch_size > 1 else 0, workers]) # number of workers
+ sampler = None if rank == -1 else distributed.DistributedSampler(dataset, shuffle=shuffle)
+ loader = DataLoader if image_weights else InfiniteDataLoader # only DataLoader allows for attribute updates
+ return loader(dataset,
+ batch_size=batch_size,
+ shuffle=shuffle and sampler is None,
+ num_workers=nw,
+ sampler=sampler,
+ pin_memory=True,
+ collate_fn=LoadImagesAndLabels.collate_fn4 if quad else LoadImagesAndLabels.collate_fn), dataset
+
+
+class InfiniteDataLoader(dataloader.DataLoader):
+ """ Dataloader that reuses workers
+
+ Uses same syntax as vanilla DataLoader
+ """
+
+ def __init__(self, *args, **kwargs):
+ super().__init__(*args, **kwargs)
+ object.__setattr__(self, 'batch_sampler', _RepeatSampler(self.batch_sampler))
+ self.iterator = super().__iter__()
+
+ def __len__(self):
+ return len(self.batch_sampler.sampler)
+
+ def __iter__(self):
+ for i in range(len(self)):
+ yield next(self.iterator)
+
+
+class _RepeatSampler:
+ """ Sampler that repeats forever
+
+ Args:
+ sampler (Sampler)
+ """
+
+ def __init__(self, sampler):
+ self.sampler = sampler
+
+ def __iter__(self):
+ while True:
+ yield from iter(self.sampler)
+
+
+class LoadImages:
+ # image/video dataloader, i.e. `python detect.py --source image.jpg/vid.mp4`
+ def __init__(self, path, img_size=640, stride=32, auto=True):
+ p = str(Path(path).resolve()) # os-agnostic absolute path
+ if '*' in p:
+ files = sorted(glob.glob(p, recursive=True)) # glob
+ elif os.path.isdir(p):
+ files = sorted(glob.glob(os.path.join(p, '*.*'))) # dir
+ elif os.path.isfile(p):
+ files = [p] # files
+ else:
+ raise Exception(f'ERROR: {p} does not exist')
+
+ images = [x for x in files if x.split('.')[-1].lower() in IMG_FORMATS]
+ videos = [x for x in files if x.split('.')[-1].lower() in VID_FORMATS]
+ ni, nv = len(images), len(videos)
+
+ self.img_size = img_size
+ self.stride = stride
+ self.files = images + videos
+ self.nf = ni + nv # number of files
+ self.video_flag = [False] * ni + [True] * nv
+ self.mode = 'image'
+ self.auto = auto
+ if any(videos):
+ self.new_video(videos[0]) # new video
+ else:
+ self.cap = None
+ assert self.nf > 0, f'No images or videos found in {p}. ' \
+ f'Supported formats are:\nimages: {IMG_FORMATS}\nvideos: {VID_FORMATS}'
+
+ def __iter__(self):
+ self.count = 0
+ return self
+
+ def __next__(self):
+ if self.count == self.nf:
+ raise StopIteration
+ path = self.files[self.count]
+
+ if self.video_flag[self.count]:
+ # Read video
+ self.mode = 'video'
+ ret_val, img0 = self.cap.read()
+ if not ret_val:
+ self.count += 1
+ self.cap.release()
+ if self.count == self.nf: # last video
+ raise StopIteration
+ else:
+ path = self.files[self.count]
+ self.new_video(path)
+ ret_val, img0 = self.cap.read()
+
+ self.frame += 1
+ s = f'video {self.count + 1}/{self.nf} ({self.frame}/{self.frames}) {path}: '
+
+ else:
+ # Read image
+ self.count += 1
+ img0 = cv2.imread(path) # BGR
+ assert img0 is not None, f'Image Not Found {path}'
+ s = f'image {self.count}/{self.nf} {path}: '
+
+ # Padded resize
+ img = letterbox(img0, self.img_size, stride=self.stride, auto=self.auto)[0]
+
+ # Convert
+ img = img.transpose((2, 0, 1))[::-1] # HWC to CHW, BGR to RGB
+ img = np.ascontiguousarray(img)
+
+ return path, img, img0, self.cap, s
+
+ def new_video(self, path):
+ self.frame = 0
+ self.cap = cv2.VideoCapture(path)
+ self.frames = int(self.cap.get(cv2.CAP_PROP_FRAME_COUNT))
+
+ def __len__(self):
+ return self.nf # number of files
+
+
+class LoadWebcam: # for inference
+ # local webcam dataloader, i.e. `python detect.py --source 0`
+ def __init__(self, pipe='0', img_size=640, stride=32):
+ self.img_size = img_size
+ self.stride = stride
+ self.pipe = eval(pipe) if pipe.isnumeric() else pipe
+ self.cap = cv2.VideoCapture(self.pipe) # video capture object
+ self.cap.set(cv2.CAP_PROP_BUFFERSIZE, 3) # set buffer size
+
+ def __iter__(self):
+ self.count = -1
+ return self
+
+ def __next__(self):
+ self.count += 1
+ if cv2.waitKey(1) == ord('q'): # q to quit
+ self.cap.release()
+ cv2.destroyAllWindows()
+ raise StopIteration
+
+ # Read frame
+ ret_val, img0 = self.cap.read()
+ img0 = cv2.flip(img0, 1) # flip left-right
+
+ # Print
+ assert ret_val, f'Camera Error {self.pipe}'
+ img_path = 'webcam.jpg'
+ s = f'webcam {self.count}: '
+
+ # Padded resize
+ img = letterbox(img0, self.img_size, stride=self.stride)[0]
+
+ # Convert
+ img = img.transpose((2, 0, 1))[::-1] # HWC to CHW, BGR to RGB
+ img = np.ascontiguousarray(img)
+
+ return img_path, img, img0, None, s
+
+ def __len__(self):
+ return 0
+
+
+class LoadStreams:
+ # streamloader, i.e. `python detect.py --source 'rtsp://example.com/media.mp4' # RTSP, RTMP, HTTP streams`
+ def __init__(self, sources='streams.txt', img_size=640, stride=32, auto=True):
+ self.mode = 'stream'
+ self.img_size = img_size
+ self.stride = stride
+
+ if os.path.isfile(sources):
+ with open(sources) as f:
+ sources = [x.strip() for x in f.read().strip().splitlines() if len(x.strip())]
+ else:
+ sources = [sources]
+
+ n = len(sources)
+ self.imgs, self.fps, self.frames, self.threads = [None] * n, [0] * n, [0] * n, [None] * n
+ self.sources = [clean_str(x) for x in sources] # clean source names for later
+ self.auto = auto
+ for i, s in enumerate(sources): # index, source
+ # Start thread to read frames from video stream
+ st = f'{i + 1}/{n}: {s}... '
+ if 'youtube.com/' in s or 'youtu.be/' in s: # if source is YouTube video
+ check_requirements(('pafy', 'youtube_dl'))
+ import pafy
+ s = pafy.new(s).getbest(preftype="mp4").url # YouTube URL
+ s = eval(s) if s.isnumeric() else s # i.e. s = '0' local webcam
+ cap = cv2.VideoCapture(s)
+ assert cap.isOpened(), f'{st}Failed to open {s}'
+ w = int(cap.get(cv2.CAP_PROP_FRAME_WIDTH))
+ h = int(cap.get(cv2.CAP_PROP_FRAME_HEIGHT))
+ self.fps[i] = max(cap.get(cv2.CAP_PROP_FPS) % 100, 0) or 30.0 # 30 FPS fallback
+ self.frames[i] = max(int(cap.get(cv2.CAP_PROP_FRAME_COUNT)), 0) or float('inf') # infinite stream fallback
+
+ _, self.imgs[i] = cap.read() # guarantee first frame
+ self.threads[i] = Thread(target=self.update, args=([i, cap, s]), daemon=True)
+ LOGGER.info(f"{st} Success ({self.frames[i]} frames {w}x{h} at {self.fps[i]:.2f} FPS)")
+ self.threads[i].start()
+ LOGGER.info('') # newline
+
+ # check for common shapes
+ s = np.stack([letterbox(x, self.img_size, stride=self.stride, auto=self.auto)[0].shape for x in self.imgs])
+ self.rect = np.unique(s, axis=0).shape[0] == 1 # rect inference if all shapes equal
+ if not self.rect:
+ LOGGER.warning('WARNING: Stream shapes differ. For optimal performance supply similarly-shaped streams.')
+
+ def update(self, i, cap, stream):
+ # Read stream `i` frames in daemon thread
+ n, f, read = 0, self.frames[i], 1 # frame number, frame array, inference every 'read' frame
+ while cap.isOpened() and n < f:
+ n += 1
+ # _, self.imgs[index] = cap.read()
+ cap.grab()
+ if n % read == 0:
+ success, im = cap.retrieve()
+ if success:
+ self.imgs[i] = im
+ else:
+ LOGGER.warning('WARNING: Video stream unresponsive, please check your IP camera connection.')
+ self.imgs[i] *= 0
+ cap.open(stream) # re-open stream if signal was lost
+ time.sleep(1 / self.fps[i]) # wait time
+
+ def __iter__(self):
+ self.count = -1
+ return self
+
+ def __next__(self):
+ self.count += 1
+ if not all(x.is_alive() for x in self.threads) or cv2.waitKey(1) == ord('q'): # q to quit
+ cv2.destroyAllWindows()
+ raise StopIteration
+
+ # Letterbox
+ img0 = self.imgs.copy()
+ img = [letterbox(x, self.img_size, stride=self.stride, auto=self.rect and self.auto)[0] for x in img0]
+
+ # Stack
+ img = np.stack(img, 0)
+
+ # Convert
+ img = img[..., ::-1].transpose((0, 3, 1, 2)) # BGR to RGB, BHWC to BCHW
+ img = np.ascontiguousarray(img)
+
+ return self.sources, img, img0, None, ''
+
+ def __len__(self):
+ return len(self.sources) # 1E12 frames = 32 streams at 30 FPS for 30 years
+
+
+def img2label_paths(img_paths):
+ # Define label paths as a function of image paths
+ sa, sb = os.sep + 'images' + os.sep, os.sep + 'labels' + os.sep # /images/, /labels/ substrings
+ return [sb.join(x.rsplit(sa, 1)).rsplit('.', 1)[0] + '.txt' for x in img_paths]
+
+
+class LoadImagesAndLabels(Dataset):
+ # train_loader/val_loader, loads images and labels for training and validation
+ cache_version = 0.6 # dataset labels *.cache version
+
+ def __init__(self, path, img_size=640, batch_size=16, augment=False, hyp=None, rect=False, image_weights=False,
+ cache_images=False, single_cls=False, stride=32, pad=0.0, prefix=''):
+ self.img_size = img_size
+ self.augment = augment
+ self.hyp = hyp
+ self.image_weights = image_weights
+ self.rect = False if image_weights else rect
+ self.mosaic = self.augment and not self.rect # load 4 images at a time into a mosaic (only during training)
+ self.mosaic_border = [-img_size // 2, -img_size // 2]
+ self.stride = stride
+ self.path = path
+ self.albumentations = Albumentations() if augment else None
+
+ try:
+ f = [] # image files
+ for p in path if isinstance(path, list) else [path]:
+ p = Path(p) # os-agnostic
+ if p.is_dir(): # dir
+ f += glob.glob(str(p / '**' / '*.*'), recursive=True)
+ # f = list(p.rglob('*.*')) # pathlib
+ elif p.is_file(): # file
+ with open(p) as t:
+ t = t.read().strip().splitlines()
+ parent = str(p.parent) + os.sep
+ f += [x.replace('./', parent) if x.startswith('./') else x for x in t] # local to global path
+ # f += [p.parent / x.lstrip(os.sep) for x in t] # local to global path (pathlib)
+ else:
+ raise Exception(f'{prefix}{p} does not exist')
+ self.img_files = sorted(x.replace('/', os.sep) for x in f if x.split('.')[-1].lower() in IMG_FORMATS)
+ # self.img_files = sorted([x for x in f if x.suffix[1:].lower() in IMG_FORMATS]) # pathlib
+ assert self.img_files, f'{prefix}No images found'
+ except Exception as e:
+ raise Exception(f'{prefix}Error loading data from {path}: {e}\nSee {HELP_URL}')
+
+ # Check cache
+ self.label_files = img2label_paths(self.img_files) # labels
+ cache_path = (p if p.is_file() else Path(self.label_files[0]).parent).with_suffix('.cache')
+ try:
+ cache, exists = np.load(cache_path, allow_pickle=True).item(), True # load dict
+ assert cache['version'] == self.cache_version # same version
+ assert cache['hash'] == get_hash(self.label_files + self.img_files) # same hash
+ except:
+ cache, exists = self.cache_labels(cache_path, prefix), False # cache
+
+ # Display cache
+ nf, nm, ne, nc, n = cache.pop('results') # found, missing, empty, corrupted, total
+ if exists:
+ d = f"Scanning '{cache_path}' images and labels... {nf} found, {nm} missing, {ne} empty, {nc} corrupted"
+ tqdm(None, desc=prefix + d, total=n, initial=n) # display cache results
+ if cache['msgs']:
+ LOGGER.info('\n'.join(cache['msgs'])) # display warnings
+ assert nf > 0 or not augment, f'{prefix}No labels in {cache_path}. Can not train without labels. See {HELP_URL}'
+
+ # Read cache
+ [cache.pop(k) for k in ('hash', 'version', 'msgs')] # remove items
+ labels, shapes, self.segments = zip(*cache.values())
+ self.labels = list(labels)
+ self.shapes = np.array(shapes, dtype=np.float64)
+ self.img_files = list(cache.keys()) # update
+ self.label_files = img2label_paths(cache.keys()) # update
+ n = len(shapes) # number of images
+ bi = np.floor(np.arange(n) / batch_size).astype(np.int) # batch index
+ nb = bi[-1] + 1 # number of batches
+ self.batch = bi # batch index of image
+ self.n = n
+ self.indices = range(n)
+
+ # Update labels
+ include_class = [] # filter labels to include only these classes (optional)
+ include_class_array = np.array(include_class).reshape(1, -1)
+ for i, (label, segment) in enumerate(zip(self.labels, self.segments)):
+ if include_class:
+ j = (label[:, 0:1] == include_class_array).any(1)
+ self.labels[i] = label[j]
+ if segment:
+ self.segments[i] = segment[j]
+ if single_cls: # single-class training, merge all classes into 0
+ self.labels[i][:, 0] = 0
+ if segment:
+ self.segments[i][:, 0] = 0
+
+ # Rectangular Training
+ if self.rect:
+ # Sort by aspect ratio
+ s = self.shapes # wh
+ ar = s[:, 1] / s[:, 0] # aspect ratio
+ irect = ar.argsort()
+ self.img_files = [self.img_files[i] for i in irect]
+ self.label_files = [self.label_files[i] for i in irect]
+ self.labels = [self.labels[i] for i in irect]
+ self.shapes = s[irect] # wh
+ ar = ar[irect]
+
+ # Set training image shapes
+ shapes = [[1, 1]] * nb
+ for i in range(nb):
+ ari = ar[bi == i]
+ mini, maxi = ari.min(), ari.max()
+ if maxi < 1:
+ shapes[i] = [maxi, 1]
+ elif mini > 1:
+ shapes[i] = [1, 1 / mini]
+
+ self.batch_shapes = np.ceil(np.array(shapes) * img_size / stride + pad).astype(np.int) * stride
+
+ # Cache images into memory for faster training (WARNING: large datasets may exceed system RAM)
+ self.imgs, self.img_npy = [None] * n, [None] * n
+ if cache_images:
+ if cache_images == 'disk':
+ self.im_cache_dir = Path(Path(self.img_files[0]).parent.as_posix() + '_npy')
+ self.img_npy = [self.im_cache_dir / Path(f).with_suffix('.npy').name for f in self.img_files]
+ self.im_cache_dir.mkdir(parents=True, exist_ok=True)
+ gb = 0 # Gigabytes of cached images
+ self.img_hw0, self.img_hw = [None] * n, [None] * n
+ results = ThreadPool(NUM_THREADS).imap(lambda x: load_image(*x), zip(repeat(self), range(n)))
+ pbar = tqdm(enumerate(results), total=n)
+ for i, x in pbar:
+ if cache_images == 'disk':
+ if not self.img_npy[i].exists():
+ np.save(self.img_npy[i].as_posix(), x[0])
+ gb += self.img_npy[i].stat().st_size
+ else:
+ self.imgs[i], self.img_hw0[i], self.img_hw[i] = x # im, hw_orig, hw_resized = load_image(self, i)
+ gb += self.imgs[i].nbytes
+ pbar.desc = f'{prefix}Caching images ({gb / 1E9:.1f}GB {cache_images})'
+ pbar.close()
+
+ def cache_labels(self, path=Path('./labels.cache'), prefix=''):
+ # Cache dataset labels, check images and read shapes
+ x = {} # dict
+ nm, nf, ne, nc, msgs = 0, 0, 0, 0, [] # number missing, found, empty, corrupt, messages
+ desc = f"{prefix}Scanning '{path.parent / path.stem}' images and labels..."
+ with Pool(NUM_THREADS) as pool:
+ pbar = tqdm(pool.imap(verify_image_label, zip(self.img_files, self.label_files, repeat(prefix))),
+ desc=desc, total=len(self.img_files))
+ for im_file, l, shape, segments, nm_f, nf_f, ne_f, nc_f, msg in pbar:
+ nm += nm_f
+ nf += nf_f
+ ne += ne_f
+ nc += nc_f
+ if im_file:
+ x[im_file] = [l, shape, segments]
+ if msg:
+ msgs.append(msg)
+ pbar.desc = f"{desc}{nf} found, {nm} missing, {ne} empty, {nc} corrupted"
+
+ pbar.close()
+ if msgs:
+ LOGGER.info('\n'.join(msgs))
+ if nf == 0:
+ LOGGER.warning(f'{prefix}WARNING: No labels found in {path}. See {HELP_URL}')
+ x['hash'] = get_hash(self.label_files + self.img_files)
+ x['results'] = nf, nm, ne, nc, len(self.img_files)
+ x['msgs'] = msgs # warnings
+ x['version'] = self.cache_version # cache version
+ try:
+ np.save(path, x) # save cache for next time
+ path.with_suffix('.cache.npy').rename(path) # remove .npy suffix
+ LOGGER.info(f'{prefix}New cache created: {path}')
+ except Exception as e:
+ LOGGER.warning(f'{prefix}WARNING: Cache directory {path.parent} is not writeable: {e}') # not writeable
+ return x
+
+ def __len__(self):
+ return len(self.img_files)
+
+ # def __iter__(self):
+ # self.count = -1
+ # print('ran dataset iter')
+ # #self.shuffled_vector = np.random.permutation(self.nF) if self.augment else np.arange(self.nF)
+ # return self
+
+ def __getitem__(self, index):
+ index = self.indices[index] # linear, shuffled, or image_weights
+
+ hyp = self.hyp
+ mosaic = self.mosaic and random.random() < hyp['mosaic']
+ if mosaic:
+ # Load mosaic
+ img, labels = load_mosaic(self, index)
+ shapes = None
+
+ # MixUp augmentation
+ if random.random() < hyp['mixup']:
+ img, labels = mixup(img, labels, *load_mosaic(self, random.randint(0, self.n - 1)))
+
+ else:
+ # Load image
+ img, (h0, w0), (h, w) = load_image(self, index)
+
+ # Letterbox
+ shape = self.batch_shapes[self.batch[index]] if self.rect else self.img_size # final letterboxed shape
+ img, ratio, pad = letterbox(img, shape, auto=False, scaleup=self.augment)
+ shapes = (h0, w0), ((h / h0, w / w0), pad) # for COCO mAP rescaling
+
+ labels = self.labels[index].copy()
+ if labels.size: # normalized xywh to pixel xyxy format
+ labels[:, 1:] = xywhn2xyxy(labels[:, 1:], ratio[0] * w, ratio[1] * h, padw=pad[0], padh=pad[1])
+
+ if self.augment:
+ img, labels = random_perspective(img, labels,
+ degrees=hyp['degrees'],
+ translate=hyp['translate'],
+ scale=hyp['scale'],
+ shear=hyp['shear'],
+ perspective=hyp['perspective'])
+
+ nl = len(labels) # number of labels
+ if nl:
+ labels[:, 1:5] = xyxy2xywhn(labels[:, 1:5], w=img.shape[1], h=img.shape[0], clip=True, eps=1E-3)
+
+ if self.augment:
+ # Albumentations
+ img, labels = self.albumentations(img, labels)
+ nl = len(labels) # update after albumentations
+
+ # HSV color-space
+ augment_hsv(img, hgain=hyp['hsv_h'], sgain=hyp['hsv_s'], vgain=hyp['hsv_v'])
+
+ # Flip up-down
+ if random.random() < hyp['flipud']:
+ img = np.flipud(img)
+ if nl:
+ labels[:, 2] = 1 - labels[:, 2]
+
+ # Flip left-right
+ if random.random() < hyp['fliplr']:
+ img = np.fliplr(img)
+ if nl:
+ labels[:, 1] = 1 - labels[:, 1]
+
+ # Cutouts
+ # labels = cutout(img, labels, p=0.5)
+
+ labels_out = torch.zeros((nl, 6))
+ if nl:
+ labels_out[:, 1:] = torch.from_numpy(labels)
+
+ # Convert
+ img = img.transpose((2, 0, 1))[::-1] # HWC to CHW, BGR to RGB
+ img = np.ascontiguousarray(img)
+
+ return torch.from_numpy(img), labels_out, self.img_files[index], shapes
+
+ @staticmethod
+ def collate_fn(batch):
+ img, label, path, shapes = zip(*batch) # transposed
+ for i, l in enumerate(label):
+ l[:, 0] = i # add target image index for build_targets()
+ return torch.stack(img, 0), torch.cat(label, 0), path, shapes
+
+ @staticmethod
+ def collate_fn4(batch):
+ img, label, path, shapes = zip(*batch) # transposed
+ n = len(shapes) // 4
+ img4, label4, path4, shapes4 = [], [], path[:n], shapes[:n]
+
+ ho = torch.tensor([[0.0, 0, 0, 1, 0, 0]])
+ wo = torch.tensor([[0.0, 0, 1, 0, 0, 0]])
+ s = torch.tensor([[1, 1, 0.5, 0.5, 0.5, 0.5]]) # scale
+ for i in range(n): # zidane torch.zeros(16,3,720,1280) # BCHW
+ i *= 4
+ if random.random() < 0.5:
+ im = F.interpolate(img[i].unsqueeze(0).float(), scale_factor=2.0, mode='bilinear', align_corners=False)[
+ 0].type(img[i].type())
+ l = label[i]
+ else:
+ im = torch.cat((torch.cat((img[i], img[i + 1]), 1), torch.cat((img[i + 2], img[i + 3]), 1)), 2)
+ l = torch.cat((label[i], label[i + 1] + ho, label[i + 2] + wo, label[i + 3] + ho + wo), 0) * s
+ img4.append(im)
+ label4.append(l)
+
+ for i, l in enumerate(label4):
+ l[:, 0] = i # add target image index for build_targets()
+
+ return torch.stack(img4, 0), torch.cat(label4, 0), path4, shapes4
+
+
+# Ancillary functions --------------------------------------------------------------------------------------------------
+def load_image(self, i):
+ # loads 1 image from dataset index 'i', returns im, original hw, resized hw
+ im = self.imgs[i]
+ if im is None: # not cached in ram
+ npy = self.img_npy[i]
+ if npy and npy.exists(): # load npy
+ im = np.load(npy)
+ else: # read image
+ path = self.img_files[i]
+ im = cv2.imread(path) # BGR
+ assert im is not None, f'Image Not Found {path}'
+ h0, w0 = im.shape[:2] # orig hw
+ r = self.img_size / max(h0, w0) # ratio
+ if r != 1: # if sizes are not equal
+ im = cv2.resize(im, (int(w0 * r), int(h0 * r)),
+ interpolation=cv2.INTER_AREA if r < 1 and not self.augment else cv2.INTER_LINEAR)
+ return im, (h0, w0), im.shape[:2] # im, hw_original, hw_resized
+ else:
+ return self.imgs[i], self.img_hw0[i], self.img_hw[i] # im, hw_original, hw_resized
+
+
+def load_mosaic(self, index):
+ # 4-mosaic loader. Loads 1 image + 3 random images into a 4-image mosaic
+ labels4, segments4 = [], []
+ s = self.img_size
+ yc, xc = (int(random.uniform(-x, 2 * s + x)) for x in self.mosaic_border) # mosaic center x, y
+ indices = [index] + random.choices(self.indices, k=3) # 3 additional image indices
+ random.shuffle(indices)
+ for i, index in enumerate(indices):
+ # Load image
+ img, _, (h, w) = load_image(self, index)
+
+ # place img in img4
+ if i == 0: # top left
+ img4 = np.full((s * 2, s * 2, img.shape[2]), 114, dtype=np.uint8) # base image with 4 tiles
+ x1a, y1a, x2a, y2a = max(xc - w, 0), max(yc - h, 0), xc, yc # xmin, ymin, xmax, ymax (large image)
+ x1b, y1b, x2b, y2b = w - (x2a - x1a), h - (y2a - y1a), w, h # xmin, ymin, xmax, ymax (small image)
+ elif i == 1: # top right
+ x1a, y1a, x2a, y2a = xc, max(yc - h, 0), min(xc + w, s * 2), yc
+ x1b, y1b, x2b, y2b = 0, h - (y2a - y1a), min(w, x2a - x1a), h
+ elif i == 2: # bottom left
+ x1a, y1a, x2a, y2a = max(xc - w, 0), yc, xc, min(s * 2, yc + h)
+ x1b, y1b, x2b, y2b = w - (x2a - x1a), 0, w, min(y2a - y1a, h)
+ elif i == 3: # bottom right
+ x1a, y1a, x2a, y2a = xc, yc, min(xc + w, s * 2), min(s * 2, yc + h)
+ x1b, y1b, x2b, y2b = 0, 0, min(w, x2a - x1a), min(y2a - y1a, h)
+
+ img4[y1a:y2a, x1a:x2a] = img[y1b:y2b, x1b:x2b] # img4[ymin:ymax, xmin:xmax]
+ padw = x1a - x1b
+ padh = y1a - y1b
+
+ # Labels
+ labels, segments = self.labels[index].copy(), self.segments[index].copy()
+ if labels.size:
+ labels[:, 1:] = xywhn2xyxy(labels[:, 1:], w, h, padw, padh) # normalized xywh to pixel xyxy format
+ segments = [xyn2xy(x, w, h, padw, padh) for x in segments]
+ labels4.append(labels)
+ segments4.extend(segments)
+
+ # Concat/clip labels
+ labels4 = np.concatenate(labels4, 0)
+ for x in (labels4[:, 1:], *segments4):
+ np.clip(x, 0, 2 * s, out=x) # clip when using random_perspective()
+ # img4, labels4 = replicate(img4, labels4) # replicate
+
+ # Augment
+ img4, labels4, segments4 = copy_paste(img4, labels4, segments4, p=self.hyp['copy_paste'])
+ img4, labels4 = random_perspective(img4, labels4, segments4,
+ degrees=self.hyp['degrees'],
+ translate=self.hyp['translate'],
+ scale=self.hyp['scale'],
+ shear=self.hyp['shear'],
+ perspective=self.hyp['perspective'],
+ border=self.mosaic_border) # border to remove
+
+ return img4, labels4
+
+
+def load_mosaic9(self, index):
+ # 9-mosaic loader. Loads 1 image + 8 random images into a 9-image mosaic
+ labels9, segments9 = [], []
+ s = self.img_size
+ indices = [index] + random.choices(self.indices, k=8) # 8 additional image indices
+ random.shuffle(indices)
+ for i, index in enumerate(indices):
+ # Load image
+ img, _, (h, w) = load_image(self, index)
+
+ # place img in img9
+ if i == 0: # center
+ img9 = np.full((s * 3, s * 3, img.shape[2]), 114, dtype=np.uint8) # base image with 4 tiles
+ h0, w0 = h, w
+ c = s, s, s + w, s + h # xmin, ymin, xmax, ymax (base) coordinates
+ elif i == 1: # top
+ c = s, s - h, s + w, s
+ elif i == 2: # top right
+ c = s + wp, s - h, s + wp + w, s
+ elif i == 3: # right
+ c = s + w0, s, s + w0 + w, s + h
+ elif i == 4: # bottom right
+ c = s + w0, s + hp, s + w0 + w, s + hp + h
+ elif i == 5: # bottom
+ c = s + w0 - w, s + h0, s + w0, s + h0 + h
+ elif i == 6: # bottom left
+ c = s + w0 - wp - w, s + h0, s + w0 - wp, s + h0 + h
+ elif i == 7: # left
+ c = s - w, s + h0 - h, s, s + h0
+ elif i == 8: # top left
+ c = s - w, s + h0 - hp - h, s, s + h0 - hp
+
+ padx, pady = c[:2]
+ x1, y1, x2, y2 = (max(x, 0) for x in c) # allocate coords
+
+ # Labels
+ labels, segments = self.labels[index].copy(), self.segments[index].copy()
+ if labels.size:
+ labels[:, 1:] = xywhn2xyxy(labels[:, 1:], w, h, padx, pady) # normalized xywh to pixel xyxy format
+ segments = [xyn2xy(x, w, h, padx, pady) for x in segments]
+ labels9.append(labels)
+ segments9.extend(segments)
+
+ # Image
+ img9[y1:y2, x1:x2] = img[y1 - pady:, x1 - padx:] # img9[ymin:ymax, xmin:xmax]
+ hp, wp = h, w # height, width previous
+
+ # Offset
+ yc, xc = (int(random.uniform(0, s)) for _ in self.mosaic_border) # mosaic center x, y
+ img9 = img9[yc:yc + 2 * s, xc:xc + 2 * s]
+
+ # Concat/clip labels
+ labels9 = np.concatenate(labels9, 0)
+ labels9[:, [1, 3]] -= xc
+ labels9[:, [2, 4]] -= yc
+ c = np.array([xc, yc]) # centers
+ segments9 = [x - c for x in segments9]
+
+ for x in (labels9[:, 1:], *segments9):
+ np.clip(x, 0, 2 * s, out=x) # clip when using random_perspective()
+ # img9, labels9 = replicate(img9, labels9) # replicate
+
+ # Augment
+ img9, labels9 = random_perspective(img9, labels9, segments9,
+ degrees=self.hyp['degrees'],
+ translate=self.hyp['translate'],
+ scale=self.hyp['scale'],
+ shear=self.hyp['shear'],
+ perspective=self.hyp['perspective'],
+ border=self.mosaic_border) # border to remove
+
+ return img9, labels9
+
+
+def create_folder(path='./new'):
+ # Create folder
+ if os.path.exists(path):
+ shutil.rmtree(path) # delete output folder
+ os.makedirs(path) # make new output folder
+
+
+def flatten_recursive(path='../datasets/coco128'):
+ # Flatten a recursive directory by bringing all files to top level
+ new_path = Path(path + '_flat')
+ create_folder(new_path)
+ for file in tqdm(glob.glob(str(Path(path)) + '/**/*.*', recursive=True)):
+ shutil.copyfile(file, new_path / Path(file).name)
+
+
+def extract_boxes(path='../datasets/coco128'): # from utils.datasets import *; extract_boxes()
+ # Convert detection dataset into classification dataset, with one directory per class
+ path = Path(path) # images dir
+ shutil.rmtree(path / 'classifier') if (path / 'classifier').is_dir() else None # remove existing
+ files = list(path.rglob('*.*'))
+ n = len(files) # number of files
+ for im_file in tqdm(files, total=n):
+ if im_file.suffix[1:] in IMG_FORMATS:
+ # image
+ im = cv2.imread(str(im_file))[..., ::-1] # BGR to RGB
+ h, w = im.shape[:2]
+
+ # labels
+ lb_file = Path(img2label_paths([str(im_file)])[0])
+ if Path(lb_file).exists():
+ with open(lb_file) as f:
+ lb = np.array([x.split() for x in f.read().strip().splitlines()], dtype=np.float32) # labels
+
+ for j, x in enumerate(lb):
+ c = int(x[0]) # class
+ f = (path / 'classifier') / f'{c}' / f'{path.stem}_{im_file.stem}_{j}.jpg' # new filename
+ if not f.parent.is_dir():
+ f.parent.mkdir(parents=True)
+
+ b = x[1:] * [w, h, w, h] # box
+ # b[2:] = b[2:].max() # rectangle to square
+ b[2:] = b[2:] * 1.2 + 3 # pad
+ b = xywh2xyxy(b.reshape(-1, 4)).ravel().astype(np.int)
+
+ b[[0, 2]] = np.clip(b[[0, 2]], 0, w) # clip boxes outside of image
+ b[[1, 3]] = np.clip(b[[1, 3]], 0, h)
+ assert cv2.imwrite(str(f), im[b[1]:b[3], b[0]:b[2]]), f'box failure in {f}'
+
+
+def autosplit(path='../datasets/coco128/images', weights=(0.9, 0.1, 0.0), annotated_only=False):
+ """ Autosplit a dataset into train/val/test splits and save path/autosplit_*.txt files
+ Usage: from utils.datasets import *; autosplit()
+ Arguments
+ path: Path to images directory
+ weights: Train, val, test weights (list, tuple)
+ annotated_only: Only use images with an annotated txt file
+ """
+ path = Path(path) # images dir
+ files = sorted(x for x in path.rglob('*.*') if x.suffix[1:].lower() in IMG_FORMATS) # image files only
+ n = len(files) # number of files
+ random.seed(0) # for reproducibility
+ indices = random.choices([0, 1, 2], weights=weights, k=n) # assign each image to a split
+
+ txt = ['autosplit_train.txt', 'autosplit_val.txt', 'autosplit_test.txt'] # 3 txt files
+ [(path.parent / x).unlink(missing_ok=True) for x in txt] # remove existing
+
+ print(f'Autosplitting images from {path}' + ', using *.txt labeled images only' * annotated_only)
+ for i, img in tqdm(zip(indices, files), total=n):
+ if not annotated_only or Path(img2label_paths([str(img)])[0]).exists(): # check label
+ with open(path.parent / txt[i], 'a') as f:
+ f.write('./' + img.relative_to(path.parent).as_posix() + '\n') # add image to txt file
+
+
+def verify_image_label(args):
+ # Verify one image-label pair
+ im_file, lb_file, prefix = args
+ nm, nf, ne, nc, msg, segments = 0, 0, 0, 0, '', [] # number (missing, found, empty, corrupt), message, segments
+ try:
+ # verify images
+ im = Image.open(im_file)
+ im.verify() # PIL verify
+ shape = exif_size(im) # image size
+ assert (shape[0] > 9) & (shape[1] > 9), f'image size {shape} <10 pixels'
+ assert im.format.lower() in IMG_FORMATS, f'invalid image format {im.format}'
+ if im.format.lower() in ('jpg', 'jpeg'):
+ with open(im_file, 'rb') as f:
+ f.seek(-2, 2)
+ if f.read() != b'\xff\xd9': # corrupt JPEG
+ ImageOps.exif_transpose(Image.open(im_file)).save(im_file, 'JPEG', subsampling=0, quality=100)
+ msg = f'{prefix}WARNING: {im_file}: corrupt JPEG restored and saved'
+
+ # verify labels
+ if os.path.isfile(lb_file):
+ nf = 1 # label found
+ with open(lb_file) as f:
+ l = [x.split() for x in f.read().strip().splitlines() if len(x)]
+ if any([len(x) > 8 for x in l]): # is segment
+ classes = np.array([x[0] for x in l], dtype=np.float32)
+ segments = [np.array(x[1:], dtype=np.float32).reshape(-1, 2) for x in l] # (cls, xy1...)
+ l = np.concatenate((classes.reshape(-1, 1), segments2boxes(segments)), 1) # (cls, xywh)
+ l = np.array(l, dtype=np.float32)
+ nl = len(l)
+ if nl:
+ assert l.shape[1] == 5, f'labels require 5 columns, {l.shape[1]} columns detected'
+ assert (l >= 0).all(), f'negative label values {l[l < 0]}'
+ assert (l[:, 1:] <= 1).all(), f'non-normalized or out of bounds coordinates {l[:, 1:][l[:, 1:] > 1]}'
+ _, i = np.unique(l, axis=0, return_index=True)
+ if len(i) < nl: # duplicate row check
+ l = l[i] # remove duplicates
+ if segments:
+ segments = segments[i]
+ msg = f'{prefix}WARNING: {im_file}: {nl - len(i)} duplicate labels removed'
+ else:
+ ne = 1 # label empty
+ l = np.zeros((0, 5), dtype=np.float32)
+ else:
+ nm = 1 # label missing
+ l = np.zeros((0, 5), dtype=np.float32)
+ return im_file, l, shape, segments, nm, nf, ne, nc, msg
+ except Exception as e:
+ nc = 1
+ msg = f'{prefix}WARNING: {im_file}: ignoring corrupt image/label: {e}'
+ return [None, None, None, None, nm, nf, ne, nc, msg]
+
+
+def dataset_stats(path='coco128.yaml', autodownload=False, verbose=False, profile=False, hub=False):
+ """ Return dataset statistics dictionary with images and instances counts per split per class
+ To run in parent directory: export PYTHONPATH="$PWD/yolov3"
+ Usage1: from utils.datasets import *; dataset_stats('coco128.yaml', autodownload=True)
+ Usage2: from utils.datasets import *; dataset_stats('../datasets/coco128_with_yaml.zip')
+ Arguments
+ path: Path to data.yaml or data.zip (with data.yaml inside data.zip)
+ autodownload: Attempt to download dataset if not found locally
+ verbose: Print stats dictionary
+ """
+
+ def round_labels(labels):
+ # Update labels to integer class and 6 decimal place floats
+ return [[int(c), *(round(x, 4) for x in points)] for c, *points in labels]
+
+ def unzip(path):
+ # Unzip data.zip TODO: CONSTRAINT: path/to/abc.zip MUST unzip to 'path/to/abc/'
+ if str(path).endswith('.zip'): # path is data.zip
+ assert Path(path).is_file(), f'Error unzipping {path}, file not found'
+ ZipFile(path).extractall(path=path.parent) # unzip
+ dir = path.with_suffix('') # dataset directory == zip name
+ return True, str(dir), next(dir.rglob('*.yaml')) # zipped, data_dir, yaml_path
+ else: # path is data.yaml
+ return False, None, path
+
+ def hub_ops(f, max_dim=1920):
+ # HUB ops for 1 image 'f': resize and save at reduced quality in /dataset-hub for web/app viewing
+ f_new = im_dir / Path(f).name # dataset-hub image filename
+ try: # use PIL
+ im = Image.open(f)
+ r = max_dim / max(im.height, im.width) # ratio
+ if r < 1.0: # image too large
+ im = im.resize((int(im.width * r), int(im.height * r)))
+ im.save(f_new, 'JPEG', quality=75, optimize=True) # save
+ except Exception as e: # use OpenCV
+ print(f'WARNING: HUB ops PIL failure {f}: {e}')
+ im = cv2.imread(f)
+ im_height, im_width = im.shape[:2]
+ r = max_dim / max(im_height, im_width) # ratio
+ if r < 1.0: # image too large
+ im = cv2.resize(im, (int(im_width * r), int(im_height * r)), interpolation=cv2.INTER_LINEAR)
+ cv2.imwrite(str(f_new), im)
+
+ zipped, data_dir, yaml_path = unzip(Path(path))
+ with open(check_yaml(yaml_path), errors='ignore') as f:
+ data = yaml.safe_load(f) # data dict
+ if zipped:
+ data['path'] = data_dir # TODO: should this be dir.resolve()?
+ check_dataset(data, autodownload) # download dataset if missing
+ hub_dir = Path(data['path'] + ('-hub' if hub else ''))
+ stats = {'nc': data['nc'], 'names': data['names']} # statistics dictionary
+ for split in 'train', 'val', 'test':
+ if data.get(split) is None:
+ stats[split] = None # i.e. no test set
+ continue
+ x = []
+ dataset = LoadImagesAndLabels(data[split]) # load dataset
+ for label in tqdm(dataset.labels, total=dataset.n, desc='Statistics'):
+ x.append(np.bincount(label[:, 0].astype(int), minlength=data['nc']))
+ x = np.array(x) # shape(128x80)
+ stats[split] = {'instance_stats': {'total': int(x.sum()), 'per_class': x.sum(0).tolist()},
+ 'image_stats': {'total': dataset.n, 'unlabelled': int(np.all(x == 0, 1).sum()),
+ 'per_class': (x > 0).sum(0).tolist()},
+ 'labels': [{str(Path(k).name): round_labels(v.tolist())} for k, v in
+ zip(dataset.img_files, dataset.labels)]}
+
+ if hub:
+ im_dir = hub_dir / 'images'
+ im_dir.mkdir(parents=True, exist_ok=True)
+ for _ in tqdm(ThreadPool(NUM_THREADS).imap(hub_ops, dataset.img_files), total=dataset.n, desc='HUB Ops'):
+ pass
+
+ # Profile
+ stats_path = hub_dir / 'stats.json'
+ if profile:
+ for _ in range(1):
+ file = stats_path.with_suffix('.npy')
+ t1 = time.time()
+ np.save(file, stats)
+ t2 = time.time()
+ x = np.load(file, allow_pickle=True)
+ print(f'stats.npy times: {time.time() - t2:.3f}s read, {t2 - t1:.3f}s write')
+
+ file = stats_path.with_suffix('.json')
+ t1 = time.time()
+ with open(file, 'w') as f:
+ json.dump(stats, f) # save stats *.json
+ t2 = time.time()
+ with open(file) as f:
+ x = json.load(f) # load hyps dict
+ print(f'stats.json times: {time.time() - t2:.3f}s read, {t2 - t1:.3f}s write')
+
+ # Save, print and return
+ if hub:
+ print(f'Saving {stats_path.resolve()}...')
+ with open(stats_path, 'w') as f:
+ json.dump(stats, f) # save stats.json
+ if verbose:
+ print(json.dumps(stats, indent=2, sort_keys=False))
+ return stats
diff --git a/ros2_ws/src/yolov3_ros/utils/docker/Dockerfile b/ros2_ws/src/yolov3_ros/utils/docker/Dockerfile
new file mode 100644
index 00000000..a83e664c
--- /dev/null
+++ b/ros2_ws/src/yolov3_ros/utils/docker/Dockerfile
@@ -0,0 +1,75 @@
+# YOLOv3 🚀 by Ultralytics, GPL-3.0 license
+# Builds ultralytics/yolov5:latest image on DockerHub https://hub.docker.com/r/ultralytics/yolov3
+# Image is CUDA-optimized for YOLOv5 single/multi-GPU training and inference
+
+# Start FROM NVIDIA PyTorch image https://ngc.nvidia.com/catalog/containers/nvidia:pytorch
+# FROM docker.io/pytorch/pytorch:latest
+FROM pytorch/pytorch:latest
+
+# Downloads to user config dir
+ADD https://ultralytics.com/assets/Arial.ttf https://ultralytics.com/assets/Arial.Unicode.ttf /root/.config/Ultralytics/
+
+# Install linux packages
+ENV DEBIAN_FRONTEND noninteractive
+RUN apt update
+RUN TZ=Etc/UTC apt install -y tzdata
+RUN apt install --no-install-recommends -y gcc git zip curl htop libgl1-mesa-glx libglib2.0-0 libpython3-dev gnupg
+# RUN alias python=python3
+
+# Security updates
+# https://security.snyk.io/vuln/SNYK-UBUNTU1804-OPENSSL-3314796
+RUN apt upgrade --no-install-recommends -y openssl
+
+# Create working directory
+RUN rm -rf /usr/src/app && mkdir -p /usr/src/app
+WORKDIR /usr/src/app
+
+# Copy contents
+# COPY . /usr/src/app (issues as not a .git directory)
+RUN git clone https://github.com/ultralytics/yolov5 /usr/src/app
+
+# Install pip packages
+COPY requirements.txt .
+RUN python3 -m pip install --upgrade pip wheel
+RUN pip install --no-cache -r requirements.txt albumentations comet gsutil notebook \
+ coremltools onnx onnx-simplifier onnxruntime 'openvino-dev>=2022.3'
+ # tensorflow tensorflowjs \
+
+# Set environment variables
+ENV OMP_NUM_THREADS=1
+
+# Cleanup
+ENV DEBIAN_FRONTEND teletype
+
+
+# Usage Examples -------------------------------------------------------------------------------------------------------
+
+# Build and Push
+# t=ultralytics/yolov5:latest && sudo docker build -f utils/docker/Dockerfile -t $t . && sudo docker push $t
+
+# Pull and Run
+# t=ultralytics/yolov5:latest && sudo docker pull $t && sudo docker run -it --ipc=host --gpus all $t
+
+# Pull and Run with local directory access
+# t=ultralytics/yolov5:latest && sudo docker pull $t && sudo docker run -it --ipc=host --gpus all -v "$(pwd)"/datasets:/usr/src/datasets $t
+
+# Kill all
+# sudo docker kill $(sudo docker ps -q)
+
+# Kill all image-based
+# sudo docker kill $(sudo docker ps -qa --filter ancestor=ultralytics/yolov5:latest)
+
+# DockerHub tag update
+# t=ultralytics/yolov5:latest tnew=ultralytics/yolov5:v6.2 && sudo docker pull $t && sudo docker tag $t $tnew && sudo docker push $tnew
+
+# Clean up
+# sudo docker system prune -a --volumes
+
+# Update Ubuntu drivers
+# https://www.maketecheasier.com/install-nvidia-drivers-ubuntu/
+
+# DDP test
+# python -m torch.distributed.run --nproc_per_node 2 --master_port 1 train.py --epochs 3
+
+# GCP VM from Image
+# docker.io/ultralytics/yolov5:latest
diff --git a/ros2_ws/src/yolov3_ros/utils/docker/Dockerfile-arm64 b/ros2_ws/src/yolov3_ros/utils/docker/Dockerfile-arm64
new file mode 100644
index 00000000..31c2eaf8
--- /dev/null
+++ b/ros2_ws/src/yolov3_ros/utils/docker/Dockerfile-arm64
@@ -0,0 +1,41 @@
+# YOLOv3 🚀 by Ultralytics, GPL-3.0 license
+# Builds ultralytics/yolov5:latest-arm64 image on DockerHub https://hub.docker.com/r/ultralytics/yolov3
+# Image is aarch64-compatible for Apple M1 and other ARM architectures i.e. Jetson Nano and Raspberry Pi
+
+# Start FROM Ubuntu image https://hub.docker.com/_/ubuntu
+FROM arm64v8/ubuntu:rolling
+
+# Downloads to user config dir
+ADD https://ultralytics.com/assets/Arial.ttf https://ultralytics.com/assets/Arial.Unicode.ttf /root/.config/Ultralytics/
+
+# Install linux packages
+ENV DEBIAN_FRONTEND noninteractive
+RUN apt update
+RUN TZ=Etc/UTC apt install -y tzdata
+RUN apt install --no-install-recommends -y python3-pip git zip curl htop gcc libgl1-mesa-glx libglib2.0-0 libpython3-dev
+# RUN alias python=python3
+
+# Install pip packages
+COPY requirements.txt .
+RUN python3 -m pip install --upgrade pip wheel
+RUN pip install --no-cache -r requirements.txt albumentations gsutil notebook \
+ coremltools onnx onnxruntime
+ # tensorflow-aarch64 tensorflowjs \
+
+# Create working directory
+RUN mkdir -p /usr/src/app
+WORKDIR /usr/src/app
+
+# Copy contents
+# COPY . /usr/src/app (issues as not a .git directory)
+RUN git clone https://github.com/ultralytics/yolov5 /usr/src/app
+ENV DEBIAN_FRONTEND teletype
+
+
+# Usage Examples -------------------------------------------------------------------------------------------------------
+
+# Build and Push
+# t=ultralytics/yolov5:latest-arm64 && sudo docker build --platform linux/arm64 -f utils/docker/Dockerfile-arm64 -t $t . && sudo docker push $t
+
+# Pull and Run
+# t=ultralytics/yolov5:latest-arm64 && sudo docker pull $t && sudo docker run -it --ipc=host -v "$(pwd)"/datasets:/usr/src/datasets $t
diff --git a/ros2_ws/src/yolov3_ros/utils/docker/Dockerfile-cpu b/ros2_ws/src/yolov3_ros/utils/docker/Dockerfile-cpu
new file mode 100644
index 00000000..8e27bf61
--- /dev/null
+++ b/ros2_ws/src/yolov3_ros/utils/docker/Dockerfile-cpu
@@ -0,0 +1,42 @@
+# YOLOv3 🚀 by Ultralytics, GPL-3.0 license
+# Builds ultralytics/yolov5:latest-cpu image on DockerHub https://hub.docker.com/r/ultralytics/yolov3
+# Image is CPU-optimized for ONNX, OpenVINO and PyTorch YOLOv5 deployments
+
+# Start FROM Ubuntu image https://hub.docker.com/_/ubuntu
+FROM ubuntu:rolling
+
+# Downloads to user config dir
+ADD https://ultralytics.com/assets/Arial.ttf https://ultralytics.com/assets/Arial.Unicode.ttf /root/.config/Ultralytics/
+
+# Install linux packages
+ENV DEBIAN_FRONTEND noninteractive
+RUN apt update
+RUN TZ=Etc/UTC apt install -y tzdata
+RUN apt install --no-install-recommends -y python3-pip git zip curl htop libgl1-mesa-glx libglib2.0-0 libpython3-dev gnupg
+# RUN alias python=python3
+
+# Install pip packages
+COPY requirements.txt .
+RUN python3 -m pip install --upgrade pip wheel
+RUN pip install --no-cache -r requirements.txt albumentations gsutil notebook \
+ coremltools onnx onnx-simplifier onnxruntime 'openvino-dev>=2022.3' \
+ # tensorflow tensorflowjs \
+ --extra-index-url https://download.pytorch.org/whl/cpu
+
+# Create working directory
+RUN mkdir -p /usr/src/app
+WORKDIR /usr/src/app
+
+# Copy contents
+# COPY . /usr/src/app (issues as not a .git directory)
+RUN git clone https://github.com/ultralytics/yolov5 /usr/src/app
+ENV DEBIAN_FRONTEND teletype
+
+
+# Usage Examples -------------------------------------------------------------------------------------------------------
+
+# Build and Push
+# t=ultralytics/yolov5:latest-cpu && sudo docker build -f utils/docker/Dockerfile-cpu -t $t . && sudo docker push $t
+
+# Pull and Run
+# t=ultralytics/yolov5:latest-cpu && sudo docker pull $t && sudo docker run -it --ipc=host -v "$(pwd)"/datasets:/usr/src/datasets $t
diff --git a/ros2_ws/src/yolov3_ros/utils/downloads.py b/ros2_ws/src/yolov3_ros/utils/downloads.py
new file mode 100644
index 00000000..cd653078
--- /dev/null
+++ b/ros2_ws/src/yolov3_ros/utils/downloads.py
@@ -0,0 +1,149 @@
+# YOLOv3 🚀 by Ultralytics, GPL-3.0 license
+"""
+Download utils
+"""
+
+import os
+import platform
+import subprocess
+import time
+import urllib
+from pathlib import Path
+from zipfile import ZipFile
+
+import requests
+import torch
+
+
+def gsutil_getsize(url=''):
+ # gs://bucket/file size https://cloud.google.com/storage/docs/gsutil/commands/du
+ s = subprocess.check_output(f'gsutil du {url}', shell=True).decode('utf-8')
+ return eval(s.split(' ')[0]) if len(s) else 0 # bytes
+
+
+def safe_download(file, url, url2=None, min_bytes=1E0, error_msg=''):
+ # Attempts to download file from url or url2, checks and removes incomplete downloads < min_bytes
+ file = Path(file)
+ assert_msg = f"Downloaded file '{file}' does not exist or size is < min_bytes={min_bytes}"
+ try: # url1
+ print(f'Downloading {url} to {file}...')
+ torch.hub.download_url_to_file(url, str(file))
+ assert file.exists() and file.stat().st_size > min_bytes, assert_msg # check
+ except Exception as e: # url2
+ file.unlink(missing_ok=True) # remove partial downloads
+ print(f'ERROR: {e}\nRe-attempting {url2 or url} to {file}...')
+ os.system(f"curl -L '{url2 or url}' -o '{file}' --retry 3 -C -") # curl download, retry and resume on fail
+ finally:
+ if not file.exists() or file.stat().st_size < min_bytes: # check
+ file.unlink(missing_ok=True) # remove partial downloads
+ print(f"ERROR: {assert_msg}\n{error_msg}")
+ print('')
+
+
+def attempt_download(file, repo='ultralytics/yolov3'): # from utils.downloads import *; attempt_download()
+ # Attempt file download if does not exist
+ file = Path(str(file).strip().replace("'", ''))
+
+ if not file.exists():
+ # URL specified
+ name = Path(urllib.parse.unquote(str(file))).name # decode '%2F' to '/' etc.
+ if str(file).startswith(('http:/', 'https:/')): # download
+ url = str(file).replace(':/', '://') # Pathlib turns :// -> :/
+ name = name.split('?')[0] # parse authentication https://url.com/file.txt?auth...
+ safe_download(file=name, url=url, min_bytes=1E5)
+ return name
+
+ # GitHub assets
+ file.parent.mkdir(parents=True, exist_ok=True) # make parent dir (if required)
+ try:
+ response = requests.get(f'https://api.github.com/repos/{repo}/releases/latest').json() # github api
+ assets = [x['name'] for x in response['assets']] # release assets, i.e. ['yolov3.pt'...]
+ tag = response['tag_name'] # i.e. 'v1.0'
+ except: # fallback plan
+ assets = ['yolov3.pt', 'yolov3-spp.pt', 'yolov3-tiny.pt']
+ try:
+ tag = subprocess.check_output('git tag', shell=True, stderr=subprocess.STDOUT).decode().split()[-1]
+ except:
+ tag = 'v9.5.0' # current release
+
+ if name in assets:
+ safe_download(file,
+ url=f'https://github.com/{repo}/releases/download/{tag}/{name}',
+ # url2=f'https://storage.googleapis.com/{repo}/ckpt/{name}', # backup url (optional)
+ min_bytes=1E5,
+ error_msg=f'{file} missing, try downloading from https://github.com/{repo}/releases/')
+
+ return str(file)
+
+
+def gdrive_download(id='16TiPfZj7htmTyhntwcZyEEAejOUxuT6m', file='tmp.zip'):
+ # Downloads a file from Google Drive. from yolov3.utils.downloads import *; gdrive_download()
+ t = time.time()
+ file = Path(file)
+ cookie = Path('cookie') # gdrive cookie
+ print(f'Downloading https://drive.google.com/uc?export=download&id={id} as {file}... ', end='')
+ file.unlink(missing_ok=True) # remove existing file
+ cookie.unlink(missing_ok=True) # remove existing cookie
+
+ # Attempt file download
+ out = "NUL" if platform.system() == "Windows" else "/dev/null"
+ os.system(f'curl -c ./cookie -s -L "drive.google.com/uc?export=download&id={id}" > {out}')
+ if os.path.exists('cookie'): # large file
+ s = f'curl -Lb ./cookie "drive.google.com/uc?export=download&confirm={get_token()}&id={id}" -o {file}'
+ else: # small file
+ s = f'curl -s -L -o {file} "drive.google.com/uc?export=download&id={id}"'
+ r = os.system(s) # execute, capture return
+ cookie.unlink(missing_ok=True) # remove existing cookie
+
+ # Error check
+ if r != 0:
+ file.unlink(missing_ok=True) # remove partial
+ print('Download error ') # raise Exception('Download error')
+ return r
+
+ # Unzip if archive
+ if file.suffix == '.zip':
+ print('unzipping... ', end='')
+ ZipFile(file).extractall(path=file.parent) # unzip
+ file.unlink() # remove zip
+
+ print(f'Done ({time.time() - t:.1f}s)')
+ return r
+
+
+def get_token(cookie="./cookie"):
+ with open(cookie) as f:
+ for line in f:
+ if "download" in line:
+ return line.split()[-1]
+ return ""
+
+# Google utils: https://cloud.google.com/storage/docs/reference/libraries ----------------------------------------------
+#
+#
+# def upload_blob(bucket_name, source_file_name, destination_blob_name):
+# # Uploads a file to a bucket
+# # https://cloud.google.com/storage/docs/uploading-objects#storage-upload-object-python
+#
+# storage_client = storage.Client()
+# bucket = storage_client.get_bucket(bucket_name)
+# blob = bucket.blob(destination_blob_name)
+#
+# blob.upload_from_filename(source_file_name)
+#
+# print('File {} uploaded to {}.'.format(
+# source_file_name,
+# destination_blob_name))
+#
+#
+# def download_blob(bucket_name, source_blob_name, destination_file_name):
+# # Uploads a blob from a bucket
+# storage_client = storage.Client()
+# bucket = storage_client.get_bucket(bucket_name)
+# blob = bucket.blob(source_blob_name)
+#
+# blob.download_to_filename(destination_file_name)
+#
+# print('Blob {} downloaded to {}.'.format(
+# source_blob_name,
+# destination_file_name))
diff --git a/ros2_ws/src/yolov3_ros/utils/flask_rest_api/README.md b/ros2_ws/src/yolov3_ros/utils/flask_rest_api/README.md
new file mode 100644
index 00000000..a726acbd
--- /dev/null
+++ b/ros2_ws/src/yolov3_ros/utils/flask_rest_api/README.md
@@ -0,0 +1,73 @@
+# Flask REST API
+
+[REST](https://en.wikipedia.org/wiki/Representational_state_transfer) [API](https://en.wikipedia.org/wiki/API)s are
+commonly used to expose Machine Learning (ML) models to other services. This folder contains an example REST API
+created using Flask to expose the YOLOv5s model from [PyTorch Hub](https://pytorch.org/hub/ultralytics_yolov5/).
+
+## Requirements
+
+[Flask](https://palletsprojects.com/p/flask/) is required. Install with:
+
+```shell
+$ pip install Flask
+```
+
+## Run
+
+After Flask installation run:
+
+```shell
+$ python3 restapi.py --port 5000
+```
+
+Then use [curl](https://curl.se/) to perform a request:
+
+```shell
+$ curl -X POST -F image=@zidane.jpg 'http://localhost:5000/v1/object-detection/yolov5s'
+```
+
+The model inference results are returned as a JSON response:
+
+```json
+[
+ {
+ "class": 0,
+ "confidence": 0.8900438547,
+ "height": 0.9318675399,
+ "name": "person",
+ "width": 0.3264600933,
+ "xcenter": 0.7438579798,
+ "ycenter": 0.5207948685
+ },
+ {
+ "class": 0,
+ "confidence": 0.8440024257,
+ "height": 0.7155083418,
+ "name": "person",
+ "width": 0.6546785235,
+ "xcenter": 0.427829951,
+ "ycenter": 0.6334488392
+ },
+ {
+ "class": 27,
+ "confidence": 0.3771208823,
+ "height": 0.3902671337,
+ "name": "tie",
+ "width": 0.0696444362,
+ "xcenter": 0.3675483763,
+ "ycenter": 0.7991207838
+ },
+ {
+ "class": 27,
+ "confidence": 0.3527112305,
+ "height": 0.1540903747,
+ "name": "tie",
+ "width": 0.0336618312,
+ "xcenter": 0.7814827561,
+ "ycenter": 0.5065554976
+ }
+]
+```
+
+An example python script to perform inference using [requests](https://docs.python-requests.org/en/master/) is given
+in `example_request.py`
diff --git a/ros2_ws/src/yolov3_ros/utils/flask_rest_api/example_request.py b/ros2_ws/src/yolov3_ros/utils/flask_rest_api/example_request.py
new file mode 100644
index 00000000..5e6d0c1d
--- /dev/null
+++ b/ros2_ws/src/yolov3_ros/utils/flask_rest_api/example_request.py
@@ -0,0 +1,19 @@
+# YOLOv3 🚀 by Ultralytics, GPL-3.0 license
+"""
+Perform test request
+"""
+
+import pprint
+
+import requests
+
+DETECTION_URL = 'http://localhost:5000/v1/object-detection/yolov5s'
+IMAGE = 'zidane.jpg'
+
+# Read image
+with open(IMAGE, 'rb') as f:
+ image_data = f.read()
+
+response = requests.post(DETECTION_URL, files={'image': image_data}).json()
+
+pprint.pprint(response)
diff --git a/ros2_ws/src/yolov3_ros/utils/flask_rest_api/restapi.py b/ros2_ws/src/yolov3_ros/utils/flask_rest_api/restapi.py
new file mode 100644
index 00000000..5d8f5996
--- /dev/null
+++ b/ros2_ws/src/yolov3_ros/utils/flask_rest_api/restapi.py
@@ -0,0 +1,48 @@
+# YOLOv3 🚀 by Ultralytics, GPL-3.0 license
+"""
+Run a Flask REST API exposing one or more YOLOv5s models
+"""
+
+import argparse
+import io
+
+import torch
+from flask import Flask, request
+from PIL import Image
+
+app = Flask(__name__)
+models = {}
+
+DETECTION_URL = '/v1/object-detection/'
+
+
+@app.route(DETECTION_URL, methods=['POST'])
+def predict(model):
+ if request.method != 'POST':
+ return
+
+ if request.files.get('image'):
+ # Method 1
+ # with request.files["image"] as f:
+ # im = Image.open(io.BytesIO(f.read()))
+
+ # Method 2
+ im_file = request.files['image']
+ im_bytes = im_file.read()
+ im = Image.open(io.BytesIO(im_bytes))
+
+ if model in models:
+ results = models[model](im, size=640) # reduce size=320 for faster inference
+ return results.pandas().xyxy[0].to_json(orient='records')
+
+
+if __name__ == '__main__':
+ parser = argparse.ArgumentParser(description='Flask API exposing YOLOv5 model')
+ parser.add_argument('--port', default=5000, type=int, help='port number')
+ parser.add_argument('--model', nargs='+', default=['yolov5s'], help='model(s) to run, i.e. --model yolov5n yolov5s')
+ opt = parser.parse_args()
+
+ for m in opt.model:
+ models[m] = torch.hub.load('ultralytics/yolov5', m, force_reload=True, skip_validation=True)
+
+ app.run(host='0.0.0.0', port=opt.port) # debug=True causes Restarting with stat
diff --git a/ros2_ws/src/yolov3_ros/utils/general.py b/ros2_ws/src/yolov3_ros/utils/general.py
new file mode 100755
index 00000000..8331e7db
--- /dev/null
+++ b/ros2_ws/src/yolov3_ros/utils/general.py
@@ -0,0 +1,841 @@
+# YOLOv3 🚀 by Ultralytics, GPL-3.0 license
+"""
+General utils
+"""
+
+import contextlib
+import glob
+import logging
+import math
+import os
+import platform
+import random
+import re
+import shutil
+import signal
+import time
+import urllib
+from itertools import repeat
+from multiprocessing.pool import ThreadPool
+from pathlib import Path
+from subprocess import check_output
+from zipfile import ZipFile
+
+import cv2
+import numpy as np
+import pandas as pd
+import pkg_resources as pkg
+import torch
+import torchvision
+import yaml
+
+from utils.downloads import gsutil_getsize
+from utils.metrics import box_iou, fitness
+
+# Settings
+torch.set_printoptions(linewidth=320, precision=5, profile='long')
+np.set_printoptions(linewidth=320, formatter={'float_kind': '{:11.5g}'.format}) # format short g, %precision=5
+pd.options.display.max_columns = 10
+cv2.setNumThreads(0) # prevent OpenCV from multithreading (incompatible with PyTorch DataLoader)
+os.environ['NUMEXPR_MAX_THREADS'] = str(min(os.cpu_count(), 8)) # NumExpr max threads
+
+FILE = Path(__file__).resolve()
+ROOT = FILE.parents[1] # root directory
+
+
+def set_logging(name=None, verbose=True):
+ # Sets level and returns logger
+ rank = int(os.getenv('RANK', -1)) # rank in world for Multi-GPU trainings
+ logging.basicConfig(format="%(message)s", level=logging.INFO if (verbose and rank in (-1, 0)) else logging.WARNING)
+ return logging.getLogger(name)
+
+
+LOGGER = set_logging(__name__) # define globally (used in train.py, val.py, detect.py, etc.)
+
+
+class Profile(contextlib.ContextDecorator):
+ # Usage: @Profile() decorator or 'with Profile():' context manager
+ def __enter__(self):
+ self.start = time.time()
+
+ def __exit__(self, type, value, traceback):
+ print(f'Profile results: {time.time() - self.start:.5f}s')
+
+
+class Timeout(contextlib.ContextDecorator):
+ # Usage: @Timeout(seconds) decorator or 'with Timeout(seconds):' context manager
+ def __init__(self, seconds, *, timeout_msg='', suppress_timeout_errors=True):
+ self.seconds = int(seconds)
+ self.timeout_message = timeout_msg
+ self.suppress = bool(suppress_timeout_errors)
+
+ def _timeout_handler(self, signum, frame):
+ raise TimeoutError(self.timeout_message)
+
+ def __enter__(self):
+ signal.signal(signal.SIGALRM, self._timeout_handler) # Set handler for SIGALRM
+ signal.alarm(self.seconds) # start countdown for SIGALRM to be raised
+
+ def __exit__(self, exc_type, exc_val, exc_tb):
+ signal.alarm(0) # Cancel SIGALRM if it's scheduled
+ if self.suppress and exc_type is TimeoutError: # Suppress TimeoutError
+ return True
+
+
+class WorkingDirectory(contextlib.ContextDecorator):
+ # Usage: @WorkingDirectory(dir) decorator or 'with WorkingDirectory(dir):' context manager
+ def __init__(self, new_dir):
+ self.dir = new_dir # new dir
+ self.cwd = Path.cwd().resolve() # current dir
+
+ def __enter__(self):
+ os.chdir(self.dir)
+
+ def __exit__(self, exc_type, exc_val, exc_tb):
+ os.chdir(self.cwd)
+
+
+def try_except(func):
+ # try-except function. Usage: @try_except decorator
+ def handler(*args, **kwargs):
+ try:
+ func(*args, **kwargs)
+ except Exception as e:
+ print(e)
+
+ return handler
+
+
+def methods(instance):
+ # Get class/instance methods
+ return [f for f in dir(instance) if callable(getattr(instance, f)) and not f.startswith("__")]
+
+
+def print_args(name, opt):
+ # Print argparser arguments
+ LOGGER.info(colorstr(f'{name}: ') + ', '.join(f'{k}={v}' for k, v in vars(opt).items()))
+
+
+def init_seeds(seed=0):
+ # Initialize random number generator (RNG) seeds https://pytorch.org/docs/stable/notes/randomness.html
+ # cudnn seed 0 settings are slower and more reproducible, else faster and less reproducible
+ import torch.backends.cudnn as cudnn
+ random.seed(seed)
+ np.random.seed(seed)
+ torch.manual_seed(seed)
+ cudnn.benchmark, cudnn.deterministic = (False, True) if seed == 0 else (True, False)
+
+
+def intersect_dicts(da, db, exclude=()):
+ # Dictionary intersection of matching keys and shapes, omitting 'exclude' keys, using da values
+ return {k: v for k, v in da.items() if k in db and not any(x in k for x in exclude) and v.shape == db[k].shape}
+
+
+def get_latest_run(search_dir='.'):
+ # Return path to most recent 'last.pt' in /runs (i.e. to --resume from)
+ last_list = glob.glob(f'{search_dir}/**/last*.pt', recursive=True)
+ return max(last_list, key=os.path.getctime) if last_list else ''
+
+
+def user_config_dir(dir='Ultralytics', env_var='YOLOV3_CONFIG_DIR'):
+ # Return path of user configuration directory. Prefer environment variable if exists. Make dir if required.
+ env = os.getenv(env_var)
+ if env:
+ path = Path(env) # use environment variable
+ else:
+ cfg = {'Windows': 'AppData/Roaming', 'Linux': '.config', 'Darwin': 'Library/Application Support'} # 3 OS dirs
+ path = Path.home() / cfg.get(platform.system(), '') # OS-specific config dir
+ path = (path if is_writeable(path) else Path('/tmp')) / dir # GCP and AWS lambda fix, only /tmp is writeable
+ path.mkdir(exist_ok=True) # make if required
+ return path
+
+
+def is_writeable(dir, test=False):
+ # Return True if directory has write permissions, test opening a file with write permissions if test=True
+ if test: # method 1
+ file = Path(dir) / 'tmp.txt'
+ try:
+ with open(file, 'w'): # open file with write permissions
+ pass
+ file.unlink() # remove file
+ return True
+ except OSError:
+ return False
+ else: # method 2
+ return os.access(dir, os.R_OK) # possible issues on Windows
+
+
+def is_docker():
+ # Is environment a Docker container?
+ return Path('/workspace').exists() # or Path('/.dockerenv').exists()
+
+
+def is_colab():
+ # Is environment a Google Colab instance?
+ try:
+ import google.colab
+ return True
+ except ImportError:
+ return False
+
+
+def is_pip():
+ # Is file in a pip package?
+ return 'site-packages' in Path(__file__).resolve().parts
+
+
+def is_ascii(s=''):
+ # Is string composed of all ASCII (no UTF) characters? (note str().isascii() introduced in python 3.7)
+ s = str(s) # convert list, tuple, None, etc. to str
+ return len(s.encode().decode('ascii', 'ignore')) == len(s)
+
+
+def is_chinese(s='人工智能'):
+ # Is string composed of any Chinese characters?
+ return re.search('[\u4e00-\u9fff]', s)
+
+
+def emojis(str=''):
+ # Return platform-dependent emoji-safe version of string
+ return str.encode().decode('ascii', 'ignore') if platform.system() == 'Windows' else str
+
+
+def file_size(path):
+ # Return file/dir size (MB)
+ path = Path(path)
+ if path.is_file():
+ return path.stat().st_size / 1E6
+ elif path.is_dir():
+ return sum(f.stat().st_size for f in path.glob('**/*') if f.is_file()) / 1E6
+ else:
+ return 0.0
+
+
+def check_online():
+ # Check internet connectivity
+ import socket
+ try:
+ socket.create_connection(("1.1.1.1", 443), 5) # check host accessibility
+ return True
+ except OSError:
+ return False
+
+
+@try_except
+@WorkingDirectory(ROOT)
+def check_git_status():
+ # Recommend 'git pull' if code is out of date
+ msg = ', for updates see https://github.com/ultralytics/yolov3'
+ print(colorstr('github: '), end='')
+ assert Path('.git').exists(), 'skipping check (not a git repository)' + msg
+ assert not is_docker(), 'skipping check (Docker image)' + msg
+ assert check_online(), 'skipping check (offline)' + msg
+
+ cmd = 'git fetch && git config --get remote.origin.url'
+ url = check_output(cmd, shell=True, timeout=5).decode().strip().rstrip('.git') # git fetch
+ branch = check_output('git rev-parse --abbrev-ref HEAD', shell=True).decode().strip() # checked out
+ n = int(check_output(f'git rev-list {branch}..origin/master --count', shell=True)) # commits behind
+ if n > 0:
+ s = f"⚠️ YOLOv3 is out of date by {n} commit{'s' * (n > 1)}. Use `git pull` or `git clone {url}` to update."
+ else:
+ s = f'up to date with {url} ✅'
+ print(emojis(s)) # emoji-safe
+
+
+def check_python(minimum='3.6.2'):
+ # Check current python version vs. required python version
+ check_version(platform.python_version(), minimum, name='Python ', hard=True)
+
+
+def check_version(current='0.0.0', minimum='0.0.0', name='version ', pinned=False, hard=False):
+ # Check version vs. required version
+ current, minimum = (pkg.parse_version(x) for x in (current, minimum))
+ result = (current == minimum) if pinned else (current >= minimum) # bool
+ if hard: # assert min requirements met
+ assert result, f'{name}{minimum} required by YOLOv3, but {name}{current} is currently installed'
+ else:
+ return result
+
+
+@try_except
+def check_requirements(requirements=ROOT / 'requirements.txt', exclude=(), install=True):
+ # Check installed dependencies meet requirements (pass *.txt file or list of packages)
+ prefix = colorstr('red', 'bold', 'requirements:')
+ check_python() # check python version
+ if isinstance(requirements, (str, Path)): # requirements.txt file
+ file = Path(requirements)
+ assert file.exists(), f"{prefix} {file.resolve()} not found, check failed."
+ with file.open() as f:
+ requirements = [f'{x.name}{x.specifier}' for x in pkg.parse_requirements(f) if x.name not in exclude]
+ else: # list or tuple of packages
+ requirements = [x for x in requirements if x not in exclude]
+
+ n = 0 # number of packages updates
+ for r in requirements:
+ try:
+ pkg.require(r)
+ except Exception as e: # DistributionNotFound or VersionConflict if requirements not met
+ s = f"{prefix} {r} not found and is required by YOLOv3"
+ if install:
+ print(f"{s}, attempting auto-update...")
+ try:
+ assert check_online(), f"'pip install {r}' skipped (offline)"
+ print(check_output(f"pip install '{r}'", shell=True).decode())
+ n += 1
+ except Exception as e:
+ print(f'{prefix} {e}')
+ else:
+ print(f'{s}. Please install and rerun your command.')
+
+ if n: # if packages updated
+ source = file.resolve() if 'file' in locals() else requirements
+ s = f"{prefix} {n} package{'s' * (n > 1)} updated per {source}\n" \
+ f"{prefix} ⚠️ {colorstr('bold', 'Restart runtime or rerun command for updates to take effect')}\n"
+ print(emojis(s))
+
+
+def check_img_size(imgsz, s=32, floor=0):
+ # Verify image size is a multiple of stride s in each dimension
+ if isinstance(imgsz, int): # integer i.e. img_size=640
+ new_size = max(make_divisible(imgsz, int(s)), floor)
+ else: # list i.e. img_size=[640, 480]
+ new_size = [max(make_divisible(x, int(s)), floor) for x in imgsz]
+ if new_size != imgsz:
+ print(f'WARNING: --img-size {imgsz} must be multiple of max stride {s}, updating to {new_size}')
+ return new_size
+
+
+def check_imshow():
+ # Check if environment supports image displays
+ try:
+ assert not is_docker(), 'cv2.imshow() is disabled in Docker environments'
+ assert not is_colab(), 'cv2.imshow() is disabled in Google Colab environments'
+ cv2.imshow('test', np.zeros((1, 1, 3)))
+ cv2.waitKey(1)
+ cv2.destroyAllWindows()
+ cv2.waitKey(1)
+ return True
+ except Exception as e:
+ print(f'WARNING: Environment does not support cv2.imshow() or PIL Image.show() image displays\n{e}')
+ return False
+
+
+def check_suffix(file='yolov3.pt', suffix=('.pt',), msg=''):
+ # Check file(s) for acceptable suffix
+ if file and suffix:
+ if isinstance(suffix, str):
+ suffix = [suffix]
+ for f in file if isinstance(file, (list, tuple)) else [file]:
+ s = Path(f).suffix.lower() # file suffix
+ if len(s):
+ assert s in suffix, f"{msg}{f} acceptable suffix is {suffix}"
+
+
+def check_yaml(file, suffix=('.yaml', '.yml')):
+ # Search/download YAML file (if necessary) and return path, checking suffix
+ return check_file(file, suffix)
+
+
+def check_file(file, suffix=''):
+ # Search/download file (if necessary) and return path
+ check_suffix(file, suffix) # optional
+ file = str(file) # convert to str()
+ if Path(file).is_file() or file == '': # exists
+ return file
+ elif file.startswith(('http:/', 'https:/')): # download
+ url = str(Path(file).as_posix()).replace(':/', '://') # Pathlib turns :// -> :/
+ file = Path(urllib.parse.unquote(file).split('?')[0]).name # '%2F' to '/', split https://url.com/file.txt?auth
+ if Path(file).is_file():
+ print(f'Found {url} locally at {file}') # file already exists
+ else:
+ print(f'Downloading {url} to {file}...')
+ torch.hub.download_url_to_file(url, file)
+ assert Path(file).exists() and Path(file).stat().st_size > 0, f'File download failed: {url}' # check
+ return file
+ else: # search
+ files = []
+ for d in 'data', 'models', 'utils': # search directories
+ files.extend(glob.glob(str(ROOT / d / '**' / file), recursive=True)) # find file
+ assert len(files), f'File not found: {file}' # assert file was found
+ assert len(files) == 1, f"Multiple files match '{file}', specify exact path: {files}" # assert unique
+ return files[0] # return file
+
+
+def check_dataset(data, autodownload=True):
+ # Download and/or unzip dataset if not found locally
+ # Usage: https://github.com/ultralytics/yolov5/releases/download/v1.0/coco128_with_yaml.zip
+
+ # Download (optional)
+ extract_dir = ''
+ if isinstance(data, (str, Path)) and str(data).endswith('.zip'): # i.e. gs://bucket/dir/coco128.zip
+ download(data, dir='../datasets', unzip=True, delete=False, curl=False, threads=1)
+ data = next((Path('../datasets') / Path(data).stem).rglob('*.yaml'))
+ extract_dir, autodownload = data.parent, False
+
+ # Read yaml (optional)
+ if isinstance(data, (str, Path)):
+ with open(data, errors='ignore') as f:
+ data = yaml.safe_load(f) # dictionary
+
+ # Parse yaml
+ path = extract_dir or Path(data.get('path') or '') # optional 'path' default to '.'
+ for k in 'train', 'val', 'test':
+ if data.get(k): # prepend path
+ data[k] = str(path / data[k]) if isinstance(data[k], str) else [str(path / x) for x in data[k]]
+
+ assert 'nc' in data, "Dataset 'nc' key missing."
+ if 'names' not in data:
+ data['names'] = [f'class{i}' for i in range(data['nc'])] # assign class names if missing
+ train, val, test, s = (data.get(x) for x in ('train', 'val', 'test', 'download'))
+ if val:
+ val = [Path(x).resolve() for x in (val if isinstance(val, list) else [val])] # val path
+ if not all(x.exists() for x in val):
+ print('\nWARNING: Dataset not found, nonexistent paths: %s' % [str(x) for x in val if not x.exists()])
+ if s and autodownload: # download script
+ root = path.parent if 'path' in data else '..' # unzip directory i.e. '../'
+ if s.startswith('http') and s.endswith('.zip'): # URL
+ f = Path(s).name # filename
+ print(f'Downloading {s} to {f}...')
+ torch.hub.download_url_to_file(s, f)
+ Path(root).mkdir(parents=True, exist_ok=True) # create root
+ ZipFile(f).extractall(path=root) # unzip
+ Path(f).unlink() # remove zip
+ r = None # success
+ elif s.startswith('bash '): # bash script
+ print(f'Running {s} ...')
+ r = os.system(s)
+ else: # python script
+ r = exec(s, {'yaml': data}) # return None
+ print(f"Dataset autodownload {f'success, saved to {root}' if r in (0, None) else 'failure'}\n")
+ else:
+ raise Exception('Dataset not found.')
+
+ return data # dictionary
+
+
+def url2file(url):
+ # Convert URL to filename, i.e. https://url.com/file.txt?auth -> file.txt
+ url = str(Path(url)).replace(':/', '://') # Pathlib turns :// -> :/
+ file = Path(urllib.parse.unquote(url)).name.split('?')[0] # '%2F' to '/', split https://url.com/file.txt?auth
+ return file
+
+
+def download(url, dir='.', unzip=True, delete=True, curl=False, threads=1):
+ # Multi-threaded file download and unzip function, used in data.yaml for autodownload
+ def download_one(url, dir):
+ # Download 1 file
+ f = dir / Path(url).name # filename
+ if Path(url).is_file(): # exists in current path
+ Path(url).rename(f) # move to dir
+ elif not f.exists():
+ print(f'Downloading {url} to {f}...')
+ if curl:
+ os.system(f"curl -L '{url}' -o '{f}' --retry 9 -C -") # curl download, retry and resume on fail
+ else:
+ torch.hub.download_url_to_file(url, f, progress=True) # torch download
+ if unzip and f.suffix in ('.zip', '.gz'):
+ print(f'Unzipping {f}...')
+ if f.suffix == '.zip':
+ ZipFile(f).extractall(path=dir) # unzip
+ elif f.suffix == '.gz':
+ os.system(f'tar xfz {f} --directory {f.parent}') # unzip
+ if delete:
+ f.unlink() # remove zip
+
+ dir = Path(dir)
+ dir.mkdir(parents=True, exist_ok=True) # make directory
+ if threads > 1:
+ pool = ThreadPool(threads)
+ pool.imap(lambda x: download_one(*x), zip(url, repeat(dir))) # multi-threaded
+ pool.close()
+ pool.join()
+ else:
+ for u in [url] if isinstance(url, (str, Path)) else url:
+ download_one(u, dir)
+
+
+def make_divisible(x, divisor):
+ # Returns x evenly divisible by divisor
+ return math.ceil(x / divisor) * divisor
+
+
+def clean_str(s):
+ # Cleans a string by replacing special characters with underscore _
+ return re.sub(pattern="[|@#!¡·$€%&()=?¿^*;:,¨´><+]", repl="_", string=s)
+
+
+def one_cycle(y1=0.0, y2=1.0, steps=100):
+ # lambda function for sinusoidal ramp from y1 to y2 https://arxiv.org/pdf/1812.01187.pdf
+ return lambda x: ((1 - math.cos(x * math.pi / steps)) / 2) * (y2 - y1) + y1
+
+
+def colorstr(*input):
+ # Colors a string https://en.wikipedia.org/wiki/ANSI_escape_code, i.e. colorstr('blue', 'hello world')
+ *args, string = input if len(input) > 1 else ('blue', 'bold', input[0]) # color arguments, string
+ colors = {'black': '\033[30m', # basic colors
+ 'red': '\033[31m',
+ 'green': '\033[32m',
+ 'yellow': '\033[33m',
+ 'blue': '\033[34m',
+ 'magenta': '\033[35m',
+ 'cyan': '\033[36m',
+ 'white': '\033[37m',
+ 'bright_black': '\033[90m', # bright colors
+ 'bright_red': '\033[91m',
+ 'bright_green': '\033[92m',
+ 'bright_yellow': '\033[93m',
+ 'bright_blue': '\033[94m',
+ 'bright_magenta': '\033[95m',
+ 'bright_cyan': '\033[96m',
+ 'bright_white': '\033[97m',
+ 'end': '\033[0m', # misc
+ 'bold': '\033[1m',
+ 'underline': '\033[4m'}
+ return ''.join(colors[x] for x in args) + f'{string}' + colors['end']
+
+
+def labels_to_class_weights(labels, nc=80):
+ # Get class weights (inverse frequency) from training labels
+ if labels[0] is None: # no labels loaded
+ return torch.Tensor()
+
+ labels = np.concatenate(labels, 0) # labels.shape = (866643, 5) for COCO
+ classes = labels[:, 0].astype(np.int) # labels = [class xywh]
+ weights = np.bincount(classes, minlength=nc) # occurrences per class
+
+ # Prepend gridpoint count (for uCE training)
+ # gpi = ((320 / 32 * np.array([1, 2, 4])) ** 2 * 3).sum() # gridpoints per image
+ # weights = np.hstack([gpi * len(labels) - weights.sum() * 9, weights * 9]) ** 0.5 # prepend gridpoints to start
+
+ weights[weights == 0] = 1 # replace empty bins with 1
+ weights = 1 / weights # number of targets per class
+ weights /= weights.sum() # normalize
+ return torch.from_numpy(weights)
+
+
+def labels_to_image_weights(labels, nc=80, class_weights=np.ones(80)):
+ # Produces image weights based on class_weights and image contents
+ class_counts = np.array([np.bincount(x[:, 0].astype(np.int), minlength=nc) for x in labels])
+ image_weights = (class_weights.reshape(1, nc) * class_counts).sum(1)
+ # index = random.choices(range(n), weights=image_weights, k=1) # weight image sample
+ return image_weights
+
+
+def coco80_to_coco91_class(): # converts 80-index (val2014) to 91-index (paper)
+ # https://tech.amikelive.com/node-718/what-object-categories-labels-are-in-coco-dataset/
+ # a = np.loadtxt('data/coco.names', dtype='str', delimiter='\n')
+ # b = np.loadtxt('data/coco_paper.names', dtype='str', delimiter='\n')
+ # x1 = [list(a[i] == b).index(True) + 1 for i in range(80)] # darknet to coco
+ # x2 = [list(b[i] == a).index(True) if any(b[i] == a) else None for i in range(91)] # coco to darknet
+ x = [1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 27, 28, 31, 32, 33, 34,
+ 35, 36, 37, 38, 39, 40, 41, 42, 43, 44, 46, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56, 57, 58, 59, 60, 61, 62, 63,
+ 64, 65, 67, 70, 72, 73, 74, 75, 76, 77, 78, 79, 80, 81, 82, 84, 85, 86, 87, 88, 89, 90]
+ return x
+
+
+def xyxy2xywh(x):
+ # Convert nx4 boxes from [x1, y1, x2, y2] to [x, y, w, h] where xy1=top-left, xy2=bottom-right
+ y = x.clone() if isinstance(x, torch.Tensor) else np.copy(x)
+ y[:, 0] = (x[:, 0] + x[:, 2]) / 2 # x center
+ y[:, 1] = (x[:, 1] + x[:, 3]) / 2 # y center
+ y[:, 2] = x[:, 2] - x[:, 0] # width
+ y[:, 3] = x[:, 3] - x[:, 1] # height
+ return y
+
+
+def xywh2xyxy(x):
+ # Convert nx4 boxes from [x, y, w, h] to [x1, y1, x2, y2] where xy1=top-left, xy2=bottom-right
+ y = x.clone() if isinstance(x, torch.Tensor) else np.copy(x)
+ y[:, 0] = x[:, 0] - x[:, 2] / 2 # top left x
+ y[:, 1] = x[:, 1] - x[:, 3] / 2 # top left y
+ y[:, 2] = x[:, 0] + x[:, 2] / 2 # bottom right x
+ y[:, 3] = x[:, 1] + x[:, 3] / 2 # bottom right y
+ return y
+
+
+def xywhn2xyxy(x, w=640, h=640, padw=0, padh=0):
+ # Convert nx4 boxes from [x, y, w, h] normalized to [x1, y1, x2, y2] where xy1=top-left, xy2=bottom-right
+ y = x.clone() if isinstance(x, torch.Tensor) else np.copy(x)
+ y[:, 0] = w * (x[:, 0] - x[:, 2] / 2) + padw # top left x
+ y[:, 1] = h * (x[:, 1] - x[:, 3] / 2) + padh # top left y
+ y[:, 2] = w * (x[:, 0] + x[:, 2] / 2) + padw # bottom right x
+ y[:, 3] = h * (x[:, 1] + x[:, 3] / 2) + padh # bottom right y
+ return y
+
+
+def xyxy2xywhn(x, w=640, h=640, clip=False, eps=0.0):
+ # Convert nx4 boxes from [x1, y1, x2, y2] to [x, y, w, h] normalized where xy1=top-left, xy2=bottom-right
+ if clip:
+ clip_coords(x, (h - eps, w - eps)) # warning: inplace clip
+ y = x.clone() if isinstance(x, torch.Tensor) else np.copy(x)
+ y[:, 0] = ((x[:, 0] + x[:, 2]) / 2) / w # x center
+ y[:, 1] = ((x[:, 1] + x[:, 3]) / 2) / h # y center
+ y[:, 2] = (x[:, 2] - x[:, 0]) / w # width
+ y[:, 3] = (x[:, 3] - x[:, 1]) / h # height
+ return y
+
+
+def xyn2xy(x, w=640, h=640, padw=0, padh=0):
+ # Convert normalized segments into pixel segments, shape (n,2)
+ y = x.clone() if isinstance(x, torch.Tensor) else np.copy(x)
+ y[:, 0] = w * x[:, 0] + padw # top left x
+ y[:, 1] = h * x[:, 1] + padh # top left y
+ return y
+
+
+def segment2box(segment, width=640, height=640):
+ # Convert 1 segment label to 1 box label, applying inside-image constraint, i.e. (xy1, xy2, ...) to (xyxy)
+ x, y = segment.T # segment xy
+ inside = (x >= 0) & (y >= 0) & (x <= width) & (y <= height)
+ x, y, = x[inside], y[inside]
+ return np.array([x.min(), y.min(), x.max(), y.max()]) if any(x) else np.zeros((1, 4)) # xyxy
+
+
+def segments2boxes(segments):
+ # Convert segment labels to box labels, i.e. (cls, xy1, xy2, ...) to (cls, xywh)
+ boxes = []
+ for s in segments:
+ x, y = s.T # segment xy
+ boxes.append([x.min(), y.min(), x.max(), y.max()]) # cls, xyxy
+ return xyxy2xywh(np.array(boxes)) # cls, xywh
+
+
+def resample_segments(segments, n=1000):
+ # Up-sample an (n,2) segment
+ for i, s in enumerate(segments):
+ x = np.linspace(0, len(s) - 1, n)
+ xp = np.arange(len(s))
+ segments[i] = np.concatenate([np.interp(x, xp, s[:, i]) for i in range(2)]).reshape(2, -1).T # segment xy
+ return segments
+
+
+def scale_coords(img1_shape, coords, img0_shape, ratio_pad=None):
+ # Rescale coords (xyxy) from img1_shape to img0_shape
+ if ratio_pad is None: # calculate from img0_shape
+ gain = min(img1_shape[0] / img0_shape[0], img1_shape[1] / img0_shape[1]) # gain = old / new
+ pad = (img1_shape[1] - img0_shape[1] * gain) / 2, (img1_shape[0] - img0_shape[0] * gain) / 2 # wh padding
+ else:
+ gain = ratio_pad[0][0]
+ pad = ratio_pad[1]
+
+ coords[:, [0, 2]] -= pad[0] # x padding
+ coords[:, [1, 3]] -= pad[1] # y padding
+ coords[:, :4] /= gain
+ clip_coords(coords, img0_shape)
+ return coords
+
+
+def clip_coords(boxes, shape):
+ # Clip bounding xyxy bounding boxes to image shape (height, width)
+ if isinstance(boxes, torch.Tensor): # faster individually
+ boxes[:, 0].clamp_(0, shape[1]) # x1
+ boxes[:, 1].clamp_(0, shape[0]) # y1
+ boxes[:, 2].clamp_(0, shape[1]) # x2
+ boxes[:, 3].clamp_(0, shape[0]) # y2
+ else: # np.array (faster grouped)
+ boxes[:, [0, 2]] = boxes[:, [0, 2]].clip(0, shape[1]) # x1, x2
+ boxes[:, [1, 3]] = boxes[:, [1, 3]].clip(0, shape[0]) # y1, y2
+
+
+def non_max_suppression(prediction, conf_thres=0.25, iou_thres=0.45, classes=None, agnostic=False, multi_label=False,
+ labels=(), max_det=300):
+ """Runs Non-Maximum Suppression (NMS) on inference results
+
+ Returns:
+ list of detections, on (n,6) tensor per image [xyxy, conf, cls]
+ """
+
+ nc = prediction.shape[2] - 5 # number of classes
+ xc = prediction[..., 4] > conf_thres # candidates
+
+ # Checks
+ assert 0 <= conf_thres <= 1, f'Invalid Confidence threshold {conf_thres}, valid values are between 0.0 and 1.0'
+ assert 0 <= iou_thres <= 1, f'Invalid IoU {iou_thres}, valid values are between 0.0 and 1.0'
+
+ # Settings
+ min_wh, max_wh = 2, 4096 # (pixels) minimum and maximum box width and height
+ max_nms = 30000 # maximum number of boxes into torchvision.ops.nms()
+ time_limit = 10.0 # seconds to quit after
+ redundant = True # require redundant detections
+ multi_label &= nc > 1 # multiple labels per box (adds 0.5ms/img)
+ merge = False # use merge-NMS
+
+ t = time.time()
+ output = [torch.zeros((0, 6), device=prediction.device)] * prediction.shape[0]
+ for xi, x in enumerate(prediction): # image index, image inference
+ # Apply constraints
+ # x[((x[..., 2:4] < min_wh) | (x[..., 2:4] > max_wh)).any(1), 4] = 0 # width-height
+ x = x[xc[xi]] # confidence
+
+ # Cat apriori labels if autolabelling
+ if labels and len(labels[xi]):
+ l = labels[xi]
+ v = torch.zeros((len(l), nc + 5), device=x.device)
+ v[:, :4] = l[:, 1:5] # box
+ v[:, 4] = 1.0 # conf
+ v[range(len(l)), l[:, 0].long() + 5] = 1.0 # cls
+ x = torch.cat((x, v), 0)
+
+ # If none remain process next image
+ if not x.shape[0]:
+ continue
+
+ # Compute conf
+ x[:, 5:] *= x[:, 4:5] # conf = obj_conf * cls_conf
+
+ # Box (center x, center y, width, height) to (x1, y1, x2, y2)
+ box = xywh2xyxy(x[:, :4])
+
+ # Detections matrix nx6 (xyxy, conf, cls)
+ if multi_label:
+ i, j = (x[:, 5:] > conf_thres).nonzero(as_tuple=False).T
+ x = torch.cat((box[i], x[i, j + 5, None], j[:, None].float()), 1)
+ else: # best class only
+ conf, j = x[:, 5:].max(1, keepdim=True)
+ x = torch.cat((box, conf, j.float()), 1)[conf.view(-1) > conf_thres]
+
+ # Filter by class
+ if classes is not None:
+ x = x[(x[:, 5:6] == torch.tensor(classes, device=x.device)).any(1)]
+
+ # Apply finite constraint
+ # if not torch.isfinite(x).all():
+ # x = x[torch.isfinite(x).all(1)]
+
+ # Check shape
+ n = x.shape[0] # number of boxes
+ if not n: # no boxes
+ continue
+ elif n > max_nms: # excess boxes
+ x = x[x[:, 4].argsort(descending=True)[:max_nms]] # sort by confidence
+
+ # Batched NMS
+ c = x[:, 5:6] * (0 if agnostic else max_wh) # classes
+ boxes, scores = x[:, :4] + c, x[:, 4] # boxes (offset by class), scores
+ i = torchvision.ops.nms(boxes, scores, iou_thres) # NMS
+ if i.shape[0] > max_det: # limit detections
+ i = i[:max_det]
+ if merge and (1 < n < 3E3): # Merge NMS (boxes merged using weighted mean)
+ # update boxes as boxes(i,4) = weights(i,n) * boxes(n,4)
+ iou = box_iou(boxes[i], boxes) > iou_thres # iou matrix
+ weights = iou * scores[None] # box weights
+ x[i, :4] = torch.mm(weights, x[:, :4]).float() / weights.sum(1, keepdim=True) # merged boxes
+ if redundant:
+ i = i[iou.sum(1) > 1] # require redundancy
+
+ output[xi] = x[i]
+ if (time.time() - t) > time_limit:
+ print(f'WARNING: NMS time limit {time_limit}s exceeded')
+ break # time limit exceeded
+
+ return output
+
+
+def strip_optimizer(f='best.pt', s=''): # from utils.general import *; strip_optimizer()
+ # Strip optimizer from 'f' to finalize training, optionally save as 's'
+ x = torch.load(f, map_location=torch.device('cpu'))
+ if x.get('ema'):
+ x['model'] = x['ema'] # replace model with ema
+ for k in 'optimizer', 'training_results', 'wandb_id', 'ema', 'updates': # keys
+ x[k] = None
+ x['epoch'] = -1
+ x['model'].half() # to FP16
+ for p in x['model'].parameters():
+ p.requires_grad = False
+ torch.save(x, s or f)
+ mb = os.path.getsize(s or f) / 1E6 # filesize
+ print(f"Optimizer stripped from {f},{(' saved as %s,' % s) if s else ''} {mb:.1f}MB")
+
+
+def print_mutation(results, hyp, save_dir, bucket):
+ evolve_csv, results_csv, evolve_yaml = save_dir / 'evolve.csv', save_dir / 'results.csv', save_dir / 'hyp_evolve.yaml'
+ keys = ('metrics/precision', 'metrics/recall', 'metrics/mAP_0.5', 'metrics/mAP_0.5:0.95',
+ 'val/box_loss', 'val/obj_loss', 'val/cls_loss') + tuple(hyp.keys()) # [results + hyps]
+ keys = tuple(x.strip() for x in keys)
+ vals = results + tuple(hyp.values())
+ n = len(keys)
+
+ # Download (optional)
+ if bucket:
+ url = f'gs://{bucket}/evolve.csv'
+ if gsutil_getsize(url) > (os.path.getsize(evolve_csv) if os.path.exists(evolve_csv) else 0):
+ os.system(f'gsutil cp {url} {save_dir}') # download evolve.csv if larger than local
+
+ # Log to evolve.csv
+ s = '' if evolve_csv.exists() else (('%20s,' * n % keys).rstrip(',') + '\n') # add header
+ with open(evolve_csv, 'a') as f:
+ f.write(s + ('%20.5g,' * n % vals).rstrip(',') + '\n')
+
+ # Print to screen
+ print(colorstr('evolve: ') + ', '.join(f'{x.strip():>20s}' for x in keys))
+ print(colorstr('evolve: ') + ', '.join(f'{x:20.5g}' for x in vals), end='\n\n\n')
+
+ # Save yaml
+ with open(evolve_yaml, 'w') as f:
+ data = pd.read_csv(evolve_csv)
+ data = data.rename(columns=lambda x: x.strip()) # strip keys
+ i = np.argmax(fitness(data.values[:, :7])) #
+ f.write('# YOLOv3 Hyperparameter Evolution Results\n' +
+ f'# Best generation: {i}\n' +
+ f'# Last generation: {len(data)}\n' +
+ '# ' + ', '.join(f'{x.strip():>20s}' for x in keys[:7]) + '\n' +
+ '# ' + ', '.join(f'{x:>20.5g}' for x in data.values[i, :7]) + '\n\n')
+ yaml.safe_dump(hyp, f, sort_keys=False)
+
+ if bucket:
+ os.system(f'gsutil cp {evolve_csv} {evolve_yaml} gs://{bucket}') # upload
+
+
+def apply_classifier(x, model, img, im0):
+ # Apply a second stage classifier to YOLO outputs
+ # Example model = torchvision.models.__dict__['efficientnet_b0'](pretrained=True).to(device).eval()
+ im0 = [im0] if isinstance(im0, np.ndarray) else im0
+ for i, d in enumerate(x): # per image
+ if d is not None and len(d):
+ d = d.clone()
+
+ # Reshape and pad cutouts
+ b = xyxy2xywh(d[:, :4]) # boxes
+ b[:, 2:] = b[:, 2:].max(1)[0].unsqueeze(1) # rectangle to square
+ b[:, 2:] = b[:, 2:] * 1.3 + 30 # pad
+ d[:, :4] = xywh2xyxy(b).long()
+
+ # Rescale boxes from img_size to im0 size
+ scale_coords(img.shape[2:], d[:, :4], im0[i].shape)
+
+ # Classes
+ pred_cls1 = d[:, 5].long()
+ ims = []
+ for j, a in enumerate(d): # per item
+ cutout = im0[i][int(a[1]):int(a[3]), int(a[0]):int(a[2])]
+ im = cv2.resize(cutout, (224, 224)) # BGR
+ # cv2.imwrite('example%i.jpg' % j, cutout)
+
+ im = im[:, :, ::-1].transpose(2, 0, 1) # BGR to RGB, to 3x416x416
+ im = np.ascontiguousarray(im, dtype=np.float32) # uint8 to float32
+ im /= 255 # 0 - 255 to 0.0 - 1.0
+ ims.append(im)
+
+ pred_cls2 = model(torch.Tensor(ims).to(d.device)).argmax(1) # classifier prediction
+ x[i] = x[i][pred_cls1 == pred_cls2] # retain matching class detections
+
+ return x
+
+
+def increment_path(path, exist_ok=False, sep='', mkdir=False):
+ # Increment file or directory path, i.e. runs/exp --> runs/exp{sep}2, runs/exp{sep}3, ... etc.
+ path = Path(path) # os-agnostic
+ if path.exists() and not exist_ok:
+ path, suffix = (path.with_suffix(''), path.suffix) if path.is_file() else (path, '')
+ dirs = glob.glob(f"{path}{sep}*") # similar paths
+ matches = [re.search(rf"%s{sep}(\d+)" % path.stem, d) for d in dirs]
+ i = [int(m.groups()[0]) for m in matches if m] # indices
+ n = max(i) + 1 if i else 2 # increment number
+ path = Path(f"{path}{sep}{n}{suffix}") # increment path
+ if mkdir:
+ path.mkdir(parents=True, exist_ok=True) # make directory
+ return path
+
+
+# Variables
+NCOLS = 0 if is_docker() else shutil.get_terminal_size().columns # terminal window size
diff --git a/ros2_ws/src/yolov3_ros/utils/google_app_engine/Dockerfile b/ros2_ws/src/yolov3_ros/utils/google_app_engine/Dockerfile
new file mode 100644
index 00000000..0155618f
--- /dev/null
+++ b/ros2_ws/src/yolov3_ros/utils/google_app_engine/Dockerfile
@@ -0,0 +1,25 @@
+FROM gcr.io/google-appengine/python
+
+# Create a virtualenv for dependencies. This isolates these packages from
+# system-level packages.
+# Use -p python3 or -p python3.7 to select python version. Default is version 2.
+RUN virtualenv /env -p python3
+
+# Setting these environment variables are the same as running
+# source /env/bin/activate.
+ENV VIRTUAL_ENV /env
+ENV PATH /env/bin:$PATH
+
+RUN apt-get update && apt-get install -y python-opencv
+
+# Copy the application's requirements.txt and run pip to install all
+# dependencies into the virtualenv.
+ADD requirements.txt /app/requirements.txt
+RUN pip install -r /app/requirements.txt
+
+# Add the application source code.
+ADD . /app
+
+# Run a WSGI server to serve the application. gunicorn must be declared as
+# a dependency in requirements.txt.
+CMD gunicorn -b :$PORT main:app
diff --git a/ros2_ws/src/yolov3_ros/utils/google_app_engine/additional_requirements.txt b/ros2_ws/src/yolov3_ros/utils/google_app_engine/additional_requirements.txt
new file mode 100644
index 00000000..b6b496fe
--- /dev/null
+++ b/ros2_ws/src/yolov3_ros/utils/google_app_engine/additional_requirements.txt
@@ -0,0 +1,4 @@
+# add these requirements in your app on top of the existing ones
+pip==21.1
+Flask==1.0.2
+gunicorn==19.10.0
diff --git a/ros2_ws/src/yolov3_ros/utils/google_app_engine/app.yaml b/ros2_ws/src/yolov3_ros/utils/google_app_engine/app.yaml
new file mode 100644
index 00000000..5056b7c1
--- /dev/null
+++ b/ros2_ws/src/yolov3_ros/utils/google_app_engine/app.yaml
@@ -0,0 +1,14 @@
+runtime: custom
+env: flex
+
+service: yolov5app
+
+liveness_check:
+ initial_delay_sec: 600
+
+manual_scaling:
+ instances: 1
+resources:
+ cpu: 1
+ memory_gb: 4
+ disk_size_gb: 20
diff --git a/ros2_ws/src/yolov3_ros/utils/loggers/__init__.py b/ros2_ws/src/yolov3_ros/utils/loggers/__init__.py
new file mode 100644
index 00000000..a234ce2c
--- /dev/null
+++ b/ros2_ws/src/yolov3_ros/utils/loggers/__init__.py
@@ -0,0 +1,159 @@
+# YOLOv3 🚀 by Ultralytics, GPL-3.0 license
+"""
+Logging utils
+"""
+
+import os
+import warnings
+from threading import Thread
+
+import pkg_resources as pkg
+import torch
+from torch.utils.tensorboard import SummaryWriter
+
+from utils.general import colorstr, emojis
+from utils.loggers.wandb.wandb_utils import WandbLogger
+from utils.plots import plot_images, plot_results
+from utils.torch_utils import de_parallel
+
+LOGGERS = ('csv', 'tb', 'wandb') # text-file, TensorBoard, Weights & Biases
+RANK = int(os.getenv('RANK', -1))
+
+try:
+ import wandb
+
+ assert hasattr(wandb, '__version__') # verify package import not local dir
+ if pkg.parse_version(wandb.__version__) >= pkg.parse_version('0.12.2') and RANK in [0, -1]:
+ try:
+ wandb_login_success = wandb.login(timeout=30)
+ except wandb.errors.UsageError: # known non-TTY terminal issue
+ wandb_login_success = False
+ if not wandb_login_success:
+ wandb = None
+except (ImportError, AssertionError):
+ wandb = None
+
+
+class Loggers():
+ # Loggers class
+ def __init__(self, save_dir=None, weights=None, opt=None, hyp=None, logger=None, include=LOGGERS):
+ self.save_dir = save_dir
+ self.weights = weights
+ self.opt = opt
+ self.hyp = hyp
+ self.logger = logger # for printing results to console
+ self.include = include
+ self.keys = ['train/box_loss', 'train/obj_loss', 'train/cls_loss', # train loss
+ 'metrics/precision', 'metrics/recall', 'metrics/mAP_0.5', 'metrics/mAP_0.5:0.95', # metrics
+ 'val/box_loss', 'val/obj_loss', 'val/cls_loss', # val loss
+ 'x/lr0', 'x/lr1', 'x/lr2'] # params
+ for k in LOGGERS:
+ setattr(self, k, None) # init empty logger dictionary
+ self.csv = True # always log to csv
+
+ # Message
+ if not wandb:
+ prefix = colorstr('Weights & Biases: ')
+ s = f"{prefix}run 'pip install wandb' to automatically track and visualize YOLOv3 🚀 runs (RECOMMENDED)"
+ print(emojis(s))
+
+ # TensorBoard
+ s = self.save_dir
+ if 'tb' in self.include and not self.opt.evolve:
+ prefix = colorstr('TensorBoard: ')
+ self.logger.info(f"{prefix}Start with 'tensorboard --logdir {s.parent}', view at http://localhost:6006/")
+ self.tb = SummaryWriter(str(s))
+
+ # W&B
+ if wandb and 'wandb' in self.include:
+ wandb_artifact_resume = isinstance(self.opt.resume, str) and self.opt.resume.startswith('wandb-artifact://')
+ run_id = torch.load(self.weights).get('wandb_id') if self.opt.resume and not wandb_artifact_resume else None
+ self.opt.hyp = self.hyp # add hyperparameters
+ self.wandb = WandbLogger(self.opt, run_id)
+ else:
+ self.wandb = None
+
+ def on_pretrain_routine_end(self):
+ # Callback runs on pre-train routine end
+ paths = self.save_dir.glob('*labels*.jpg') # training labels
+ if self.wandb:
+ self.wandb.log({"Labels": [wandb.Image(str(x), caption=x.name) for x in paths]})
+
+ def on_train_batch_end(self, ni, model, imgs, targets, paths, plots, sync_bn):
+ # Callback runs on train batch end
+ if plots:
+ if ni == 0:
+ if not sync_bn: # tb.add_graph() --sync known issue https://github.com/ultralytics/yolov5/issues/3754
+ with warnings.catch_warnings():
+ warnings.simplefilter('ignore') # suppress jit trace warning
+ self.tb.add_graph(torch.jit.trace(de_parallel(model), imgs[0:1], strict=False), [])
+ if ni < 3:
+ f = self.save_dir / f'train_batch{ni}.jpg' # filename
+ Thread(target=plot_images, args=(imgs, targets, paths, f), daemon=True).start()
+ if self.wandb and ni == 10:
+ files = sorted(self.save_dir.glob('train*.jpg'))
+ self.wandb.log({'Mosaics': [wandb.Image(str(f), caption=f.name) for f in files if f.exists()]})
+
+ def on_train_epoch_end(self, epoch):
+ # Callback runs on train epoch end
+ if self.wandb:
+ self.wandb.current_epoch = epoch + 1
+
+ def on_val_image_end(self, pred, predn, path, names, im):
+ # Callback runs on val image end
+ if self.wandb:
+ self.wandb.val_one_image(pred, predn, path, names, im)
+
+ def on_val_end(self):
+ # Callback runs on val end
+ if self.wandb:
+ files = sorted(self.save_dir.glob('val*.jpg'))
+ self.wandb.log({"Validation": [wandb.Image(str(f), caption=f.name) for f in files]})
+
+ def on_fit_epoch_end(self, vals, epoch, best_fitness, fi):
+ # Callback runs at the end of each fit (train+val) epoch
+ x = {k: v for k, v in zip(self.keys, vals)} # dict
+ if self.csv:
+ file = self.save_dir / 'results.csv'
+ n = len(x) + 1 # number of cols
+ s = '' if file.exists() else (('%20s,' * n % tuple(['epoch'] + self.keys)).rstrip(',') + '\n') # add header
+ with open(file, 'a') as f:
+ f.write(s + ('%20.5g,' * n % tuple([epoch] + vals)).rstrip(',') + '\n')
+
+ if self.tb:
+ for k, v in x.items():
+ self.tb.add_scalar(k, v, epoch)
+
+ if self.wandb:
+ self.wandb.log(x)
+ self.wandb.end_epoch(best_result=best_fitness == fi)
+
+ def on_model_save(self, last, epoch, final_epoch, best_fitness, fi):
+ # Callback runs on model save event
+ if self.wandb:
+ if ((epoch + 1) % self.opt.save_period == 0 and not final_epoch) and self.opt.save_period != -1:
+ self.wandb.log_model(last.parent, self.opt, epoch, fi, best_model=best_fitness == fi)
+
+ def on_train_end(self, last, best, plots, epoch, results):
+ # Callback runs on training end
+ if plots:
+ plot_results(file=self.save_dir / 'results.csv') # save results.png
+ files = ['results.png', 'confusion_matrix.png', *(f'{x}_curve.png' for x in ('F1', 'PR', 'P', 'R'))]
+ files = [(self.save_dir / f) for f in files if (self.save_dir / f).exists()] # filter
+
+ if self.tb:
+ import cv2
+ for f in files:
+ self.tb.add_image(f.stem, cv2.imread(str(f))[..., ::-1], epoch, dataformats='HWC')
+
+ if self.wandb:
+ self.wandb.log({"Results": [wandb.Image(str(f), caption=f.name) for f in files]})
+ # Calling wandb.log. TODO: Refactor this into WandbLogger.log_model
+ if not self.opt.evolve:
+ wandb.log_artifact(str(best if best.exists() else last), type='model',
+ name='run_' + self.wandb.wandb_run.id + '_model',
+ aliases=['latest', 'best', 'stripped'])
+ self.wandb.finish_run()
+ else:
+ self.wandb.finish_run()
+ self.wandb = WandbLogger(self.opt)
diff --git a/ros2_ws/src/yolov3_ros/utils/loggers/clearml/README.md b/ros2_ws/src/yolov3_ros/utils/loggers/clearml/README.md
new file mode 100644
index 00000000..2ca61080
--- /dev/null
+++ b/ros2_ws/src/yolov3_ros/utils/loggers/clearml/README.md
@@ -0,0 +1,271 @@
+# ClearML Integration
+
+
+
+## About ClearML
+
+[ClearML](https://cutt.ly/yolov5-tutorial-clearml) is an [open-source](https://github.com/allegroai/clearml) toolbox
+designed to save you time ⏱️.
+
+🔨 Track every YOLOv5 training run in the experiment manager
+
+🔧 Version and easily access your custom training data with the integrated ClearML Data Versioning Tool
+
+🔦 Remotely train and monitor your YOLOv5 training runs using ClearML Agent
+
+🔬 Get the very best mAP using ClearML Hyperparameter Optimization
+
+🔭 Turn your newly trained YOLOv5 model into an API with just a few commands using ClearML Serving
+
+
+And so much more. It's up to you how many of these tools you want to use, you can stick to the experiment manager, or chain them all together into an impressive pipeline!
+
+
+
+
+
+
+
+
+## 🦾 Setting Things Up
+
+To keep track of your experiments and/or data, ClearML needs to communicate to a server. You have 2 options to get one:
+
+Either sign up for free to the [ClearML Hosted Service](https://cutt.ly/yolov5-tutorial-clearml) or you can set up your
+own server, see [here](https://clear.ml/docs/latest/docs/deploying_clearml/clearml_server). Even the server is
+open-source, so even if you're dealing with sensitive data, you should be good to go!
+
+1. Install the `clearml` python package:
+
+ ```bash
+ pip install clearml
+ ```
+
+1. Connect the ClearML SDK to the server
+ by [creating credentials](https://app.clear.ml/settings/workspace-configuration) (go right top to Settings ->
+ Workspace -> Create new credentials), then execute the command below and follow the instructions:
+
+ ```bash
+ clearml-init
+ ```
+
+That's it! You're done 😎
+
+
+
+## 🚀 Training YOLOv5 With ClearML
+
+To enable ClearML experiment tracking, simply install the ClearML pip package.
+
+```bash
+pip install clearml>=1.2.0
+```
+
+This will enable integration with the YOLOv5 training script. Every training run from now on, will be captured and
+stored by the ClearML experiment manager.
+
+If you want to change the `project_name` or `task_name`, use the `--project` and `--name` arguments of the `train.py`
+script, by default the project will be called `YOLOv5` and the task `Training`.
+PLEASE NOTE: ClearML uses `/` as a delimiter for subprojects, so be careful when using `/` in your project name!
+
+```bash
+python train.py --img 640 --batch 16 --epochs 3 --data coco128.yaml --weights yolov5s.pt --cache
+```
+
+or with custom project and task name:
+
+```bash
+python train.py --project my_project --name my_training --img 640 --batch 16 --epochs 3 --data coco128.yaml --weights yolov5s.pt --cache
+```
+
+This will capture:
+
+- Source code + uncommitted changes
+- Installed packages
+- (Hyper)parameters
+- Model files (use `--save-period n` to save a checkpoint every n epochs)
+- Console output
+- Scalars (mAP_0.5, mAP_0.5:0.95, precision, recall, losses, learning rates, ...)
+- General info such as machine details, runtime, creation date etc.
+- All produced plots such as label correlogram and confusion matrix
+- Images with bounding boxes per epoch
+- Mosaic per epoch
+- Validation images per epoch
+- ...
+
+That's a lot right? 🤯
+Now, we can visualize all of this information in the ClearML UI to get an overview of our training progress. Add custom
+columns to the table view (such as e.g. mAP_0.5) so you can easily sort on the best performing model. Or select multiple
+experiments and directly compare them!
+
+There even more we can do with all of this information, like hyperparameter optimization and remote execution, so keep
+reading if you want to see how that works!
+
+
+
+## 🔗 Dataset Version Management
+
+Versioning your data separately from your code is generally a good idea and makes it easy to acquire the latest version
+too. This repository supports supplying a dataset version ID, and it will make sure to get the data if it's not there
+yet. Next to that, this workflow also saves the used dataset ID as part of the task parameters, so you will always know
+for sure which data was used in which experiment!
+
+
+
+### Prepare Your Dataset
+
+The YOLOv5 repository supports a number of different datasets by using yaml files containing their information. By
+default datasets are downloaded to the `../datasets` folder in relation to the repository root folder. So if you
+downloaded the `coco128` dataset using the link in the yaml or with the scripts provided by yolov5, you get this folder
+structure:
+
+```
+..
+|_ yolov5
+|_ datasets
+ |_ coco128
+ |_ images
+ |_ labels
+ |_ LICENSE
+ |_ README.txt
+```
+
+But this can be any dataset you wish. Feel free to use your own, as long as you keep to this folder structure.
+
+Next, ⚠️**copy the corresponding yaml file to the root of the dataset folder**⚠️. This yaml files contains the
+information ClearML will need to properly use the dataset. You can make this yourself too, of course, just follow the
+structure of the example yamls.
+
+Basically we need the following keys: `path`, `train`, `test`, `val`, `nc`, `names`.
+
+```
+..
+|_ yolov5
+|_ datasets
+ |_ coco128
+ |_ images
+ |_ labels
+ |_ coco128.yaml # <---- HERE!
+ |_ LICENSE
+ |_ README.txt
+```
+
+### Upload Your Dataset
+
+To get this dataset into ClearML as a versioned dataset, go to the dataset root folder and run the following command:
+
+```bash
+cd coco128
+clearml-data sync --project YOLOv5 --name coco128 --folder .
+```
+
+The command `clearml-data sync` is actually a shorthand command. You could also run these commands one after the other:
+
+```bash
+# Optionally add --parent if you want to base
+# this version on another dataset version, so no duplicate files are uploaded!
+clearml-data create --name coco128 --project YOLOv5
+clearml-data add --files .
+clearml-data close
+```
+
+### Run Training Using A ClearML Dataset
+
+Now that you have a ClearML dataset, you can very simply use it to train custom YOLOv5 🚀 models!
+
+```bash
+python train.py --img 640 --batch 16 --epochs 3 --data clearml:// --weights yolov5s.pt --cache
+```
+
+
+
+## 👀 Hyperparameter Optimization
+
+Now that we have our experiments and data versioned, it's time to take a look at what we can build on top!
+
+Using the code information, installed packages and environment details, the experiment itself is now **completely
+reproducible**. In fact, ClearML allows you to clone an experiment and even change its parameters. We can then just
+rerun it with these new parameters automatically, this is basically what HPO does!
+
+To **run hyperparameter optimization locally**, we've included a pre-made script for you. Just make sure a training task
+has been run at least once, so it is in the ClearML experiment manager, we will essentially clone it and change its
+hyperparameters.
+
+You'll need to fill in the ID of this `template task` in the script found at `utils/loggers/clearml/hpo.py` and then
+just run it :) You can change `task.execute_locally()` to `task.execute()` to put it in a ClearML queue and have a
+remote agent work on it instead.
+
+```bash
+# To use optuna, install it first, otherwise you can change the optimizer to just be RandomSearch
+pip install optuna
+python utils/loggers/clearml/hpo.py
+```
+
+
+
+## 🤯 Remote Execution (advanced)
+
+Running HPO locally is really handy, but what if we want to run our experiments on a remote machine instead? Maybe you
+have access to a very powerful GPU machine on-site, or you have some budget to use cloud GPUs.
+This is where the ClearML Agent comes into play. Check out what the agent can do here:
+
+- [YouTube video](https://youtu.be/MX3BrXnaULs)
+- [Documentation](https://clear.ml/docs/latest/docs/clearml_agent)
+
+In short: every experiment tracked by the experiment manager contains enough information to reproduce it on a different
+machine (installed packages, uncommitted changes etc.). So a ClearML agent does just that: it listens to a queue for
+incoming tasks and when it finds one, it recreates the environment and runs it while still reporting scalars, plots etc.
+to the experiment manager.
+
+You can turn any machine (a cloud VM, a local GPU machine, your own laptop ... ) into a ClearML agent by simply running:
+
+```bash
+clearml-agent daemon --queue [--docker]
+```
+
+### Cloning, Editing And Enqueuing
+
+With our agent running, we can give it some work. Remember from the HPO section that we can clone a task and edit the
+hyperparameters? We can do that from the interface too!
+
+🪄 Clone the experiment by right-clicking it
+
+🎯 Edit the hyperparameters to what you wish them to be
+
+⏳ Enqueue the task to any of the queues by right-clicking it
+
+
+
+### Executing A Task Remotely
+
+Now you can clone a task like we explained above, or simply mark your current script by adding `task.execute_remotely()`
+and on execution it will be put into a queue, for the agent to start working on!
+
+To run the YOLOv5 training script remotely, all you have to do is add this line to the training.py script after the
+clearml logger has been instantiated:
+
+```python
+# ...
+# Loggers
+data_dict = None
+if RANK in {-1, 0}:
+ loggers = Loggers(save_dir, weights, opt, hyp, LOGGER) # loggers instance
+ if loggers.clearml:
+ loggers.clearml.task.execute_remotely(queue="my_queue") # <------ ADD THIS LINE
+ # Data_dict is either None is user did not choose for ClearML dataset or is filled in by ClearML
+ data_dict = loggers.clearml.data_dict
+# ...
+```
+
+When running the training script after this change, python will run the script up until that line, after which it will
+package the code and send it to the queue instead!
+
+### Autoscaling workers
+
+ClearML comes with autoscalers too! This tool will automatically spin up new remote machines in the cloud of your
+choice (AWS, GCP, Azure) and turn them into ClearML agents for you whenever there are experiments detected in the queue.
+Once the tasks are processed, the autoscaler will automatically shut down the remote machines, and you stop paying!
+
+Check out the autoscalers getting started video below.
+
+[](https://youtu.be/j4XVMAaUt3E)
diff --git a/ros2_ws/src/yolov3_ros/utils/loggers/clearml/__init__.py b/ros2_ws/src/yolov3_ros/utils/loggers/clearml/__init__.py
new file mode 100644
index 00000000..e69de29b
diff --git a/ros2_ws/src/yolov3_ros/utils/loggers/clearml/clearml_utils.py b/ros2_ws/src/yolov3_ros/utils/loggers/clearml/clearml_utils.py
new file mode 100644
index 00000000..2764abe9
--- /dev/null
+++ b/ros2_ws/src/yolov3_ros/utils/loggers/clearml/clearml_utils.py
@@ -0,0 +1,164 @@
+"""Main Logger class for ClearML experiment tracking."""
+import glob
+import re
+from pathlib import Path
+
+import numpy as np
+import yaml
+
+from utils.plots import Annotator, colors
+
+try:
+ import clearml
+ from clearml import Dataset, Task
+
+ assert hasattr(clearml, '__version__') # verify package import not local dir
+except (ImportError, AssertionError):
+ clearml = None
+
+
+def construct_dataset(clearml_info_string):
+ """Load in a clearml dataset and fill the internal data_dict with its contents.
+ """
+ dataset_id = clearml_info_string.replace('clearml://', '')
+ dataset = Dataset.get(dataset_id=dataset_id)
+ dataset_root_path = Path(dataset.get_local_copy())
+
+ # We'll search for the yaml file definition in the dataset
+ yaml_filenames = list(glob.glob(str(dataset_root_path / '*.yaml')) + glob.glob(str(dataset_root_path / '*.yml')))
+ if len(yaml_filenames) > 1:
+ raise ValueError('More than one yaml file was found in the dataset root, cannot determine which one contains '
+ 'the dataset definition this way.')
+ elif len(yaml_filenames) == 0:
+ raise ValueError('No yaml definition found in dataset root path, check that there is a correct yaml file '
+ 'inside the dataset root path.')
+ with open(yaml_filenames[0]) as f:
+ dataset_definition = yaml.safe_load(f)
+
+ assert set(dataset_definition.keys()).issuperset(
+ {'train', 'test', 'val', 'nc', 'names'}
+ ), "The right keys were not found in the yaml file, make sure it at least has the following keys: ('train', 'test', 'val', 'nc', 'names')"
+
+ data_dict = dict()
+ data_dict['train'] = str(
+ (dataset_root_path / dataset_definition['train']).resolve()) if dataset_definition['train'] else None
+ data_dict['test'] = str(
+ (dataset_root_path / dataset_definition['test']).resolve()) if dataset_definition['test'] else None
+ data_dict['val'] = str(
+ (dataset_root_path / dataset_definition['val']).resolve()) if dataset_definition['val'] else None
+ data_dict['nc'] = dataset_definition['nc']
+ data_dict['names'] = dataset_definition['names']
+
+ return data_dict
+
+
+class ClearmlLogger:
+ """Log training runs, datasets, models, and predictions to ClearML.
+
+ This logger sends information to ClearML at app.clear.ml or to your own hosted server. By default,
+ this information includes hyperparameters, system configuration and metrics, model metrics, code information and
+ basic data metrics and analyses.
+
+ By providing additional command line arguments to train.py, datasets,
+ models and predictions can also be logged.
+ """
+
+ def __init__(self, opt, hyp):
+ """
+ - Initialize ClearML Task, this object will capture the experiment
+ - Upload dataset version to ClearML Data if opt.upload_dataset is True
+
+ arguments:
+ opt (namespace) -- Commandline arguments for this run
+ hyp (dict) -- Hyperparameters for this run
+
+ """
+ self.current_epoch = 0
+ # Keep tracked of amount of logged images to enforce a limit
+ self.current_epoch_logged_images = set()
+ # Maximum number of images to log to clearML per epoch
+ self.max_imgs_to_log_per_epoch = 16
+ # Get the interval of epochs when bounding box images should be logged
+ self.bbox_interval = opt.bbox_interval
+ self.clearml = clearml
+ self.task = None
+ self.data_dict = None
+ if self.clearml:
+ self.task = Task.init(
+ project_name=opt.project if opt.project != 'runs/train' else 'YOLOv5',
+ task_name=opt.name if opt.name != 'exp' else 'Training',
+ tags=['YOLOv5'],
+ output_uri=True,
+ reuse_last_task_id=opt.exist_ok,
+ auto_connect_frameworks={'pytorch': False}
+ # We disconnect pytorch auto-detection, because we added manual model save points in the code
+ )
+ # ClearML's hooks will already grab all general parameters
+ # Only the hyperparameters coming from the yaml config file
+ # will have to be added manually!
+ self.task.connect(hyp, name='Hyperparameters')
+ self.task.connect(opt, name='Args')
+
+ # Make sure the code is easily remotely runnable by setting the docker image to use by the remote agent
+ self.task.set_base_docker('ultralytics/yolov5:latest',
+ docker_arguments='--ipc=host -e="CLEARML_AGENT_SKIP_PYTHON_ENV_INSTALL=1"',
+ docker_setup_bash_script='pip install clearml')
+
+ # Get ClearML Dataset Version if requested
+ if opt.data.startswith('clearml://'):
+ # data_dict should have the following keys:
+ # names, nc (number of classes), test, train, val (all three relative paths to ../datasets)
+ self.data_dict = construct_dataset(opt.data)
+ # Set data to data_dict because wandb will crash without this information and opt is the best way
+ # to give it to them
+ opt.data = self.data_dict
+
+ def log_debug_samples(self, files, title='Debug Samples'):
+ """
+ Log files (images) as debug samples in the ClearML task.
+
+ arguments:
+ files (List(PosixPath)) a list of file paths in PosixPath format
+ title (str) A title that groups together images with the same values
+ """
+ for f in files:
+ if f.exists():
+ it = re.search(r'_batch(\d+)', f.name)
+ iteration = int(it.groups()[0]) if it else 0
+ self.task.get_logger().report_image(title=title,
+ series=f.name.replace(it.group(), ''),
+ local_path=str(f),
+ iteration=iteration)
+
+ def log_image_with_boxes(self, image_path, boxes, class_names, image, conf_threshold=0.25):
+ """
+ Draw the bounding boxes on a single image and report the result as a ClearML debug sample.
+
+ arguments:
+ image_path (PosixPath) the path the original image file
+ boxes (list): list of scaled predictions in the format - [xmin, ymin, xmax, ymax, confidence, class]
+ class_names (dict): dict containing mapping of class int to class name
+ image (Tensor): A torch tensor containing the actual image data
+ """
+ if len(self.current_epoch_logged_images) < self.max_imgs_to_log_per_epoch and self.current_epoch >= 0:
+ # Log every bbox_interval times and deduplicate for any intermittend extra eval runs
+ if self.current_epoch % self.bbox_interval == 0 and image_path not in self.current_epoch_logged_images:
+ im = np.ascontiguousarray(np.moveaxis(image.mul(255).clamp(0, 255).byte().cpu().numpy(), 0, 2))
+ annotator = Annotator(im=im, pil=True)
+ for i, (conf, class_nr, box) in enumerate(zip(boxes[:, 4], boxes[:, 5], boxes[:, :4])):
+ color = colors(i)
+
+ class_name = class_names[int(class_nr)]
+ confidence_percentage = round(float(conf) * 100, 2)
+ label = f'{class_name}: {confidence_percentage}%'
+
+ if conf > conf_threshold:
+ annotator.rectangle(box.cpu().numpy(), outline=color)
+ annotator.box_label(box.cpu().numpy(), label=label, color=color)
+
+ annotated_image = annotator.result()
+ self.task.get_logger().report_image(title='Bounding Boxes',
+ series=image_path.name,
+ iteration=self.current_epoch,
+ image=annotated_image)
+ self.current_epoch_logged_images.add(image_path)
diff --git a/ros2_ws/src/yolov3_ros/utils/loggers/clearml/hpo.py b/ros2_ws/src/yolov3_ros/utils/loggers/clearml/hpo.py
new file mode 100644
index 00000000..ee518b0f
--- /dev/null
+++ b/ros2_ws/src/yolov3_ros/utils/loggers/clearml/hpo.py
@@ -0,0 +1,84 @@
+from clearml import Task
+# Connecting ClearML with the current process,
+# from here on everything is logged automatically
+from clearml.automation import HyperParameterOptimizer, UniformParameterRange
+from clearml.automation.optuna import OptimizerOptuna
+
+task = Task.init(project_name='Hyper-Parameter Optimization',
+ task_name='YOLOv5',
+ task_type=Task.TaskTypes.optimizer,
+ reuse_last_task_id=False)
+
+# Example use case:
+optimizer = HyperParameterOptimizer(
+ # This is the experiment we want to optimize
+ base_task_id='',
+ # here we define the hyper-parameters to optimize
+ # Notice: The parameter name should exactly match what you see in the UI: /
+ # For Example, here we see in the base experiment a section Named: "General"
+ # under it a parameter named "batch_size", this becomes "General/batch_size"
+ # If you have `argparse` for example, then arguments will appear under the "Args" section,
+ # and you should instead pass "Args/batch_size"
+ hyper_parameters=[
+ UniformParameterRange('Hyperparameters/lr0', min_value=1e-5, max_value=1e-1),
+ UniformParameterRange('Hyperparameters/lrf', min_value=0.01, max_value=1.0),
+ UniformParameterRange('Hyperparameters/momentum', min_value=0.6, max_value=0.98),
+ UniformParameterRange('Hyperparameters/weight_decay', min_value=0.0, max_value=0.001),
+ UniformParameterRange('Hyperparameters/warmup_epochs', min_value=0.0, max_value=5.0),
+ UniformParameterRange('Hyperparameters/warmup_momentum', min_value=0.0, max_value=0.95),
+ UniformParameterRange('Hyperparameters/warmup_bias_lr', min_value=0.0, max_value=0.2),
+ UniformParameterRange('Hyperparameters/box', min_value=0.02, max_value=0.2),
+ UniformParameterRange('Hyperparameters/cls', min_value=0.2, max_value=4.0),
+ UniformParameterRange('Hyperparameters/cls_pw', min_value=0.5, max_value=2.0),
+ UniformParameterRange('Hyperparameters/obj', min_value=0.2, max_value=4.0),
+ UniformParameterRange('Hyperparameters/obj_pw', min_value=0.5, max_value=2.0),
+ UniformParameterRange('Hyperparameters/iou_t', min_value=0.1, max_value=0.7),
+ UniformParameterRange('Hyperparameters/anchor_t', min_value=2.0, max_value=8.0),
+ UniformParameterRange('Hyperparameters/fl_gamma', min_value=0.0, max_value=4.0),
+ UniformParameterRange('Hyperparameters/hsv_h', min_value=0.0, max_value=0.1),
+ UniformParameterRange('Hyperparameters/hsv_s', min_value=0.0, max_value=0.9),
+ UniformParameterRange('Hyperparameters/hsv_v', min_value=0.0, max_value=0.9),
+ UniformParameterRange('Hyperparameters/degrees', min_value=0.0, max_value=45.0),
+ UniformParameterRange('Hyperparameters/translate', min_value=0.0, max_value=0.9),
+ UniformParameterRange('Hyperparameters/scale', min_value=0.0, max_value=0.9),
+ UniformParameterRange('Hyperparameters/shear', min_value=0.0, max_value=10.0),
+ UniformParameterRange('Hyperparameters/perspective', min_value=0.0, max_value=0.001),
+ UniformParameterRange('Hyperparameters/flipud', min_value=0.0, max_value=1.0),
+ UniformParameterRange('Hyperparameters/fliplr', min_value=0.0, max_value=1.0),
+ UniformParameterRange('Hyperparameters/mosaic', min_value=0.0, max_value=1.0),
+ UniformParameterRange('Hyperparameters/mixup', min_value=0.0, max_value=1.0),
+ UniformParameterRange('Hyperparameters/copy_paste', min_value=0.0, max_value=1.0)],
+ # this is the objective metric we want to maximize/minimize
+ objective_metric_title='metrics',
+ objective_metric_series='mAP_0.5',
+ # now we decide if we want to maximize it or minimize it (accuracy we maximize)
+ objective_metric_sign='max',
+ # let us limit the number of concurrent experiments,
+ # this in turn will make sure we do dont bombard the scheduler with experiments.
+ # if we have an auto-scaler connected, this, by proxy, will limit the number of machine
+ max_number_of_concurrent_tasks=1,
+ # this is the optimizer class (actually doing the optimization)
+ # Currently, we can choose from GridSearch, RandomSearch or OptimizerBOHB (Bayesian optimization Hyper-Band)
+ optimizer_class=OptimizerOptuna,
+ # If specified only the top K performing Tasks will be kept, the others will be automatically archived
+ save_top_k_tasks_only=5, # 5,
+ compute_time_limit=None,
+ total_max_jobs=20,
+ min_iteration_per_job=None,
+ max_iteration_per_job=None,
+)
+
+# report every 10 seconds, this is way too often, but we are testing here
+optimizer.set_report_period(10 / 60)
+# You can also use the line below instead to run all the optimizer tasks locally, without using queues or agent
+# an_optimizer.start_locally(job_complete_callback=job_complete_callback)
+# set the time limit for the optimization process (2 hours)
+optimizer.set_time_limit(in_minutes=120.0)
+# Start the optimization process in the local environment
+optimizer.start_locally()
+# wait until process is done (notice we are controlling the optimization process in the background)
+optimizer.wait()
+# make sure background optimization stopped
+optimizer.stop()
+
+print('We are done, good bye')
diff --git a/ros2_ws/src/yolov3_ros/utils/loggers/comet/README.md b/ros2_ws/src/yolov3_ros/utils/loggers/comet/README.md
new file mode 100644
index 00000000..4090cf93
--- /dev/null
+++ b/ros2_ws/src/yolov3_ros/utils/loggers/comet/README.md
@@ -0,0 +1,284 @@
+
+
+# YOLOv5 with Comet
+
+This guide will cover how to use YOLOv5 with [Comet](https://bit.ly/yolov5-readme-comet2)
+
+# About Comet
+
+Comet builds tools that help data scientists, engineers, and team leaders accelerate and optimize machine learning and
+deep learning models.
+
+Track and visualize model metrics in real time, save your hyperparameters, datasets, and model checkpoints, and
+visualize your model predictions
+with [Comet Custom Panels](https://www.comet.com/docs/v2/guides/comet-dashboard/code-panels/about-panels/?utm_source=yolov5&utm_medium=partner&utm_campaign=partner_yolov5_2022&utm_content=github)!
+Comet makes sure you never lose track of your work and makes it easy to share results and collaborate across teams of
+all sizes!
+
+# Getting Started
+
+## Install Comet
+
+```shell
+pip install comet_ml
+```
+
+## Configure Comet Credentials
+
+There are two ways to configure Comet with YOLOv5.
+
+You can either set your credentials through environment variables
+
+**Environment Variables**
+
+```shell
+export COMET_API_KEY=
+export COMET_PROJECT_NAME= # This will default to 'yolov5'
+```
+
+Or create a `.comet.config` file in your working directory and set your credentials there.
+
+**Comet Configuration File**
+
+```
+[comet]
+api_key=
+project_name= # This will default to 'yolov5'
+```
+
+## Run the Training Script
+
+```shell
+# Train YOLOv5s on COCO128 for 5 epochs
+python train.py --img 640 --batch 16 --epochs 5 --data coco128.yaml --weights yolov5s.pt
+```
+
+That's it! Comet will automatically log your hyperparameters, command line arguments, training and validation metrics.
+You can visualize and analyze your runs in the Comet UI
+
+
+
+# Try out an Example!
+
+Check out an example of
+a [completed run here](https://www.comet.com/examples/comet-example-yolov5/a0e29e0e9b984e4a822db2a62d0cb357?experiment-tab=chart&showOutliers=true&smoothing=0&transformY=smoothing&xAxis=step&utm_source=yolov5&utm_medium=partner&utm_campaign=partner_yolov5_2022&utm_content=github)
+
+Or better yet, try it out yourself in this Colab Notebook
+
+[](https://colab.research.google.com/drive/1RG0WOQyxlDlo5Km8GogJpIEJlg_5lyYO?usp=sharing)
+
+# Log automatically
+
+By default, Comet will log the following items
+
+## Metrics
+
+- Box Loss, Object Loss, Classification Loss for the training and validation data
+- mAP_0.5, mAP_0.5:0.95 metrics for the validation data.
+- Precision and Recall for the validation data
+
+## Parameters
+
+- Model Hyperparameters
+- All parameters passed through the command line options
+
+## Visualizations
+
+- Confusion Matrix of the model predictions on the validation data
+- Plots for the PR and F1 curves across all classes
+- Correlogram of the Class Labels
+
+# Configure Comet Logging
+
+Comet can be configured to log additional data either through command line flags passed to the training script
+or through environment variables.
+
+```shell
+export COMET_MODE=online # Set whether to run Comet in 'online' or 'offline' mode. Defaults to online
+export COMET_MODEL_NAME= #Set the name for the saved model. Defaults to yolov5
+export COMET_LOG_CONFUSION_MATRIX=false # Set to disable logging a Comet Confusion Matrix. Defaults to true
+export COMET_MAX_IMAGE_UPLOADS= # Controls how many total image predictions to log to Comet. Defaults to 100.
+export COMET_LOG_PER_CLASS_METRICS=true # Set to log evaluation metrics for each detected class at the end of training. Defaults to false
+export COMET_DEFAULT_CHECKPOINT_FILENAME= # Set this if you would like to resume training from a different checkpoint. Defaults to 'last.pt'
+export COMET_LOG_BATCH_LEVEL_METRICS=true # Set this if you would like to log training metrics at the batch level. Defaults to false.
+export COMET_LOG_PREDICTIONS=true # Set this to false to disable logging model predictions
+```
+
+## Logging Checkpoints with Comet
+
+Logging Models to Comet is disabled by default. To enable it, pass the `save-period` argument to the training script.
+This will save the
+logged checkpoints to Comet based on the interval value provided by `save-period`
+
+```shell
+python train.py \
+--img 640 \
+--batch 16 \
+--epochs 5 \
+--data coco128.yaml \
+--weights yolov5s.pt \
+--save-period 1
+```
+
+## Logging Model Predictions
+
+By default, model predictions (images, ground truth labels and bounding boxes) will be logged to Comet.
+
+You can control the frequency of logged predictions and the associated images by passing the `bbox_interval` command
+line argument. Predictions can be visualized using Comet's Object Detection Custom Panel. This frequency corresponds to
+every Nth batch of data per epoch. In the example below, we are logging every 2nd batch of data for each epoch.
+
+**Note:** The YOLOv5 validation dataloader will default to a batch size of 32, so you will have to set the logging
+frequency accordingly.
+
+Here is
+an [example project using the Panel](https://www.comet.com/examples/comet-example-yolov5?shareable=YcwMiJaZSXfcEXpGOHDD12vA1&utm_source=yolov5&utm_medium=partner&utm_campaign=partner_yolov5_2022&utm_content=github)
+
+```shell
+python train.py \
+--img 640 \
+--batch 16 \
+--epochs 5 \
+--data coco128.yaml \
+--weights yolov5s.pt \
+--bbox_interval 2
+```
+
+### Controlling the number of Prediction Images logged to Comet
+
+When logging predictions from YOLOv5, Comet will log the images associated with each set of predictions. By default a
+maximum of 100 validation images are logged. You can increase or decrease this number using
+the `COMET_MAX_IMAGE_UPLOADS` environment variable.
+
+```shell
+env COMET_MAX_IMAGE_UPLOADS=200 python train.py \
+--img 640 \
+--batch 16 \
+--epochs 5 \
+--data coco128.yaml \
+--weights yolov5s.pt \
+--bbox_interval 1
+```
+
+### Logging Class Level Metrics
+
+Use the `COMET_LOG_PER_CLASS_METRICS` environment variable to log mAP, precision, recall, f1 for each class.
+
+```shell
+env COMET_LOG_PER_CLASS_METRICS=true python train.py \
+--img 640 \
+--batch 16 \
+--epochs 5 \
+--data coco128.yaml \
+--weights yolov5s.pt
+```
+
+## Uploading a Dataset to Comet Artifacts
+
+If you would like to store your data
+using [Comet Artifacts](https://www.comet.com/docs/v2/guides/data-management/using-artifacts/#learn-more?utm_source=yolov5&utm_medium=partner&utm_campaign=partner_yolov5_2022&utm_content=github),
+you can do so using the `upload_dataset` flag.
+
+The dataset be organized in the way described in
+the [YOLOv5 documentation](https://docs.ultralytics.com/tutorials/train-custom-datasets/#3-organize-directories). The
+dataset config `yaml` file must follow the same format as that of the `coco128.yaml` file.
+
+```shell
+python train.py \
+--img 640 \
+--batch 16 \
+--epochs 5 \
+--data coco128.yaml \
+--weights yolov5s.pt \
+--upload_dataset
+```
+
+You can find the uploaded dataset in the Artifacts tab in your Comet Workspace
+
+
+You can preview the data directly in the Comet UI.
+
+
+Artifacts are versioned and also support adding metadata about the dataset. Comet will automatically log the metadata
+from your dataset `yaml` file
+
+
+### Using a saved Artifact
+
+If you would like to use a dataset from Comet Artifacts, set the `path` variable in your dataset `yaml` file to point to
+the following Artifact resource URL.
+
+```
+# contents of artifact.yaml file
+path: "comet:///:"
+```
+
+Then pass this file to your training script in the following way
+
+```shell
+python train.py \
+--img 640 \
+--batch 16 \
+--epochs 5 \
+--data artifact.yaml \
+--weights yolov5s.pt
+```
+
+Artifacts also allow you to track the lineage of data as it flows through your Experimentation workflow. Here you can
+see a graph that shows you all the experiments that have used your uploaded dataset.
+
+
+## Resuming a Training Run
+
+If your training run is interrupted for any reason, e.g. disrupted internet connection, you can resume the run using
+the `resume` flag and the Comet Run Path.
+
+The Run Path has the following format `comet:////`.
+
+This will restore the run to its state before the interruption, which includes restoring the model from a checkpoint,
+restoring all hyperparameters and training arguments and downloading Comet dataset Artifacts if they were used in the
+original run. The resumed run will continue logging to the existing Experiment in the Comet UI
+
+```shell
+python train.py \
+--resume "comet://"
+```
+
+## Hyperparameter Search with the Comet Optimizer
+
+YOLOv5 is also integrated with Comet's Optimizer, making is simple to visualize hyperparameter sweeps in the Comet UI.
+
+### Configuring an Optimizer Sweep
+
+To configure the Comet Optimizer, you will have to create a JSON file with the information about the sweep. An example
+file has been provided in `utils/loggers/comet/optimizer_config.json`
+
+```shell
+python utils/loggers/comet/hpo.py \
+ --comet_optimizer_config "utils/loggers/comet/optimizer_config.json"
+```
+
+The `hpo.py` script accepts the same arguments as `train.py`. If you wish to pass additional arguments to your sweep
+simply add them after
+the script.
+
+```shell
+python utils/loggers/comet/hpo.py \
+ --comet_optimizer_config "utils/loggers/comet/optimizer_config.json" \
+ --save-period 1 \
+ --bbox_interval 1
+```
+
+### Running a Sweep in Parallel
+
+```shell
+comet optimizer -j utils/loggers/comet/hpo.py \
+ utils/loggers/comet/optimizer_config.json"
+```
+
+### Visualizing Results
+
+Comet provides a number of ways to visualize the results of your sweep. Take a look at
+a [project with a completed sweep here](https://www.comet.com/examples/comet-example-yolov5/view/PrlArHGuuhDTKC1UuBmTtOSXD/panels?utm_source=yolov5&utm_medium=partner&utm_campaign=partner_yolov5_2022&utm_content=github)
+
+
diff --git a/ros2_ws/src/yolov3_ros/utils/loggers/comet/__init__.py b/ros2_ws/src/yolov3_ros/utils/loggers/comet/__init__.py
new file mode 100644
index 00000000..d4599841
--- /dev/null
+++ b/ros2_ws/src/yolov3_ros/utils/loggers/comet/__init__.py
@@ -0,0 +1,508 @@
+import glob
+import json
+import logging
+import os
+import sys
+from pathlib import Path
+
+logger = logging.getLogger(__name__)
+
+FILE = Path(__file__).resolve()
+ROOT = FILE.parents[3] # YOLOv5 root directory
+if str(ROOT) not in sys.path:
+ sys.path.append(str(ROOT)) # add ROOT to PATH
+
+try:
+ import comet_ml
+
+ # Project Configuration
+ config = comet_ml.config.get_config()
+ COMET_PROJECT_NAME = config.get_string(os.getenv('COMET_PROJECT_NAME'), 'comet.project_name', default='yolov5')
+except (ModuleNotFoundError, ImportError):
+ comet_ml = None
+ COMET_PROJECT_NAME = None
+
+import PIL
+import torch
+import torchvision.transforms as T
+import yaml
+
+from utils.dataloaders import img2label_paths
+from utils.general import check_dataset, scale_boxes, xywh2xyxy
+from utils.metrics import box_iou
+
+COMET_PREFIX = 'comet://'
+
+COMET_MODE = os.getenv('COMET_MODE', 'online')
+
+# Model Saving Settings
+COMET_MODEL_NAME = os.getenv('COMET_MODEL_NAME', 'yolov5')
+
+# Dataset Artifact Settings
+COMET_UPLOAD_DATASET = os.getenv('COMET_UPLOAD_DATASET', 'false').lower() == 'true'
+
+# Evaluation Settings
+COMET_LOG_CONFUSION_MATRIX = os.getenv('COMET_LOG_CONFUSION_MATRIX', 'true').lower() == 'true'
+COMET_LOG_PREDICTIONS = os.getenv('COMET_LOG_PREDICTIONS', 'true').lower() == 'true'
+COMET_MAX_IMAGE_UPLOADS = int(os.getenv('COMET_MAX_IMAGE_UPLOADS', 100))
+
+# Confusion Matrix Settings
+CONF_THRES = float(os.getenv('CONF_THRES', 0.001))
+IOU_THRES = float(os.getenv('IOU_THRES', 0.6))
+
+# Batch Logging Settings
+COMET_LOG_BATCH_METRICS = os.getenv('COMET_LOG_BATCH_METRICS', 'false').lower() == 'true'
+COMET_BATCH_LOGGING_INTERVAL = os.getenv('COMET_BATCH_LOGGING_INTERVAL', 1)
+COMET_PREDICTION_LOGGING_INTERVAL = os.getenv('COMET_PREDICTION_LOGGING_INTERVAL', 1)
+COMET_LOG_PER_CLASS_METRICS = os.getenv('COMET_LOG_PER_CLASS_METRICS', 'false').lower() == 'true'
+
+RANK = int(os.getenv('RANK', -1))
+
+to_pil = T.ToPILImage()
+
+
+class CometLogger:
+ """Log metrics, parameters, source code, models and much more
+ with Comet
+ """
+
+ def __init__(self, opt, hyp, run_id=None, job_type='Training', **experiment_kwargs) -> None:
+ self.job_type = job_type
+ self.opt = opt
+ self.hyp = hyp
+
+ # Comet Flags
+ self.comet_mode = COMET_MODE
+
+ self.save_model = opt.save_period > -1
+ self.model_name = COMET_MODEL_NAME
+
+ # Batch Logging Settings
+ self.log_batch_metrics = COMET_LOG_BATCH_METRICS
+ self.comet_log_batch_interval = COMET_BATCH_LOGGING_INTERVAL
+
+ # Dataset Artifact Settings
+ self.upload_dataset = self.opt.upload_dataset if self.opt.upload_dataset else COMET_UPLOAD_DATASET
+ self.resume = self.opt.resume
+
+ # Default parameters to pass to Experiment objects
+ self.default_experiment_kwargs = {
+ 'log_code': False,
+ 'log_env_gpu': True,
+ 'log_env_cpu': True,
+ 'project_name': COMET_PROJECT_NAME,}
+ self.default_experiment_kwargs.update(experiment_kwargs)
+ self.experiment = self._get_experiment(self.comet_mode, run_id)
+
+ self.data_dict = self.check_dataset(self.opt.data)
+ self.class_names = self.data_dict['names']
+ self.num_classes = self.data_dict['nc']
+
+ self.logged_images_count = 0
+ self.max_images = COMET_MAX_IMAGE_UPLOADS
+
+ if run_id is None:
+ self.experiment.log_other('Created from', 'YOLOv5')
+ if not isinstance(self.experiment, comet_ml.OfflineExperiment):
+ workspace, project_name, experiment_id = self.experiment.url.split('/')[-3:]
+ self.experiment.log_other(
+ 'Run Path',
+ f'{workspace}/{project_name}/{experiment_id}',
+ )
+ self.log_parameters(vars(opt))
+ self.log_parameters(self.opt.hyp)
+ self.log_asset_data(
+ self.opt.hyp,
+ name='hyperparameters.json',
+ metadata={'type': 'hyp-config-file'},
+ )
+ self.log_asset(
+ f'{self.opt.save_dir}/opt.yaml',
+ metadata={'type': 'opt-config-file'},
+ )
+
+ self.comet_log_confusion_matrix = COMET_LOG_CONFUSION_MATRIX
+
+ if hasattr(self.opt, 'conf_thres'):
+ self.conf_thres = self.opt.conf_thres
+ else:
+ self.conf_thres = CONF_THRES
+ if hasattr(self.opt, 'iou_thres'):
+ self.iou_thres = self.opt.iou_thres
+ else:
+ self.iou_thres = IOU_THRES
+
+ self.log_parameters({'val_iou_threshold': self.iou_thres, 'val_conf_threshold': self.conf_thres})
+
+ self.comet_log_predictions = COMET_LOG_PREDICTIONS
+ if self.opt.bbox_interval == -1:
+ self.comet_log_prediction_interval = 1 if self.opt.epochs < 10 else self.opt.epochs // 10
+ else:
+ self.comet_log_prediction_interval = self.opt.bbox_interval
+
+ if self.comet_log_predictions:
+ self.metadata_dict = {}
+ self.logged_image_names = []
+
+ self.comet_log_per_class_metrics = COMET_LOG_PER_CLASS_METRICS
+
+ self.experiment.log_others({
+ 'comet_mode': COMET_MODE,
+ 'comet_max_image_uploads': COMET_MAX_IMAGE_UPLOADS,
+ 'comet_log_per_class_metrics': COMET_LOG_PER_CLASS_METRICS,
+ 'comet_log_batch_metrics': COMET_LOG_BATCH_METRICS,
+ 'comet_log_confusion_matrix': COMET_LOG_CONFUSION_MATRIX,
+ 'comet_model_name': COMET_MODEL_NAME,})
+
+ # Check if running the Experiment with the Comet Optimizer
+ if hasattr(self.opt, 'comet_optimizer_id'):
+ self.experiment.log_other('optimizer_id', self.opt.comet_optimizer_id)
+ self.experiment.log_other('optimizer_objective', self.opt.comet_optimizer_objective)
+ self.experiment.log_other('optimizer_metric', self.opt.comet_optimizer_metric)
+ self.experiment.log_other('optimizer_parameters', json.dumps(self.hyp))
+
+ def _get_experiment(self, mode, experiment_id=None):
+ if mode == 'offline':
+ if experiment_id is not None:
+ return comet_ml.ExistingOfflineExperiment(
+ previous_experiment=experiment_id,
+ **self.default_experiment_kwargs,
+ )
+
+ return comet_ml.OfflineExperiment(**self.default_experiment_kwargs,)
+
+ else:
+ try:
+ if experiment_id is not None:
+ return comet_ml.ExistingExperiment(
+ previous_experiment=experiment_id,
+ **self.default_experiment_kwargs,
+ )
+
+ return comet_ml.Experiment(**self.default_experiment_kwargs)
+
+ except ValueError:
+ logger.warning('COMET WARNING: '
+ 'Comet credentials have not been set. '
+ 'Comet will default to offline logging. '
+ 'Please set your credentials to enable online logging.')
+ return self._get_experiment('offline', experiment_id)
+
+ return
+
+ def log_metrics(self, log_dict, **kwargs):
+ self.experiment.log_metrics(log_dict, **kwargs)
+
+ def log_parameters(self, log_dict, **kwargs):
+ self.experiment.log_parameters(log_dict, **kwargs)
+
+ def log_asset(self, asset_path, **kwargs):
+ self.experiment.log_asset(asset_path, **kwargs)
+
+ def log_asset_data(self, asset, **kwargs):
+ self.experiment.log_asset_data(asset, **kwargs)
+
+ def log_image(self, img, **kwargs):
+ self.experiment.log_image(img, **kwargs)
+
+ def log_model(self, path, opt, epoch, fitness_score, best_model=False):
+ if not self.save_model:
+ return
+
+ model_metadata = {
+ 'fitness_score': fitness_score[-1],
+ 'epochs_trained': epoch + 1,
+ 'save_period': opt.save_period,
+ 'total_epochs': opt.epochs,}
+
+ model_files = glob.glob(f'{path}/*.pt')
+ for model_path in model_files:
+ name = Path(model_path).name
+
+ self.experiment.log_model(
+ self.model_name,
+ file_or_folder=model_path,
+ file_name=name,
+ metadata=model_metadata,
+ overwrite=True,
+ )
+
+ def check_dataset(self, data_file):
+ with open(data_file) as f:
+ data_config = yaml.safe_load(f)
+
+ if data_config['path'].startswith(COMET_PREFIX):
+ path = data_config['path'].replace(COMET_PREFIX, '')
+ data_dict = self.download_dataset_artifact(path)
+
+ return data_dict
+
+ self.log_asset(self.opt.data, metadata={'type': 'data-config-file'})
+
+ return check_dataset(data_file)
+
+ def log_predictions(self, image, labelsn, path, shape, predn):
+ if self.logged_images_count >= self.max_images:
+ return
+ detections = predn[predn[:, 4] > self.conf_thres]
+ iou = box_iou(labelsn[:, 1:], detections[:, :4])
+ mask, _ = torch.where(iou > self.iou_thres)
+ if len(mask) == 0:
+ return
+
+ filtered_detections = detections[mask]
+ filtered_labels = labelsn[mask]
+
+ image_id = path.split('/')[-1].split('.')[0]
+ image_name = f'{image_id}_curr_epoch_{self.experiment.curr_epoch}'
+ if image_name not in self.logged_image_names:
+ native_scale_image = PIL.Image.open(path)
+ self.log_image(native_scale_image, name=image_name)
+ self.logged_image_names.append(image_name)
+
+ metadata = []
+ for cls, *xyxy in filtered_labels.tolist():
+ metadata.append({
+ 'label': f'{self.class_names[int(cls)]}-gt',
+ 'score': 100,
+ 'box': {
+ 'x': xyxy[0],
+ 'y': xyxy[1],
+ 'x2': xyxy[2],
+ 'y2': xyxy[3]},})
+ for *xyxy, conf, cls in filtered_detections.tolist():
+ metadata.append({
+ 'label': f'{self.class_names[int(cls)]}',
+ 'score': conf * 100,
+ 'box': {
+ 'x': xyxy[0],
+ 'y': xyxy[1],
+ 'x2': xyxy[2],
+ 'y2': xyxy[3]},})
+
+ self.metadata_dict[image_name] = metadata
+ self.logged_images_count += 1
+
+ return
+
+ def preprocess_prediction(self, image, labels, shape, pred):
+ nl, _ = labels.shape[0], pred.shape[0]
+
+ # Predictions
+ if self.opt.single_cls:
+ pred[:, 5] = 0
+
+ predn = pred.clone()
+ scale_boxes(image.shape[1:], predn[:, :4], shape[0], shape[1])
+
+ labelsn = None
+ if nl:
+ tbox = xywh2xyxy(labels[:, 1:5]) # target boxes
+ scale_boxes(image.shape[1:], tbox, shape[0], shape[1]) # native-space labels
+ labelsn = torch.cat((labels[:, 0:1], tbox), 1) # native-space labels
+ scale_boxes(image.shape[1:], predn[:, :4], shape[0], shape[1]) # native-space pred
+
+ return predn, labelsn
+
+ def add_assets_to_artifact(self, artifact, path, asset_path, split):
+ img_paths = sorted(glob.glob(f'{asset_path}/*'))
+ label_paths = img2label_paths(img_paths)
+
+ for image_file, label_file in zip(img_paths, label_paths):
+ image_logical_path, label_logical_path = map(lambda x: os.path.relpath(x, path), [image_file, label_file])
+
+ try:
+ artifact.add(image_file, logical_path=image_logical_path, metadata={'split': split})
+ artifact.add(label_file, logical_path=label_logical_path, metadata={'split': split})
+ except ValueError as e:
+ logger.error('COMET ERROR: Error adding file to Artifact. Skipping file.')
+ logger.error(f'COMET ERROR: {e}')
+ continue
+
+ return artifact
+
+ def upload_dataset_artifact(self):
+ dataset_name = self.data_dict.get('dataset_name', 'yolov5-dataset')
+ path = str((ROOT / Path(self.data_dict['path'])).resolve())
+
+ metadata = self.data_dict.copy()
+ for key in ['train', 'val', 'test']:
+ split_path = metadata.get(key)
+ if split_path is not None:
+ metadata[key] = split_path.replace(path, '')
+
+ artifact = comet_ml.Artifact(name=dataset_name, artifact_type='dataset', metadata=metadata)
+ for key in metadata.keys():
+ if key in ['train', 'val', 'test']:
+ if isinstance(self.upload_dataset, str) and (key != self.upload_dataset):
+ continue
+
+ asset_path = self.data_dict.get(key)
+ if asset_path is not None:
+ artifact = self.add_assets_to_artifact(artifact, path, asset_path, key)
+
+ self.experiment.log_artifact(artifact)
+
+ return
+
+ def download_dataset_artifact(self, artifact_path):
+ logged_artifact = self.experiment.get_artifact(artifact_path)
+ artifact_save_dir = str(Path(self.opt.save_dir) / logged_artifact.name)
+ logged_artifact.download(artifact_save_dir)
+
+ metadata = logged_artifact.metadata
+ data_dict = metadata.copy()
+ data_dict['path'] = artifact_save_dir
+
+ metadata_names = metadata.get('names')
+ if type(metadata_names) == dict:
+ data_dict['names'] = {int(k): v for k, v in metadata.get('names').items()}
+ elif type(metadata_names) == list:
+ data_dict['names'] = {int(k): v for k, v in zip(range(len(metadata_names)), metadata_names)}
+ else:
+ raise "Invalid 'names' field in dataset yaml file. Please use a list or dictionary"
+
+ data_dict = self.update_data_paths(data_dict)
+ return data_dict
+
+ def update_data_paths(self, data_dict):
+ path = data_dict.get('path', '')
+
+ for split in ['train', 'val', 'test']:
+ if data_dict.get(split):
+ split_path = data_dict.get(split)
+ data_dict[split] = (f'{path}/{split_path}' if isinstance(split, str) else [
+ f'{path}/{x}' for x in split_path])
+
+ return data_dict
+
+ def on_pretrain_routine_end(self, paths):
+ if self.opt.resume:
+ return
+
+ for path in paths:
+ self.log_asset(str(path))
+
+ if self.upload_dataset:
+ if not self.resume:
+ self.upload_dataset_artifact()
+
+ return
+
+ def on_train_start(self):
+ self.log_parameters(self.hyp)
+
+ def on_train_epoch_start(self):
+ return
+
+ def on_train_epoch_end(self, epoch):
+ self.experiment.curr_epoch = epoch
+
+ return
+
+ def on_train_batch_start(self):
+ return
+
+ def on_train_batch_end(self, log_dict, step):
+ self.experiment.curr_step = step
+ if self.log_batch_metrics and (step % self.comet_log_batch_interval == 0):
+ self.log_metrics(log_dict, step=step)
+
+ return
+
+ def on_train_end(self, files, save_dir, last, best, epoch, results):
+ if self.comet_log_predictions:
+ curr_epoch = self.experiment.curr_epoch
+ self.experiment.log_asset_data(self.metadata_dict, 'image-metadata.json', epoch=curr_epoch)
+
+ for f in files:
+ self.log_asset(f, metadata={'epoch': epoch})
+ self.log_asset(f'{save_dir}/results.csv', metadata={'epoch': epoch})
+
+ if not self.opt.evolve:
+ model_path = str(best if best.exists() else last)
+ name = Path(model_path).name
+ if self.save_model:
+ self.experiment.log_model(
+ self.model_name,
+ file_or_folder=model_path,
+ file_name=name,
+ overwrite=True,
+ )
+
+ # Check if running Experiment with Comet Optimizer
+ if hasattr(self.opt, 'comet_optimizer_id'):
+ metric = results.get(self.opt.comet_optimizer_metric)
+ self.experiment.log_other('optimizer_metric_value', metric)
+
+ self.finish_run()
+
+ def on_val_start(self):
+ return
+
+ def on_val_batch_start(self):
+ return
+
+ def on_val_batch_end(self, batch_i, images, targets, paths, shapes, outputs):
+ if not (self.comet_log_predictions and ((batch_i + 1) % self.comet_log_prediction_interval == 0)):
+ return
+
+ for si, pred in enumerate(outputs):
+ if len(pred) == 0:
+ continue
+
+ image = images[si]
+ labels = targets[targets[:, 0] == si, 1:]
+ shape = shapes[si]
+ path = paths[si]
+ predn, labelsn = self.preprocess_prediction(image, labels, shape, pred)
+ if labelsn is not None:
+ self.log_predictions(image, labelsn, path, shape, predn)
+
+ return
+
+ def on_val_end(self, nt, tp, fp, p, r, f1, ap, ap50, ap_class, confusion_matrix):
+ if self.comet_log_per_class_metrics:
+ if self.num_classes > 1:
+ for i, c in enumerate(ap_class):
+ class_name = self.class_names[c]
+ self.experiment.log_metrics(
+ {
+ 'mAP@.5': ap50[i],
+ 'mAP@.5:.95': ap[i],
+ 'precision': p[i],
+ 'recall': r[i],
+ 'f1': f1[i],
+ 'true_positives': tp[i],
+ 'false_positives': fp[i],
+ 'support': nt[c]},
+ prefix=class_name)
+
+ if self.comet_log_confusion_matrix:
+ epoch = self.experiment.curr_epoch
+ class_names = list(self.class_names.values())
+ class_names.append('background')
+ num_classes = len(class_names)
+
+ self.experiment.log_confusion_matrix(
+ matrix=confusion_matrix.matrix,
+ max_categories=num_classes,
+ labels=class_names,
+ epoch=epoch,
+ column_label='Actual Category',
+ row_label='Predicted Category',
+ file_name=f'confusion-matrix-epoch-{epoch}.json',
+ )
+
+ def on_fit_epoch_end(self, result, epoch):
+ self.log_metrics(result, epoch=epoch)
+
+ def on_model_save(self, last, epoch, final_epoch, best_fitness, fi):
+ if ((epoch + 1) % self.opt.save_period == 0 and not final_epoch) and self.opt.save_period != -1:
+ self.log_model(last.parent, self.opt, epoch, fi, best_model=best_fitness == fi)
+
+ def on_params_update(self, params):
+ self.log_parameters(params)
+
+ def finish_run(self):
+ self.experiment.end()
diff --git a/ros2_ws/src/yolov3_ros/utils/loggers/comet/comet_utils.py b/ros2_ws/src/yolov3_ros/utils/loggers/comet/comet_utils.py
new file mode 100644
index 00000000..27600761
--- /dev/null
+++ b/ros2_ws/src/yolov3_ros/utils/loggers/comet/comet_utils.py
@@ -0,0 +1,150 @@
+import logging
+import os
+from urllib.parse import urlparse
+
+try:
+ import comet_ml
+except (ModuleNotFoundError, ImportError):
+ comet_ml = None
+
+import yaml
+
+logger = logging.getLogger(__name__)
+
+COMET_PREFIX = 'comet://'
+COMET_MODEL_NAME = os.getenv('COMET_MODEL_NAME', 'yolov5')
+COMET_DEFAULT_CHECKPOINT_FILENAME = os.getenv('COMET_DEFAULT_CHECKPOINT_FILENAME', 'last.pt')
+
+
+def download_model_checkpoint(opt, experiment):
+ model_dir = f'{opt.project}/{experiment.name}'
+ os.makedirs(model_dir, exist_ok=True)
+
+ model_name = COMET_MODEL_NAME
+ model_asset_list = experiment.get_model_asset_list(model_name)
+
+ if len(model_asset_list) == 0:
+ logger.error(f'COMET ERROR: No checkpoints found for model name : {model_name}')
+ return
+
+ model_asset_list = sorted(
+ model_asset_list,
+ key=lambda x: x['step'],
+ reverse=True,
+ )
+ logged_checkpoint_map = {asset['fileName']: asset['assetId'] for asset in model_asset_list}
+
+ resource_url = urlparse(opt.weights)
+ checkpoint_filename = resource_url.query
+
+ if checkpoint_filename:
+ asset_id = logged_checkpoint_map.get(checkpoint_filename)
+ else:
+ asset_id = logged_checkpoint_map.get(COMET_DEFAULT_CHECKPOINT_FILENAME)
+ checkpoint_filename = COMET_DEFAULT_CHECKPOINT_FILENAME
+
+ if asset_id is None:
+ logger.error(f'COMET ERROR: Checkpoint {checkpoint_filename} not found in the given Experiment')
+ return
+
+ try:
+ logger.info(f'COMET INFO: Downloading checkpoint {checkpoint_filename}')
+ asset_filename = checkpoint_filename
+
+ model_binary = experiment.get_asset(asset_id, return_type='binary', stream=False)
+ model_download_path = f'{model_dir}/{asset_filename}'
+ with open(model_download_path, 'wb') as f:
+ f.write(model_binary)
+
+ opt.weights = model_download_path
+
+ except Exception as e:
+ logger.warning('COMET WARNING: Unable to download checkpoint from Comet')
+ logger.exception(e)
+
+
+def set_opt_parameters(opt, experiment):
+ """Update the opts Namespace with parameters
+ from Comet's ExistingExperiment when resuming a run
+
+ Args:
+ opt (argparse.Namespace): Namespace of command line options
+ experiment (comet_ml.APIExperiment): Comet API Experiment object
+ """
+ asset_list = experiment.get_asset_list()
+ resume_string = opt.resume
+
+ for asset in asset_list:
+ if asset['fileName'] == 'opt.yaml':
+ asset_id = asset['assetId']
+ asset_binary = experiment.get_asset(asset_id, return_type='binary', stream=False)
+ opt_dict = yaml.safe_load(asset_binary)
+ for key, value in opt_dict.items():
+ setattr(opt, key, value)
+ opt.resume = resume_string
+
+ # Save hyperparameters to YAML file
+ # Necessary to pass checks in training script
+ save_dir = f'{opt.project}/{experiment.name}'
+ os.makedirs(save_dir, exist_ok=True)
+
+ hyp_yaml_path = f'{save_dir}/hyp.yaml'
+ with open(hyp_yaml_path, 'w') as f:
+ yaml.dump(opt.hyp, f)
+ opt.hyp = hyp_yaml_path
+
+
+def check_comet_weights(opt):
+ """Downloads model weights from Comet and updates the
+ weights path to point to saved weights location
+
+ Args:
+ opt (argparse.Namespace): Command Line arguments passed
+ to YOLOv5 training script
+
+ Returns:
+ None/bool: Return True if weights are successfully downloaded
+ else return None
+ """
+ if comet_ml is None:
+ return
+
+ if isinstance(opt.weights, str):
+ if opt.weights.startswith(COMET_PREFIX):
+ api = comet_ml.API()
+ resource = urlparse(opt.weights)
+ experiment_path = f'{resource.netloc}{resource.path}'
+ experiment = api.get(experiment_path)
+ download_model_checkpoint(opt, experiment)
+ return True
+
+ return None
+
+
+def check_comet_resume(opt):
+ """Restores run parameters to its original state based on the model checkpoint
+ and logged Experiment parameters.
+
+ Args:
+ opt (argparse.Namespace): Command Line arguments passed
+ to YOLOv5 training script
+
+ Returns:
+ None/bool: Return True if the run is restored successfully
+ else return None
+ """
+ if comet_ml is None:
+ return
+
+ if isinstance(opt.resume, str):
+ if opt.resume.startswith(COMET_PREFIX):
+ api = comet_ml.API()
+ resource = urlparse(opt.resume)
+ experiment_path = f'{resource.netloc}{resource.path}'
+ experiment = api.get(experiment_path)
+ set_opt_parameters(opt, experiment)
+ download_model_checkpoint(opt, experiment)
+
+ return True
+
+ return None
diff --git a/ros2_ws/src/yolov3_ros/utils/loggers/comet/hpo.py b/ros2_ws/src/yolov3_ros/utils/loggers/comet/hpo.py
new file mode 100644
index 00000000..fc49115c
--- /dev/null
+++ b/ros2_ws/src/yolov3_ros/utils/loggers/comet/hpo.py
@@ -0,0 +1,118 @@
+import argparse
+import json
+import logging
+import os
+import sys
+from pathlib import Path
+
+import comet_ml
+
+logger = logging.getLogger(__name__)
+
+FILE = Path(__file__).resolve()
+ROOT = FILE.parents[3] # YOLOv5 root directory
+if str(ROOT) not in sys.path:
+ sys.path.append(str(ROOT)) # add ROOT to PATH
+
+from train import train
+from utils.callbacks import Callbacks
+from utils.general import increment_path
+from utils.torch_utils import select_device
+
+# Project Configuration
+config = comet_ml.config.get_config()
+COMET_PROJECT_NAME = config.get_string(os.getenv('COMET_PROJECT_NAME'), 'comet.project_name', default='yolov5')
+
+
+def get_args(known=False):
+ parser = argparse.ArgumentParser()
+ parser.add_argument('--weights', type=str, default=ROOT / 'yolov5s.pt', help='initial weights path')
+ parser.add_argument('--cfg', type=str, default='', help='model.yaml path')
+ parser.add_argument('--data', type=str, default=ROOT / 'data/coco128.yaml', help='dataset.yaml path')
+ parser.add_argument('--hyp', type=str, default=ROOT / 'data/hyps/hyp.scratch-low.yaml', help='hyperparameters path')
+ parser.add_argument('--epochs', type=int, default=300, help='total training epochs')
+ parser.add_argument('--batch-size', type=int, default=16, help='total batch size for all GPUs, -1 for autobatch')
+ parser.add_argument('--imgsz', '--img', '--img-size', type=int, default=640, help='train, val image size (pixels)')
+ parser.add_argument('--rect', action='store_true', help='rectangular training')
+ parser.add_argument('--resume', nargs='?', const=True, default=False, help='resume most recent training')
+ parser.add_argument('--nosave', action='store_true', help='only save final checkpoint')
+ parser.add_argument('--noval', action='store_true', help='only validate final epoch')
+ parser.add_argument('--noautoanchor', action='store_true', help='disable AutoAnchor')
+ parser.add_argument('--noplots', action='store_true', help='save no plot files')
+ parser.add_argument('--evolve', type=int, nargs='?', const=300, help='evolve hyperparameters for x generations')
+ parser.add_argument('--bucket', type=str, default='', help='gsutil bucket')
+ parser.add_argument('--cache', type=str, nargs='?', const='ram', help='--cache images in "ram" (default) or "disk"')
+ parser.add_argument('--image-weights', action='store_true', help='use weighted image selection for training')
+ parser.add_argument('--device', default='', help='cuda device, i.e. 0 or 0,1,2,3 or cpu')
+ parser.add_argument('--multi-scale', action='store_true', help='vary img-size +/- 50%%')
+ parser.add_argument('--single-cls', action='store_true', help='train multi-class data as single-class')
+ parser.add_argument('--optimizer', type=str, choices=['SGD', 'Adam', 'AdamW'], default='SGD', help='optimizer')
+ parser.add_argument('--sync-bn', action='store_true', help='use SyncBatchNorm, only available in DDP mode')
+ parser.add_argument('--workers', type=int, default=8, help='max dataloader workers (per RANK in DDP mode)')
+ parser.add_argument('--project', default=ROOT / 'runs/train', help='save to project/name')
+ parser.add_argument('--name', default='exp', help='save to project/name')
+ parser.add_argument('--exist-ok', action='store_true', help='existing project/name ok, do not increment')
+ parser.add_argument('--quad', action='store_true', help='quad dataloader')
+ parser.add_argument('--cos-lr', action='store_true', help='cosine LR scheduler')
+ parser.add_argument('--label-smoothing', type=float, default=0.0, help='Label smoothing epsilon')
+ parser.add_argument('--patience', type=int, default=100, help='EarlyStopping patience (epochs without improvement)')
+ parser.add_argument('--freeze', nargs='+', type=int, default=[0], help='Freeze layers: backbone=10, first3=0 1 2')
+ parser.add_argument('--save-period', type=int, default=-1, help='Save checkpoint every x epochs (disabled if < 1)')
+ parser.add_argument('--seed', type=int, default=0, help='Global training seed')
+ parser.add_argument('--local_rank', type=int, default=-1, help='Automatic DDP Multi-GPU argument, do not modify')
+
+ # Weights & Biases arguments
+ parser.add_argument('--entity', default=None, help='W&B: Entity')
+ parser.add_argument('--upload_dataset', nargs='?', const=True, default=False, help='W&B: Upload data, "val" option')
+ parser.add_argument('--bbox_interval', type=int, default=-1, help='W&B: Set bounding-box image logging interval')
+ parser.add_argument('--artifact_alias', type=str, default='latest', help='W&B: Version of dataset artifact to use')
+
+ # Comet Arguments
+ parser.add_argument('--comet_optimizer_config', type=str, help='Comet: Path to a Comet Optimizer Config File.')
+ parser.add_argument('--comet_optimizer_id', type=str, help='Comet: ID of the Comet Optimizer sweep.')
+ parser.add_argument('--comet_optimizer_objective', type=str, help="Comet: Set to 'minimize' or 'maximize'.")
+ parser.add_argument('--comet_optimizer_metric', type=str, help='Comet: Metric to Optimize.')
+ parser.add_argument('--comet_optimizer_workers',
+ type=int,
+ default=1,
+ help='Comet: Number of Parallel Workers to use with the Comet Optimizer.')
+
+ return parser.parse_known_args()[0] if known else parser.parse_args()
+
+
+def run(parameters, opt):
+ hyp_dict = {k: v for k, v in parameters.items() if k not in ['epochs', 'batch_size']}
+
+ opt.save_dir = str(increment_path(Path(opt.project) / opt.name, exist_ok=opt.exist_ok or opt.evolve))
+ opt.batch_size = parameters.get('batch_size')
+ opt.epochs = parameters.get('epochs')
+
+ device = select_device(opt.device, batch_size=opt.batch_size)
+ train(hyp_dict, opt, device, callbacks=Callbacks())
+
+
+if __name__ == '__main__':
+ opt = get_args(known=True)
+
+ opt.weights = str(opt.weights)
+ opt.cfg = str(opt.cfg)
+ opt.data = str(opt.data)
+ opt.project = str(opt.project)
+
+ optimizer_id = os.getenv('COMET_OPTIMIZER_ID')
+ if optimizer_id is None:
+ with open(opt.comet_optimizer_config) as f:
+ optimizer_config = json.load(f)
+ optimizer = comet_ml.Optimizer(optimizer_config)
+ else:
+ optimizer = comet_ml.Optimizer(optimizer_id)
+
+ opt.comet_optimizer_id = optimizer.id
+ status = optimizer.status()
+
+ opt.comet_optimizer_objective = status['spec']['objective']
+ opt.comet_optimizer_metric = status['spec']['metric']
+
+ logger.info('COMET INFO: Starting Hyperparameter Sweep')
+ for parameter in optimizer.get_parameters():
+ run(parameter['parameters'], opt)
diff --git a/ros2_ws/src/yolov3_ros/utils/loggers/comet/optimizer_config.json b/ros2_ws/src/yolov3_ros/utils/loggers/comet/optimizer_config.json
new file mode 100644
index 00000000..83ddddab
--- /dev/null
+++ b/ros2_ws/src/yolov3_ros/utils/loggers/comet/optimizer_config.json
@@ -0,0 +1,209 @@
+{
+ "algorithm": "random",
+ "parameters": {
+ "anchor_t": {
+ "type": "discrete",
+ "values": [
+ 2,
+ 8
+ ]
+ },
+ "batch_size": {
+ "type": "discrete",
+ "values": [
+ 16,
+ 32,
+ 64
+ ]
+ },
+ "box": {
+ "type": "discrete",
+ "values": [
+ 0.02,
+ 0.2
+ ]
+ },
+ "cls": {
+ "type": "discrete",
+ "values": [
+ 0.2
+ ]
+ },
+ "cls_pw": {
+ "type": "discrete",
+ "values": [
+ 0.5
+ ]
+ },
+ "copy_paste": {
+ "type": "discrete",
+ "values": [
+ 1
+ ]
+ },
+ "degrees": {
+ "type": "discrete",
+ "values": [
+ 0,
+ 45
+ ]
+ },
+ "epochs": {
+ "type": "discrete",
+ "values": [
+ 5
+ ]
+ },
+ "fl_gamma": {
+ "type": "discrete",
+ "values": [
+ 0
+ ]
+ },
+ "fliplr": {
+ "type": "discrete",
+ "values": [
+ 0
+ ]
+ },
+ "flipud": {
+ "type": "discrete",
+ "values": [
+ 0
+ ]
+ },
+ "hsv_h": {
+ "type": "discrete",
+ "values": [
+ 0
+ ]
+ },
+ "hsv_s": {
+ "type": "discrete",
+ "values": [
+ 0
+ ]
+ },
+ "hsv_v": {
+ "type": "discrete",
+ "values": [
+ 0
+ ]
+ },
+ "iou_t": {
+ "type": "discrete",
+ "values": [
+ 0.7
+ ]
+ },
+ "lr0": {
+ "type": "discrete",
+ "values": [
+ 1e-05,
+ 0.1
+ ]
+ },
+ "lrf": {
+ "type": "discrete",
+ "values": [
+ 0.01,
+ 1
+ ]
+ },
+ "mixup": {
+ "type": "discrete",
+ "values": [
+ 1
+ ]
+ },
+ "momentum": {
+ "type": "discrete",
+ "values": [
+ 0.6
+ ]
+ },
+ "mosaic": {
+ "type": "discrete",
+ "values": [
+ 0
+ ]
+ },
+ "obj": {
+ "type": "discrete",
+ "values": [
+ 0.2
+ ]
+ },
+ "obj_pw": {
+ "type": "discrete",
+ "values": [
+ 0.5
+ ]
+ },
+ "optimizer": {
+ "type": "categorical",
+ "values": [
+ "SGD",
+ "Adam",
+ "AdamW"
+ ]
+ },
+ "perspective": {
+ "type": "discrete",
+ "values": [
+ 0
+ ]
+ },
+ "scale": {
+ "type": "discrete",
+ "values": [
+ 0
+ ]
+ },
+ "shear": {
+ "type": "discrete",
+ "values": [
+ 0
+ ]
+ },
+ "translate": {
+ "type": "discrete",
+ "values": [
+ 0
+ ]
+ },
+ "warmup_bias_lr": {
+ "type": "discrete",
+ "values": [
+ 0,
+ 0.2
+ ]
+ },
+ "warmup_epochs": {
+ "type": "discrete",
+ "values": [
+ 5
+ ]
+ },
+ "warmup_momentum": {
+ "type": "discrete",
+ "values": [
+ 0,
+ 0.95
+ ]
+ },
+ "weight_decay": {
+ "type": "discrete",
+ "values": [
+ 0,
+ 0.001
+ ]
+ }
+ },
+ "spec": {
+ "maxCombo": 0,
+ "metric": "metrics/mAP_0.5",
+ "objective": "maximize"
+ },
+ "trials": 1
+}
diff --git a/ros2_ws/src/yolov3_ros/utils/loggers/wandb/README.md b/ros2_ws/src/yolov3_ros/utils/loggers/wandb/README.md
new file mode 100644
index 00000000..bae57bda
--- /dev/null
+++ b/ros2_ws/src/yolov3_ros/utils/loggers/wandb/README.md
@@ -0,0 +1,147 @@
+📚 This guide explains how to use **Weights & Biases** (W&B) with YOLOv3 🚀. UPDATED 29 September 2021.
+* [About Weights & Biases](#about-weights-&-biases)
+* [First-Time Setup](#first-time-setup)
+* [Viewing runs](#viewing-runs)
+* [Advanced Usage: Dataset Versioning and Evaluation](#advanced-usage)
+* [Reports: Share your work with the world!](#reports)
+
+## About Weights & Biases
+Think of [W&B](https://wandb.ai/site?utm_campaign=repo_yolo_wandbtutorial) like GitHub for machine learning models. With a few lines of code, save everything you need to debug, compare and reproduce your models — architecture, hyperparameters, git commits, model weights, GPU usage, and even datasets and predictions.
+
+Used by top researchers including teams at OpenAI, Lyft, Github, and MILA, W&B is part of the new standard of best practices for machine learning. How W&B can help you optimize your machine learning workflows:
+
+ * [Debug](https://wandb.ai/wandb/getting-started/reports/Visualize-Debug-Machine-Learning-Models--VmlldzoyNzY5MDk#Free-2) model performance in real time
+ * [GPU usage](https://wandb.ai/wandb/getting-started/reports/Visualize-Debug-Machine-Learning-Models--VmlldzoyNzY5MDk#System-4) visualized automatically
+ * [Custom charts](https://wandb.ai/wandb/customizable-charts/reports/Powerful-Custom-Charts-To-Debug-Model-Peformance--VmlldzoyNzY4ODI) for powerful, extensible visualization
+ * [Share insights](https://wandb.ai/wandb/getting-started/reports/Visualize-Debug-Machine-Learning-Models--VmlldzoyNzY5MDk#Share-8) interactively with collaborators
+ * [Optimize hyperparameters](https://docs.wandb.com/sweeps) efficiently
+ * [Track](https://docs.wandb.com/artifacts) datasets, pipelines, and production models
+
+## First-Time Setup
+
+ Toggle Details
+When you first train, W&B will prompt you to create a new account and will generate an **API key** for you. If you are an existing user you can retrieve your key from https://wandb.ai/authorize. This key is used to tell W&B where to log your data. You only need to supply your key once, and then it is remembered on the same device.
+
+W&B will create a cloud **project** (default is 'YOLOv3') for your training runs, and each new training run will be provided a unique run **name** within that project as project/name. You can also manually set your project and run name as:
+
+ ```shell
+ $ python train.py --project ... --name ...
+ ```
+
+YOLOv3 notebook example: 
+
+
+
+
+
+## Viewing Runs
+
+ Toggle Details
+Run information streams from your environment to the W&B cloud console as you train. This allows you to monitor and even cancel runs in realtime . All important information is logged:
+
+ * Training & Validation losses
+ * Metrics: Precision, Recall, mAP@0.5, mAP@0.5:0.95
+ * Learning Rate over time
+ * A bounding box debugging panel, showing the training progress over time
+ * GPU: Type, **GPU Utilization**, power, temperature, **CUDA memory usage**
+ * System: Disk I/0, CPU utilization, RAM memory usage
+ * Your trained model as W&B Artifact
+ * Environment: OS and Python types, Git repository and state, **training command**
+
+
+
+
+
+
+## Advanced Usage
+You can leverage W&B artifacts and Tables integration to easily visualize and manage your datasets, models and training evaluations. Here are some quick examples to get you started.
+
+ 1. Visualize and Version Datasets
+ Log, visualize, dynamically query, and understand your data with W&B Tables. You can use the following command to log your dataset as a W&B Table. This will generate a {dataset}_wandb.yaml file which can be used to train from dataset artifact.
+
+ Usage
+ Code $ python utils/logger/wandb/log_dataset.py --project ... --name ... --data ..
+
+ 
+
+
+ 2: Train and Log Evaluation simultaneousy
+ This is an extension of the previous section, but it'll also training after uploading the dataset. This also evaluation Table
+ Evaluation table compares your predictions and ground truths across the validation set for each epoch. It uses the references to the already uploaded datasets,
+ so no images will be uploaded from your system more than once.
+
+ Usage
+ Code $ python utils/logger/wandb/log_dataset.py --data .. --upload_data
+
+
+
+
+ 3: Train using dataset artifact
+ When you upload a dataset as described in the first section, you get a new config file with an added `_wandb` to its name. This file contains the information that
+ can be used to train a model directly from the dataset artifact. This also logs evaluation
+
+ Usage
+ Code $ python utils/logger/wandb/log_dataset.py --data {data}_wandb.yaml
+
+
+
+
+ 4: Save model checkpoints as artifacts
+ To enable saving and versioning checkpoints of your experiment, pass `--save_period n` with the base cammand, where `n` represents checkpoint interval.
+ You can also log both the dataset and model checkpoints simultaneously. If not passed, only the final model will be logged
+
+
+ Usage
+ Code $ python train.py --save_period 1
+
+
+
+
+
+
+ 5: Resume runs from checkpoint artifacts.
+Any run can be resumed using artifacts if the --resume argument starts with wandb-artifact:// prefix followed by the run path, i.e, wandb-artifact://username/project/runid . This doesn't require the model checkpoint to be present on the local system.
+
+
+ Usage
+ Code $ python train.py --resume wandb-artifact://{run_path}
+
+
+
+
+ 6: Resume runs from dataset artifact & checkpoint artifacts.
+ Local dataset or model checkpoints are not required. This can be used to resume runs directly on a different device
+ The syntax is same as the previous section, but you'll need to lof both the dataset and model checkpoints as artifacts, i.e, set bot --upload_dataset or
+ train from _wandb.yaml file and set --save_period
+
+
+ Usage
+ Code $ python train.py --resume wandb-artifact://{run_path}
+
+
+
+
+
+
+
+ Reports
+W&B Reports can be created from your saved runs for sharing online. Once a report is created you will receive a link you can use to publically share your results. Here is an example report created from the COCO128 tutorial trainings of all YOLOv5 models ([link](https://wandb.ai/glenn-jocher/yolov5_tutorial/reports/YOLOv5-COCO128-Tutorial-Results--VmlldzozMDI5OTY)).
+
+
+
+
+## Environments
+
+YOLOv3 may be run in any of the following up-to-date verified environments (with all dependencies including [CUDA](https://developer.nvidia.com/cuda)/[CUDNN](https://developer.nvidia.com/cudnn), [Python](https://www.python.org/) and [PyTorch](https://pytorch.org/) preinstalled):
+
+- **Google Colab and Kaggle** notebooks with free GPU:
+- **Google Cloud** Deep Learning VM. See [GCP Quickstart Guide](https://github.com/ultralytics/yolov3/wiki/GCP-Quickstart)
+- **Amazon** Deep Learning AMI. See [AWS Quickstart Guide](https://github.com/ultralytics/yolov3/wiki/AWS-Quickstart)
+- **Docker Image**. See [Docker Quickstart Guide](https://github.com/ultralytics/yolov3/wiki/Docker-Quickstart) 
+
+
+## Status
+
+
+
+If this badge is green, all [YOLOv3 GitHub Actions](https://github.com/ultralytics/yolov3/actions) Continuous Integration (CI) tests are currently passing. CI tests verify correct operation of YOLOv3 training ([train.py](https://github.com/ultralytics/yolov3/blob/master/train.py)), validation ([val.py](https://github.com/ultralytics/yolov3/blob/master/val.py)), inference ([detect.py](https://github.com/ultralytics/yolov3/blob/master/detect.py)) and export ([export.py](https://github.com/ultralytics/yolov3/blob/master/export.py)) on MacOS, Windows, and Ubuntu every 24 hours and on every commit.
diff --git a/ros2_ws/src/yolov3_ros/utils/loggers/wandb/__init__.py b/ros2_ws/src/yolov3_ros/utils/loggers/wandb/__init__.py
new file mode 100644
index 00000000..e69de29b
diff --git a/ros2_ws/src/yolov3_ros/utils/loggers/wandb/log_dataset.py b/ros2_ws/src/yolov3_ros/utils/loggers/wandb/log_dataset.py
new file mode 100644
index 00000000..d3c77430
--- /dev/null
+++ b/ros2_ws/src/yolov3_ros/utils/loggers/wandb/log_dataset.py
@@ -0,0 +1,27 @@
+import argparse
+
+from wandb_utils import WandbLogger
+
+from utils.general import LOGGER
+
+WANDB_ARTIFACT_PREFIX = 'wandb-artifact://'
+
+
+def create_dataset_artifact(opt):
+ logger = WandbLogger(opt, None, job_type='Dataset Creation') # TODO: return value unused
+ if not logger.wandb:
+ LOGGER.info("install wandb using `pip install wandb` to log the dataset")
+
+
+if __name__ == '__main__':
+ parser = argparse.ArgumentParser()
+ parser.add_argument('--data', type=str, default='data/coco128.yaml', help='data.yaml path')
+ parser.add_argument('--single-cls', action='store_true', help='train as single-class dataset')
+ parser.add_argument('--project', type=str, default='YOLOv3', help='name of W&B Project')
+ parser.add_argument('--entity', default=None, help='W&B entity')
+ parser.add_argument('--name', type=str, default='log dataset', help='name of W&B run')
+
+ opt = parser.parse_args()
+ opt.resume = False # Explicitly disallow resume check for dataset upload job
+
+ create_dataset_artifact(opt)
diff --git a/ros2_ws/src/yolov3_ros/utils/loggers/wandb/sweep.py b/ros2_ws/src/yolov3_ros/utils/loggers/wandb/sweep.py
new file mode 100644
index 00000000..5e24f96e
--- /dev/null
+++ b/ros2_ws/src/yolov3_ros/utils/loggers/wandb/sweep.py
@@ -0,0 +1,41 @@
+import sys
+from pathlib import Path
+
+import wandb
+
+FILE = Path(__file__).resolve()
+ROOT = FILE.parents[3] # root directory
+if str(ROOT) not in sys.path:
+ sys.path.append(str(ROOT)) # add ROOT to PATH
+
+from train import parse_opt, train
+from utils.callbacks import Callbacks
+from utils.general import increment_path
+from utils.torch_utils import select_device
+
+
+def sweep():
+ wandb.init()
+ # Get hyp dict from sweep agent
+ hyp_dict = vars(wandb.config).get("_items")
+
+ # Workaround: get necessary opt args
+ opt = parse_opt(known=True)
+ opt.batch_size = hyp_dict.get("batch_size")
+ opt.save_dir = str(increment_path(Path(opt.project) / opt.name, exist_ok=opt.exist_ok or opt.evolve))
+ opt.epochs = hyp_dict.get("epochs")
+ opt.nosave = True
+ opt.data = hyp_dict.get("data")
+ opt.weights = str(opt.weights)
+ opt.cfg = str(opt.cfg)
+ opt.data = str(opt.data)
+ opt.hyp = str(opt.hyp)
+ opt.project = str(opt.project)
+ device = select_device(opt.device, batch_size=opt.batch_size)
+
+ # train
+ train(hyp_dict, opt, device, callbacks=Callbacks())
+
+
+if __name__ == "__main__":
+ sweep()
diff --git a/ros2_ws/src/yolov3_ros/utils/loggers/wandb/sweep.yaml b/ros2_ws/src/yolov3_ros/utils/loggers/wandb/sweep.yaml
new file mode 100644
index 00000000..c7790d75
--- /dev/null
+++ b/ros2_ws/src/yolov3_ros/utils/loggers/wandb/sweep.yaml
@@ -0,0 +1,143 @@
+# Hyperparameters for training
+# To set range-
+# Provide min and max values as:
+# parameter:
+#
+# min: scalar
+# max: scalar
+# OR
+#
+# Set a specific list of search space-
+# parameter:
+# values: [scalar1, scalar2, scalar3...]
+#
+# You can use grid, bayesian and hyperopt search strategy
+# For more info on configuring sweeps visit - https://docs.wandb.ai/guides/sweeps/configuration
+
+program: utils/loggers/wandb/sweep.py
+method: random
+metric:
+ name: metrics/mAP_0.5
+ goal: maximize
+
+parameters:
+ # hyperparameters: set either min, max range or values list
+ data:
+ value: "data/coco128.yaml"
+ batch_size:
+ values: [64]
+ epochs:
+ values: [10]
+
+ lr0:
+ distribution: uniform
+ min: 1e-5
+ max: 1e-1
+ lrf:
+ distribution: uniform
+ min: 0.01
+ max: 1.0
+ momentum:
+ distribution: uniform
+ min: 0.6
+ max: 0.98
+ weight_decay:
+ distribution: uniform
+ min: 0.0
+ max: 0.001
+ warmup_epochs:
+ distribution: uniform
+ min: 0.0
+ max: 5.0
+ warmup_momentum:
+ distribution: uniform
+ min: 0.0
+ max: 0.95
+ warmup_bias_lr:
+ distribution: uniform
+ min: 0.0
+ max: 0.2
+ box:
+ distribution: uniform
+ min: 0.02
+ max: 0.2
+ cls:
+ distribution: uniform
+ min: 0.2
+ max: 4.0
+ cls_pw:
+ distribution: uniform
+ min: 0.5
+ max: 2.0
+ obj:
+ distribution: uniform
+ min: 0.2
+ max: 4.0
+ obj_pw:
+ distribution: uniform
+ min: 0.5
+ max: 2.0
+ iou_t:
+ distribution: uniform
+ min: 0.1
+ max: 0.7
+ anchor_t:
+ distribution: uniform
+ min: 2.0
+ max: 8.0
+ fl_gamma:
+ distribution: uniform
+ min: 0.0
+ max: 0.1
+ hsv_h:
+ distribution: uniform
+ min: 0.0
+ max: 0.1
+ hsv_s:
+ distribution: uniform
+ min: 0.0
+ max: 0.9
+ hsv_v:
+ distribution: uniform
+ min: 0.0
+ max: 0.9
+ degrees:
+ distribution: uniform
+ min: 0.0
+ max: 45.0
+ translate:
+ distribution: uniform
+ min: 0.0
+ max: 0.9
+ scale:
+ distribution: uniform
+ min: 0.0
+ max: 0.9
+ shear:
+ distribution: uniform
+ min: 0.0
+ max: 10.0
+ perspective:
+ distribution: uniform
+ min: 0.0
+ max: 0.001
+ flipud:
+ distribution: uniform
+ min: 0.0
+ max: 1.0
+ fliplr:
+ distribution: uniform
+ min: 0.0
+ max: 1.0
+ mosaic:
+ distribution: uniform
+ min: 0.0
+ max: 1.0
+ mixup:
+ distribution: uniform
+ min: 0.0
+ max: 1.0
+ copy_paste:
+ distribution: uniform
+ min: 0.0
+ max: 1.0
diff --git a/ros2_ws/src/yolov3_ros/utils/loggers/wandb/wandb_utils.py b/ros2_ws/src/yolov3_ros/utils/loggers/wandb/wandb_utils.py
new file mode 100644
index 00000000..7087e4e9
--- /dev/null
+++ b/ros2_ws/src/yolov3_ros/utils/loggers/wandb/wandb_utils.py
@@ -0,0 +1,532 @@
+"""Utilities and tools for tracking runs with Weights & Biases."""
+
+import logging
+import os
+import sys
+from contextlib import contextmanager
+from pathlib import Path
+from typing import Dict
+
+import pkg_resources as pkg
+import yaml
+from tqdm import tqdm
+
+FILE = Path(__file__).resolve()
+ROOT = FILE.parents[3] # root directory
+if str(ROOT) not in sys.path:
+ sys.path.append(str(ROOT)) # add ROOT to PATH
+
+from utils.datasets import LoadImagesAndLabels, img2label_paths
+from utils.general import LOGGER, check_dataset, check_file
+
+try:
+ import wandb
+
+ assert hasattr(wandb, '__version__') # verify package import not local dir
+except (ImportError, AssertionError):
+ wandb = None
+
+RANK = int(os.getenv('RANK', -1))
+WANDB_ARTIFACT_PREFIX = 'wandb-artifact://'
+
+
+def remove_prefix(from_string, prefix=WANDB_ARTIFACT_PREFIX):
+ return from_string[len(prefix):]
+
+
+def check_wandb_config_file(data_config_file):
+ wandb_config = '_wandb.'.join(data_config_file.rsplit('.', 1)) # updated data.yaml path
+ if Path(wandb_config).is_file():
+ return wandb_config
+ return data_config_file
+
+
+def check_wandb_dataset(data_file):
+ is_trainset_wandb_artifact = False
+ is_valset_wandb_artifact = False
+ if check_file(data_file) and data_file.endswith('.yaml'):
+ with open(data_file, errors='ignore') as f:
+ data_dict = yaml.safe_load(f)
+ is_trainset_wandb_artifact = (isinstance(data_dict['train'], str) and
+ data_dict['train'].startswith(WANDB_ARTIFACT_PREFIX))
+ is_valset_wandb_artifact = (isinstance(data_dict['val'], str) and
+ data_dict['val'].startswith(WANDB_ARTIFACT_PREFIX))
+ if is_trainset_wandb_artifact or is_valset_wandb_artifact:
+ return data_dict
+ else:
+ return check_dataset(data_file)
+
+
+def get_run_info(run_path):
+ run_path = Path(remove_prefix(run_path, WANDB_ARTIFACT_PREFIX))
+ run_id = run_path.stem
+ project = run_path.parent.stem
+ entity = run_path.parent.parent.stem
+ model_artifact_name = 'run_' + run_id + '_model'
+ return entity, project, run_id, model_artifact_name
+
+
+def check_wandb_resume(opt):
+ process_wandb_config_ddp_mode(opt) if RANK not in [-1, 0] else None
+ if isinstance(opt.resume, str):
+ if opt.resume.startswith(WANDB_ARTIFACT_PREFIX):
+ if RANK not in [-1, 0]: # For resuming DDP runs
+ entity, project, run_id, model_artifact_name = get_run_info(opt.resume)
+ api = wandb.Api()
+ artifact = api.artifact(entity + '/' + project + '/' + model_artifact_name + ':latest')
+ modeldir = artifact.download()
+ opt.weights = str(Path(modeldir) / "last.pt")
+ return True
+ return None
+
+
+def process_wandb_config_ddp_mode(opt):
+ with open(check_file(opt.data), errors='ignore') as f:
+ data_dict = yaml.safe_load(f) # data dict
+ train_dir, val_dir = None, None
+ if isinstance(data_dict['train'], str) and data_dict['train'].startswith(WANDB_ARTIFACT_PREFIX):
+ api = wandb.Api()
+ train_artifact = api.artifact(remove_prefix(data_dict['train']) + ':' + opt.artifact_alias)
+ train_dir = train_artifact.download()
+ train_path = Path(train_dir) / 'data/images/'
+ data_dict['train'] = str(train_path)
+
+ if isinstance(data_dict['val'], str) and data_dict['val'].startswith(WANDB_ARTIFACT_PREFIX):
+ api = wandb.Api()
+ val_artifact = api.artifact(remove_prefix(data_dict['val']) + ':' + opt.artifact_alias)
+ val_dir = val_artifact.download()
+ val_path = Path(val_dir) / 'data/images/'
+ data_dict['val'] = str(val_path)
+ if train_dir or val_dir:
+ ddp_data_path = str(Path(val_dir) / 'wandb_local_data.yaml')
+ with open(ddp_data_path, 'w') as f:
+ yaml.safe_dump(data_dict, f)
+ opt.data = ddp_data_path
+
+
+class WandbLogger():
+ """Log training runs, datasets, models, and predictions to Weights & Biases.
+
+ This logger sends information to W&B at wandb.ai. By default, this information
+ includes hyperparameters, system configuration and metrics, model metrics,
+ and basic data metrics and analyses.
+
+ By providing additional command line arguments to train.py, datasets,
+ models and predictions can also be logged.
+
+ For more on how this logger is used, see the Weights & Biases documentation:
+ https://docs.wandb.com/guides/integrations/yolov5
+ """
+
+ def __init__(self, opt, run_id=None, job_type='Training'):
+ """
+ - Initialize WandbLogger instance
+ - Upload dataset if opt.upload_dataset is True
+ - Setup trainig processes if job_type is 'Training'
+
+ arguments:
+ opt (namespace) -- Commandline arguments for this run
+ run_id (str) -- Run ID of W&B run to be resumed
+ job_type (str) -- To set the job_type for this run
+
+ """
+ # Pre-training routine --
+ self.job_type = job_type
+ self.wandb, self.wandb_run = wandb, None if not wandb else wandb.run
+ self.val_artifact, self.train_artifact = None, None
+ self.train_artifact_path, self.val_artifact_path = None, None
+ self.result_artifact = None
+ self.val_table, self.result_table = None, None
+ self.bbox_media_panel_images = []
+ self.val_table_path_map = None
+ self.max_imgs_to_log = 16
+ self.wandb_artifact_data_dict = None
+ self.data_dict = None
+ # It's more elegant to stick to 1 wandb.init call,
+ # but useful config data is overwritten in the WandbLogger's wandb.init call
+ if isinstance(opt.resume, str): # checks resume from artifact
+ if opt.resume.startswith(WANDB_ARTIFACT_PREFIX):
+ entity, project, run_id, model_artifact_name = get_run_info(opt.resume)
+ model_artifact_name = WANDB_ARTIFACT_PREFIX + model_artifact_name
+ assert wandb, 'install wandb to resume wandb runs'
+ # Resume wandb-artifact:// runs here| workaround for not overwriting wandb.config
+ self.wandb_run = wandb.init(id=run_id,
+ project=project,
+ entity=entity,
+ resume='allow',
+ allow_val_change=True)
+ opt.resume = model_artifact_name
+ elif self.wandb:
+ self.wandb_run = wandb.init(config=opt,
+ resume="allow",
+ project='YOLOv3' if opt.project == 'runs/train' else Path(opt.project).stem,
+ entity=opt.entity,
+ name=opt.name if opt.name != 'exp' else None,
+ job_type=job_type,
+ id=run_id,
+ allow_val_change=True) if not wandb.run else wandb.run
+ if self.wandb_run:
+ if self.job_type == 'Training':
+ if opt.upload_dataset:
+ if not opt.resume:
+ self.wandb_artifact_data_dict = self.check_and_upload_dataset(opt)
+
+ if opt.resume:
+ # resume from artifact
+ if isinstance(opt.resume, str) and opt.resume.startswith(WANDB_ARTIFACT_PREFIX):
+ self.data_dict = dict(self.wandb_run.config.data_dict)
+ else: # local resume
+ self.data_dict = check_wandb_dataset(opt.data)
+ else:
+ self.data_dict = check_wandb_dataset(opt.data)
+ self.wandb_artifact_data_dict = self.wandb_artifact_data_dict or self.data_dict
+
+ # write data_dict to config. useful for resuming from artifacts. Do this only when not resuming.
+ self.wandb_run.config.update({'data_dict': self.wandb_artifact_data_dict},
+ allow_val_change=True)
+ self.setup_training(opt)
+
+ if self.job_type == 'Dataset Creation':
+ self.data_dict = self.check_and_upload_dataset(opt)
+
+ def check_and_upload_dataset(self, opt):
+ """
+ Check if the dataset format is compatible and upload it as W&B artifact
+
+ arguments:
+ opt (namespace)-- Commandline arguments for current run
+
+ returns:
+ Updated dataset info dictionary where local dataset paths are replaced by WAND_ARFACT_PREFIX links.
+ """
+ assert wandb, 'Install wandb to upload dataset'
+ config_path = self.log_dataset_artifact(opt.data,
+ opt.single_cls,
+ 'YOLOv3' if opt.project == 'runs/train' else Path(opt.project).stem)
+ LOGGER.info(f"Created dataset config file {config_path}")
+ with open(config_path, errors='ignore') as f:
+ wandb_data_dict = yaml.safe_load(f)
+ return wandb_data_dict
+
+ def setup_training(self, opt):
+ """
+ Setup the necessary processes for training YOLO models:
+ - Attempt to download model checkpoint and dataset artifacts if opt.resume stats with WANDB_ARTIFACT_PREFIX
+ - Update data_dict, to contain info of previous run if resumed and the paths of dataset artifact if downloaded
+ - Setup log_dict, initialize bbox_interval
+
+ arguments:
+ opt (namespace) -- commandline arguments for this run
+
+ """
+ self.log_dict, self.current_epoch = {}, 0
+ self.bbox_interval = opt.bbox_interval
+ if isinstance(opt.resume, str):
+ modeldir, _ = self.download_model_artifact(opt)
+ if modeldir:
+ self.weights = Path(modeldir) / "last.pt"
+ config = self.wandb_run.config
+ opt.weights, opt.save_period, opt.batch_size, opt.bbox_interval, opt.epochs, opt.hyp = str(
+ self.weights), config.save_period, config.batch_size, config.bbox_interval, config.epochs, \
+ config.hyp
+ data_dict = self.data_dict
+ if self.val_artifact is None: # If --upload_dataset is set, use the existing artifact, don't download
+ self.train_artifact_path, self.train_artifact = self.download_dataset_artifact(data_dict.get('train'),
+ opt.artifact_alias)
+ self.val_artifact_path, self.val_artifact = self.download_dataset_artifact(data_dict.get('val'),
+ opt.artifact_alias)
+
+ if self.train_artifact_path is not None:
+ train_path = Path(self.train_artifact_path) / 'data/images/'
+ data_dict['train'] = str(train_path)
+ if self.val_artifact_path is not None:
+ val_path = Path(self.val_artifact_path) / 'data/images/'
+ data_dict['val'] = str(val_path)
+
+ if self.val_artifact is not None:
+ self.result_artifact = wandb.Artifact("run_" + wandb.run.id + "_progress", "evaluation")
+ self.result_table = wandb.Table(["epoch", "id", "ground truth", "prediction", "avg_confidence"])
+ self.val_table = self.val_artifact.get("val")
+ if self.val_table_path_map is None:
+ self.map_val_table_path()
+ if opt.bbox_interval == -1:
+ self.bbox_interval = opt.bbox_interval = (opt.epochs // 10) if opt.epochs > 10 else 1
+ train_from_artifact = self.train_artifact_path is not None and self.val_artifact_path is not None
+ # Update the the data_dict to point to local artifacts dir
+ if train_from_artifact:
+ self.data_dict = data_dict
+
+ def download_dataset_artifact(self, path, alias):
+ """
+ download the model checkpoint artifact if the path starts with WANDB_ARTIFACT_PREFIX
+
+ arguments:
+ path -- path of the dataset to be used for training
+ alias (str)-- alias of the artifact to be download/used for training
+
+ returns:
+ (str, wandb.Artifact) -- path of the downladed dataset and it's corresponding artifact object if dataset
+ is found otherwise returns (None, None)
+ """
+ if isinstance(path, str) and path.startswith(WANDB_ARTIFACT_PREFIX):
+ artifact_path = Path(remove_prefix(path, WANDB_ARTIFACT_PREFIX) + ":" + alias)
+ dataset_artifact = wandb.use_artifact(artifact_path.as_posix().replace("\\", "/"))
+ assert dataset_artifact is not None, "'Error: W&B dataset artifact doesn\'t exist'"
+ datadir = dataset_artifact.download()
+ return datadir, dataset_artifact
+ return None, None
+
+ def download_model_artifact(self, opt):
+ """
+ download the model checkpoint artifact if the resume path starts with WANDB_ARTIFACT_PREFIX
+
+ arguments:
+ opt (namespace) -- Commandline arguments for this run
+ """
+ if opt.resume.startswith(WANDB_ARTIFACT_PREFIX):
+ model_artifact = wandb.use_artifact(remove_prefix(opt.resume, WANDB_ARTIFACT_PREFIX) + ":latest")
+ assert model_artifact is not None, 'Error: W&B model artifact doesn\'t exist'
+ modeldir = model_artifact.download()
+ epochs_trained = model_artifact.metadata.get('epochs_trained')
+ total_epochs = model_artifact.metadata.get('total_epochs')
+ is_finished = total_epochs is None
+ assert not is_finished, 'training is finished, can only resume incomplete runs.'
+ return modeldir, model_artifact
+ return None, None
+
+ def log_model(self, path, opt, epoch, fitness_score, best_model=False):
+ """
+ Log the model checkpoint as W&B artifact
+
+ arguments:
+ path (Path) -- Path of directory containing the checkpoints
+ opt (namespace) -- Command line arguments for this run
+ epoch (int) -- Current epoch number
+ fitness_score (float) -- fitness score for current epoch
+ best_model (boolean) -- Boolean representing if the current checkpoint is the best yet.
+ """
+ model_artifact = wandb.Artifact('run_' + wandb.run.id + '_model', type='model', metadata={
+ 'original_url': str(path),
+ 'epochs_trained': epoch + 1,
+ 'save period': opt.save_period,
+ 'project': opt.project,
+ 'total_epochs': opt.epochs,
+ 'fitness_score': fitness_score
+ })
+ model_artifact.add_file(str(path / 'last.pt'), name='last.pt')
+ wandb.log_artifact(model_artifact,
+ aliases=['latest', 'last', 'epoch ' + str(self.current_epoch), 'best' if best_model else ''])
+ LOGGER.info(f"Saving model artifact on epoch {epoch + 1}")
+
+ def log_dataset_artifact(self, data_file, single_cls, project, overwrite_config=False):
+ """
+ Log the dataset as W&B artifact and return the new data file with W&B links
+
+ arguments:
+ data_file (str) -- the .yaml file with information about the dataset like - path, classes etc.
+ single_class (boolean) -- train multi-class data as single-class
+ project (str) -- project name. Used to construct the artifact path
+ overwrite_config (boolean) -- overwrites the data.yaml file if set to true otherwise creates a new
+ file with _wandb postfix. Eg -> data_wandb.yaml
+
+ returns:
+ the new .yaml file with artifact links. it can be used to start training directly from artifacts
+ """
+ self.data_dict = check_dataset(data_file) # parse and check
+ data = dict(self.data_dict)
+ nc, names = (1, ['item']) if single_cls else (int(data['nc']), data['names'])
+ names = {k: v for k, v in enumerate(names)} # to index dictionary
+ self.train_artifact = self.create_dataset_table(LoadImagesAndLabels(
+ data['train'], rect=True, batch_size=1), names, name='train') if data.get('train') else None
+ self.val_artifact = self.create_dataset_table(LoadImagesAndLabels(
+ data['val'], rect=True, batch_size=1), names, name='val') if data.get('val') else None
+ if data.get('train'):
+ data['train'] = WANDB_ARTIFACT_PREFIX + str(Path(project) / 'train')
+ if data.get('val'):
+ data['val'] = WANDB_ARTIFACT_PREFIX + str(Path(project) / 'val')
+ path = Path(data_file).stem
+ path = (path if overwrite_config else path + '_wandb') + '.yaml' # updated data.yaml path
+ data.pop('download', None)
+ data.pop('path', None)
+ with open(path, 'w') as f:
+ yaml.safe_dump(data, f)
+
+ if self.job_type == 'Training': # builds correct artifact pipeline graph
+ self.wandb_run.use_artifact(self.val_artifact)
+ self.wandb_run.use_artifact(self.train_artifact)
+ self.val_artifact.wait()
+ self.val_table = self.val_artifact.get('val')
+ self.map_val_table_path()
+ else:
+ self.wandb_run.log_artifact(self.train_artifact)
+ self.wandb_run.log_artifact(self.val_artifact)
+ return path
+
+ def map_val_table_path(self):
+ """
+ Map the validation dataset Table like name of file -> it's id in the W&B Table.
+ Useful for - referencing artifacts for evaluation.
+ """
+ self.val_table_path_map = {}
+ LOGGER.info("Mapping dataset")
+ for i, data in enumerate(tqdm(self.val_table.data)):
+ self.val_table_path_map[data[3]] = data[0]
+
+ def create_dataset_table(self, dataset: LoadImagesAndLabels, class_to_id: Dict[int,str], name: str = 'dataset'):
+ """
+ Create and return W&B artifact containing W&B Table of the dataset.
+
+ arguments:
+ dataset -- instance of LoadImagesAndLabels class used to iterate over the data to build Table
+ class_to_id -- hash map that maps class ids to labels
+ name -- name of the artifact
+
+ returns:
+ dataset artifact to be logged or used
+ """
+ # TODO: Explore multiprocessing to slpit this loop parallely| This is essential for speeding up the the logging
+ artifact = wandb.Artifact(name=name, type="dataset")
+ img_files = tqdm([dataset.path]) if isinstance(dataset.path, str) and Path(dataset.path).is_dir() else None
+ img_files = tqdm(dataset.img_files) if not img_files else img_files
+ for img_file in img_files:
+ if Path(img_file).is_dir():
+ artifact.add_dir(img_file, name='data/images')
+ labels_path = 'labels'.join(dataset.path.rsplit('images', 1))
+ artifact.add_dir(labels_path, name='data/labels')
+ else:
+ artifact.add_file(img_file, name='data/images/' + Path(img_file).name)
+ label_file = Path(img2label_paths([img_file])[0])
+ artifact.add_file(str(label_file),
+ name='data/labels/' + label_file.name) if label_file.exists() else None
+ table = wandb.Table(columns=["id", "train_image", "Classes", "name"])
+ class_set = wandb.Classes([{'id': id, 'name': name} for id, name in class_to_id.items()])
+ for si, (img, labels, paths, shapes) in enumerate(tqdm(dataset)):
+ box_data, img_classes = [], {}
+ for cls, *xywh in labels[:, 1:].tolist():
+ cls = int(cls)
+ box_data.append({"position": {"middle": [xywh[0], xywh[1]], "width": xywh[2], "height": xywh[3]},
+ "class_id": cls,
+ "box_caption": "%s" % (class_to_id[cls])})
+ img_classes[cls] = class_to_id[cls]
+ boxes = {"ground_truth": {"box_data": box_data, "class_labels": class_to_id}} # inference-space
+ table.add_data(si, wandb.Image(paths, classes=class_set, boxes=boxes), list(img_classes.values()),
+ Path(paths).name)
+ artifact.add(table, name)
+ return artifact
+
+ def log_training_progress(self, predn, path, names):
+ """
+ Build evaluation Table. Uses reference from validation dataset table.
+
+ arguments:
+ predn (list): list of predictions in the native space in the format - [xmin, ymin, xmax, ymax, confidence, class]
+ path (str): local path of the current evaluation image
+ names (dict(int, str)): hash map that maps class ids to labels
+ """
+ class_set = wandb.Classes([{'id': id, 'name': name} for id, name in names.items()])
+ box_data = []
+ total_conf = 0
+ for *xyxy, conf, cls in predn.tolist():
+ if conf >= 0.25:
+ box_data.append(
+ {"position": {"minX": xyxy[0], "minY": xyxy[1], "maxX": xyxy[2], "maxY": xyxy[3]},
+ "class_id": int(cls),
+ "box_caption": f"{names[cls]} {conf:.3f}",
+ "scores": {"class_score": conf},
+ "domain": "pixel"})
+ total_conf += conf
+ boxes = {"predictions": {"box_data": box_data, "class_labels": names}} # inference-space
+ id = self.val_table_path_map[Path(path).name]
+ self.result_table.add_data(self.current_epoch,
+ id,
+ self.val_table.data[id][1],
+ wandb.Image(self.val_table.data[id][1], boxes=boxes, classes=class_set),
+ total_conf / max(1, len(box_data))
+ )
+
+ def val_one_image(self, pred, predn, path, names, im):
+ """
+ Log validation data for one image. updates the result Table if validation dataset is uploaded and log bbox media panel
+
+ arguments:
+ pred (list): list of scaled predictions in the format - [xmin, ymin, xmax, ymax, confidence, class]
+ predn (list): list of predictions in the native space - [xmin, ymin, xmax, ymax, confidence, class]
+ path (str): local path of the current evaluation image
+ """
+ if self.val_table and self.result_table: # Log Table if Val dataset is uploaded as artifact
+ self.log_training_progress(predn, path, names)
+
+ if len(self.bbox_media_panel_images) < self.max_imgs_to_log and self.current_epoch > 0:
+ if self.current_epoch % self.bbox_interval == 0:
+ box_data = [{"position": {"minX": xyxy[0], "minY": xyxy[1], "maxX": xyxy[2], "maxY": xyxy[3]},
+ "class_id": int(cls),
+ "box_caption": f"{names[cls]} {conf:.3f}",
+ "scores": {"class_score": conf},
+ "domain": "pixel"} for *xyxy, conf, cls in pred.tolist()]
+ boxes = {"predictions": {"box_data": box_data, "class_labels": names}} # inference-space
+ self.bbox_media_panel_images.append(wandb.Image(im, boxes=boxes, caption=path.name))
+
+ def log(self, log_dict):
+ """
+ save the metrics to the logging dictionary
+
+ arguments:
+ log_dict (Dict) -- metrics/media to be logged in current step
+ """
+ if self.wandb_run:
+ for key, value in log_dict.items():
+ self.log_dict[key] = value
+
+ def end_epoch(self, best_result=False):
+ """
+ commit the log_dict, model artifacts and Tables to W&B and flush the log_dict.
+
+ arguments:
+ best_result (boolean): Boolean representing if the result of this evaluation is best or not
+ """
+ if self.wandb_run:
+ with all_logging_disabled():
+ if self.bbox_media_panel_images:
+ self.log_dict["BoundingBoxDebugger"] = self.bbox_media_panel_images
+ try:
+ wandb.log(self.log_dict)
+ except BaseException as e:
+ LOGGER.info(f"An error occurred in wandb logger. The training will proceed without interruption. More info\n{e}")
+ self.wandb_run.finish()
+ self.wandb_run = None
+
+ self.log_dict = {}
+ self.bbox_media_panel_images = []
+ if self.result_artifact:
+ self.result_artifact.add(self.result_table, 'result')
+ wandb.log_artifact(self.result_artifact, aliases=['latest', 'last', 'epoch ' + str(self.current_epoch),
+ ('best' if best_result else '')])
+
+ wandb.log({"evaluation": self.result_table})
+ self.result_table = wandb.Table(["epoch", "id", "ground truth", "prediction", "avg_confidence"])
+ self.result_artifact = wandb.Artifact("run_" + wandb.run.id + "_progress", "evaluation")
+
+ def finish_run(self):
+ """
+ Log metrics if any and finish the current W&B run
+ """
+ if self.wandb_run:
+ if self.log_dict:
+ with all_logging_disabled():
+ wandb.log(self.log_dict)
+ wandb.run.finish()
+
+
+@contextmanager
+def all_logging_disabled(highest_level=logging.CRITICAL):
+ """ source - https://gist.github.com/simon-weber/7853144
+ A context manager that will prevent any logging messages triggered during the body from being processed.
+ :param highest_level: the maximum logging level in use.
+ This would only need to be changed if a custom level greater than CRITICAL is defined.
+ """
+ previous_level = logging.root.manager.disable
+ logging.disable(highest_level)
+ try:
+ yield
+ finally:
+ logging.disable(previous_level)
diff --git a/ros2_ws/src/yolov3_ros/utils/loss.py b/ros2_ws/src/yolov3_ros/utils/loss.py
new file mode 100644
index 00000000..1f38c362
--- /dev/null
+++ b/ros2_ws/src/yolov3_ros/utils/loss.py
@@ -0,0 +1,234 @@
+# YOLOv3 🚀 by Ultralytics, GPL-3.0 license
+"""
+Loss functions
+"""
+
+import torch
+import torch.nn as nn
+
+from utils.metrics import bbox_iou
+from utils.torch_utils import de_parallel
+
+
+def smooth_BCE(eps=0.1): # https://github.com/ultralytics/yolov3/issues/238#issuecomment-598028441
+ # return positive, negative label smoothing BCE targets
+ return 1.0 - 0.5 * eps, 0.5 * eps
+
+
+class BCEBlurWithLogitsLoss(nn.Module):
+ # BCEwithLogitLoss() with reduced missing label effects.
+ def __init__(self, alpha=0.05):
+ super().__init__()
+ self.loss_fcn = nn.BCEWithLogitsLoss(reduction='none') # must be nn.BCEWithLogitsLoss()
+ self.alpha = alpha
+
+ def forward(self, pred, true):
+ loss = self.loss_fcn(pred, true)
+ pred = torch.sigmoid(pred) # prob from logits
+ dx = pred - true # reduce only missing label effects
+ # dx = (pred - true).abs() # reduce missing label and false label effects
+ alpha_factor = 1 - torch.exp((dx - 1) / (self.alpha + 1e-4))
+ loss *= alpha_factor
+ return loss.mean()
+
+
+class FocalLoss(nn.Module):
+ # Wraps focal loss around existing loss_fcn(), i.e. criteria = FocalLoss(nn.BCEWithLogitsLoss(), gamma=1.5)
+ def __init__(self, loss_fcn, gamma=1.5, alpha=0.25):
+ super().__init__()
+ self.loss_fcn = loss_fcn # must be nn.BCEWithLogitsLoss()
+ self.gamma = gamma
+ self.alpha = alpha
+ self.reduction = loss_fcn.reduction
+ self.loss_fcn.reduction = 'none' # required to apply FL to each element
+
+ def forward(self, pred, true):
+ loss = self.loss_fcn(pred, true)
+ # p_t = torch.exp(-loss)
+ # loss *= self.alpha * (1.000001 - p_t) ** self.gamma # non-zero power for gradient stability
+
+ # TF implementation https://github.com/tensorflow/addons/blob/v0.7.1/tensorflow_addons/losses/focal_loss.py
+ pred_prob = torch.sigmoid(pred) # prob from logits
+ p_t = true * pred_prob + (1 - true) * (1 - pred_prob)
+ alpha_factor = true * self.alpha + (1 - true) * (1 - self.alpha)
+ modulating_factor = (1.0 - p_t) ** self.gamma
+ loss *= alpha_factor * modulating_factor
+
+ if self.reduction == 'mean':
+ return loss.mean()
+ elif self.reduction == 'sum':
+ return loss.sum()
+ else: # 'none'
+ return loss
+
+
+class QFocalLoss(nn.Module):
+ # Wraps Quality focal loss around existing loss_fcn(), i.e. criteria = FocalLoss(nn.BCEWithLogitsLoss(), gamma=1.5)
+ def __init__(self, loss_fcn, gamma=1.5, alpha=0.25):
+ super().__init__()
+ self.loss_fcn = loss_fcn # must be nn.BCEWithLogitsLoss()
+ self.gamma = gamma
+ self.alpha = alpha
+ self.reduction = loss_fcn.reduction
+ self.loss_fcn.reduction = 'none' # required to apply FL to each element
+
+ def forward(self, pred, true):
+ loss = self.loss_fcn(pred, true)
+
+ pred_prob = torch.sigmoid(pred) # prob from logits
+ alpha_factor = true * self.alpha + (1 - true) * (1 - self.alpha)
+ modulating_factor = torch.abs(true - pred_prob) ** self.gamma
+ loss *= alpha_factor * modulating_factor
+
+ if self.reduction == 'mean':
+ return loss.mean()
+ elif self.reduction == 'sum':
+ return loss.sum()
+ else: # 'none'
+ return loss
+
+
+class ComputeLoss:
+ sort_obj_iou = False
+
+ # Compute losses
+ def __init__(self, model, autobalance=False):
+ device = next(model.parameters()).device # get model device
+ h = model.hyp # hyperparameters
+
+ # Define criteria
+ BCEcls = nn.BCEWithLogitsLoss(pos_weight=torch.tensor([h['cls_pw']], device=device))
+ BCEobj = nn.BCEWithLogitsLoss(pos_weight=torch.tensor([h['obj_pw']], device=device))
+
+ # Class label smoothing https://arxiv.org/pdf/1902.04103.pdf eqn 3
+ self.cp, self.cn = smooth_BCE(eps=h.get('label_smoothing', 0.0)) # positive, negative BCE targets
+
+ # Focal loss
+ g = h['fl_gamma'] # focal loss gamma
+ if g > 0:
+ BCEcls, BCEobj = FocalLoss(BCEcls, g), FocalLoss(BCEobj, g)
+
+ m = de_parallel(model).model[-1] # Detect() module
+ self.balance = {3: [4.0, 1.0, 0.4]}.get(m.nl, [4.0, 1.0, 0.25, 0.06, 0.02]) # P3-P7
+ self.ssi = list(m.stride).index(16) if autobalance else 0 # stride 16 index
+ self.BCEcls, self.BCEobj, self.gr, self.hyp, self.autobalance = BCEcls, BCEobj, 1.0, h, autobalance
+ self.na = m.na # number of anchors
+ self.nc = m.nc # number of classes
+ self.nl = m.nl # number of layers
+ self.anchors = m.anchors
+ self.device = device
+
+ def __call__(self, p, targets): # predictions, targets
+ lcls = torch.zeros(1, device=self.device) # class loss
+ lbox = torch.zeros(1, device=self.device) # box loss
+ lobj = torch.zeros(1, device=self.device) # object loss
+ tcls, tbox, indices, anchors = self.build_targets(p, targets) # targets
+
+ # Losses
+ for i, pi in enumerate(p): # layer index, layer predictions
+ b, a, gj, gi = indices[i] # image, anchor, gridy, gridx
+ tobj = torch.zeros(pi.shape[:4], dtype=pi.dtype, device=self.device) # target obj
+
+ n = b.shape[0] # number of targets
+ if n:
+ # pxy, pwh, _, pcls = pi[b, a, gj, gi].tensor_split((2, 4, 5), dim=1) # faster, requires torch 1.8.0
+ pxy, pwh, _, pcls = pi[b, a, gj, gi].split((2, 2, 1, self.nc), 1) # target-subset of predictions
+
+ # Regression
+ pxy = pxy.sigmoid() * 2 - 0.5
+ pwh = (pwh.sigmoid() * 2) ** 2 * anchors[i]
+ pbox = torch.cat((pxy, pwh), 1) # predicted box
+ iou = bbox_iou(pbox, tbox[i], CIoU=True).squeeze() # iou(prediction, target)
+ lbox += (1.0 - iou).mean() # iou loss
+
+ # Objectness
+ iou = iou.detach().clamp(0).type(tobj.dtype)
+ if self.sort_obj_iou:
+ j = iou.argsort()
+ b, a, gj, gi, iou = b[j], a[j], gj[j], gi[j], iou[j]
+ if self.gr < 1:
+ iou = (1.0 - self.gr) + self.gr * iou
+ tobj[b, a, gj, gi] = iou # iou ratio
+
+ # Classification
+ if self.nc > 1: # cls loss (only if multiple classes)
+ t = torch.full_like(pcls, self.cn, device=self.device) # targets
+ t[range(n), tcls[i]] = self.cp
+ lcls += self.BCEcls(pcls, t) # BCE
+
+ # Append targets to text file
+ # with open('targets.txt', 'a') as file:
+ # [file.write('%11.5g ' * 4 % tuple(x) + '\n') for x in torch.cat((txy[i], twh[i]), 1)]
+
+ obji = self.BCEobj(pi[..., 4], tobj)
+ lobj += obji * self.balance[i] # obj loss
+ if self.autobalance:
+ self.balance[i] = self.balance[i] * 0.9999 + 0.0001 / obji.detach().item()
+
+ if self.autobalance:
+ self.balance = [x / self.balance[self.ssi] for x in self.balance]
+ lbox *= self.hyp['box']
+ lobj *= self.hyp['obj']
+ lcls *= self.hyp['cls']
+ bs = tobj.shape[0] # batch size
+
+ return (lbox + lobj + lcls) * bs, torch.cat((lbox, lobj, lcls)).detach()
+
+ def build_targets(self, p, targets):
+ # Build targets for compute_loss(), input targets(image,class,x,y,w,h)
+ na, nt = self.na, targets.shape[0] # number of anchors, targets
+ tcls, tbox, indices, anch = [], [], [], []
+ gain = torch.ones(7, device=self.device) # normalized to gridspace gain
+ ai = torch.arange(na, device=self.device).float().view(na, 1).repeat(1, nt) # same as .repeat_interleave(nt)
+ targets = torch.cat((targets.repeat(na, 1, 1), ai[..., None]), 2) # append anchor indices
+
+ g = 0.5 # bias
+ off = torch.tensor(
+ [
+ [0, 0],
+ [1, 0],
+ [0, 1],
+ [-1, 0],
+ [0, -1], # j,k,l,m
+ # [1, 1], [1, -1], [-1, 1], [-1, -1], # jk,jm,lk,lm
+ ],
+ device=self.device).float() * g # offsets
+
+ for i in range(self.nl):
+ anchors, shape = self.anchors[i], p[i].shape
+ gain[2:6] = torch.tensor(shape)[[3, 2, 3, 2]] # xyxy gain
+
+ # Match targets to anchors
+ t = targets * gain # shape(3,n,7)
+ if nt:
+ # Matches
+ r = t[..., 4:6] / anchors[:, None] # wh ratio
+ j = torch.max(r, 1 / r).max(2)[0] < self.hyp['anchor_t'] # compare
+ # j = wh_iou(anchors, t[:, 4:6]) > model.hyp['iou_t'] # iou(3,n)=wh_iou(anchors(3,2), gwh(n,2))
+ t = t[j] # filter
+
+ # Offsets
+ gxy = t[:, 2:4] # grid xy
+ gxi = gain[[2, 3]] - gxy # inverse
+ j, k = ((gxy % 1 < g) & (gxy > 1)).T
+ l, m = ((gxi % 1 < g) & (gxi > 1)).T
+ j = torch.stack((torch.ones_like(j), j, k, l, m))
+ t = t.repeat((5, 1, 1))[j]
+ offsets = (torch.zeros_like(gxy)[None] + off[:, None])[j]
+ else:
+ t = targets[0]
+ offsets = 0
+
+ # Define
+ bc, gxy, gwh, a = t.chunk(4, 1) # (image, class), grid xy, grid wh, anchors
+ a, (b, c) = a.long().view(-1), bc.long().T # anchors, image, class
+ gij = (gxy - offsets).long()
+ gi, gj = gij.T # grid indices
+
+ # Append
+ indices.append((b, a, gj.clamp_(0, shape[2] - 1), gi.clamp_(0, shape[3] - 1))) # image, anchor, grid
+ tbox.append(torch.cat((gxy - gij, gwh), 1)) # box
+ anch.append(anchors[a]) # anchors
+ tcls.append(c) # class
+
+ return tcls, tbox, indices, anch
diff --git a/ros2_ws/src/yolov3_ros/utils/metrics.py b/ros2_ws/src/yolov3_ros/utils/metrics.py
new file mode 100644
index 00000000..90490955
--- /dev/null
+++ b/ros2_ws/src/yolov3_ros/utils/metrics.py
@@ -0,0 +1,331 @@
+# YOLOv3 🚀 by Ultralytics, GPL-3.0 license
+"""
+Model validation metrics
+"""
+
+import math
+import warnings
+from pathlib import Path
+
+import matplotlib.pyplot as plt
+import numpy as np
+import torch
+
+
+def fitness(x):
+ # Model fitness as a weighted combination of metrics
+ w = [0.0, 0.0, 0.1, 0.9] # weights for [P, R, mAP@0.5, mAP@0.5:0.95]
+ return (x[:, :4] * w).sum(1)
+
+
+def ap_per_class(tp, conf, pred_cls, target_cls, plot=False, save_dir='.', names=()):
+ """ Compute the average precision, given the recall and precision curves.
+ Source: https://github.com/rafaelpadilla/Object-Detection-Metrics.
+ # Arguments
+ tp: True positives (nparray, nx1 or nx10).
+ conf: Objectness value from 0-1 (nparray).
+ pred_cls: Predicted object classes (nparray).
+ target_cls: True object classes (nparray).
+ plot: Plot precision-recall curve at mAP@0.5
+ save_dir: Plot save directory
+ # Returns
+ The average precision as computed in py-faster-rcnn.
+ """
+
+ # Sort by objectness
+ i = np.argsort(-conf)
+ tp, conf, pred_cls = tp[i], conf[i], pred_cls[i]
+
+ # Find unique classes
+ unique_classes = np.unique(target_cls)
+ nc = unique_classes.shape[0] # number of classes, number of detections
+
+ # Create Precision-Recall curve and compute AP for each class
+ px, py = np.linspace(0, 1, 1000), [] # for plotting
+ ap, p, r = np.zeros((nc, tp.shape[1])), np.zeros((nc, 1000)), np.zeros((nc, 1000))
+ for ci, c in enumerate(unique_classes):
+ i = pred_cls == c
+ n_l = (target_cls == c).sum() # number of labels
+ n_p = i.sum() # number of predictions
+
+ if n_p == 0 or n_l == 0:
+ continue
+ else:
+ # Accumulate FPs and TPs
+ fpc = (1 - tp[i]).cumsum(0)
+ tpc = tp[i].cumsum(0)
+
+ # Recall
+ recall = tpc / (n_l + 1e-16) # recall curve
+ r[ci] = np.interp(-px, -conf[i], recall[:, 0], left=0) # negative x, xp because xp decreases
+
+ # Precision
+ precision = tpc / (tpc + fpc) # precision curve
+ p[ci] = np.interp(-px, -conf[i], precision[:, 0], left=1) # p at pr_score
+
+ # AP from recall-precision curve
+ for j in range(tp.shape[1]):
+ ap[ci, j], mpre, mrec = compute_ap(recall[:, j], precision[:, j])
+ if plot and j == 0:
+ py.append(np.interp(px, mrec, mpre)) # precision at mAP@0.5
+
+ # Compute F1 (harmonic mean of precision and recall)
+ f1 = 2 * p * r / (p + r + 1e-16)
+ names = [v for k, v in names.items() if k in unique_classes] # list: only classes that have data
+ names = {i: v for i, v in enumerate(names)} # to dict
+ if plot:
+ plot_pr_curve(px, py, ap, Path(save_dir) / 'PR_curve.png', names)
+ plot_mc_curve(px, f1, Path(save_dir) / 'F1_curve.png', names, ylabel='F1')
+ plot_mc_curve(px, p, Path(save_dir) / 'P_curve.png', names, ylabel='Precision')
+ plot_mc_curve(px, r, Path(save_dir) / 'R_curve.png', names, ylabel='Recall')
+
+ i = f1.mean(0).argmax() # max F1 index
+ return p[:, i], r[:, i], ap, f1[:, i], unique_classes.astype('int32')
+
+
+def compute_ap(recall, precision):
+ """ Compute the average precision, given the recall and precision curves
+ # Arguments
+ recall: The recall curve (list)
+ precision: The precision curve (list)
+ # Returns
+ Average precision, precision curve, recall curve
+ """
+
+ # Append sentinel values to beginning and end
+ mrec = np.concatenate(([0.0], recall, [1.0]))
+ mpre = np.concatenate(([1.0], precision, [0.0]))
+
+ # Compute the precision envelope
+ mpre = np.flip(np.maximum.accumulate(np.flip(mpre)))
+
+ # Integrate area under curve
+ method = 'interp' # methods: 'continuous', 'interp'
+ if method == 'interp':
+ x = np.linspace(0, 1, 101) # 101-point interp (COCO)
+ ap = np.trapz(np.interp(x, mrec, mpre), x) # integrate
+ else: # 'continuous'
+ i = np.where(mrec[1:] != mrec[:-1])[0] # points where x axis (recall) changes
+ ap = np.sum((mrec[i + 1] - mrec[i]) * mpre[i + 1]) # area under curve
+
+ return ap, mpre, mrec
+
+
+class ConfusionMatrix:
+ # Updated version of https://github.com/kaanakan/object_detection_confusion_matrix
+ def __init__(self, nc, conf=0.25, iou_thres=0.45):
+ self.matrix = np.zeros((nc + 1, nc + 1))
+ self.nc = nc # number of classes
+ self.conf = conf
+ self.iou_thres = iou_thres
+
+ def process_batch(self, detections, labels):
+ """
+ Return intersection-over-union (Jaccard index) of boxes.
+ Both sets of boxes are expected to be in (x1, y1, x2, y2) format.
+ Arguments:
+ detections (Array[N, 6]), x1, y1, x2, y2, conf, class
+ labels (Array[M, 5]), class, x1, y1, x2, y2
+ Returns:
+ None, updates confusion matrix accordingly
+ """
+ detections = detections[detections[:, 4] > self.conf]
+ gt_classes = labels[:, 0].int()
+ detection_classes = detections[:, 5].int()
+ iou = box_iou(labels[:, 1:], detections[:, :4])
+
+ x = torch.where(iou > self.iou_thres)
+ if x[0].shape[0]:
+ matches = torch.cat((torch.stack(x, 1), iou[x[0], x[1]][:, None]), 1).cpu().numpy()
+ if x[0].shape[0] > 1:
+ matches = matches[matches[:, 2].argsort()[::-1]]
+ matches = matches[np.unique(matches[:, 1], return_index=True)[1]]
+ matches = matches[matches[:, 2].argsort()[::-1]]
+ matches = matches[np.unique(matches[:, 0], return_index=True)[1]]
+ else:
+ matches = np.zeros((0, 3))
+
+ n = matches.shape[0] > 0
+ m0, m1, _ = matches.transpose().astype(np.int16)
+ for i, gc in enumerate(gt_classes):
+ j = m0 == i
+ if n and sum(j) == 1:
+ self.matrix[detection_classes[m1[j]], gc] += 1 # correct
+ else:
+ self.matrix[self.nc, gc] += 1 # background FP
+
+ if n:
+ for i, dc in enumerate(detection_classes):
+ if not any(m1 == i):
+ self.matrix[dc, self.nc] += 1 # background FN
+
+ def matrix(self):
+ return self.matrix
+
+ def plot(self, normalize=True, save_dir='', names=()):
+ try:
+ import seaborn as sn
+
+ array = self.matrix / ((self.matrix.sum(0).reshape(1, -1) + 1E-6) if normalize else 1) # normalize columns
+ array[array < 0.005] = np.nan # don't annotate (would appear as 0.00)
+
+ fig = plt.figure(figsize=(12, 9), tight_layout=True)
+ sn.set(font_scale=1.0 if self.nc < 50 else 0.8) # for label size
+ labels = (0 < len(names) < 99) and len(names) == self.nc # apply names to ticklabels
+ with warnings.catch_warnings():
+ warnings.simplefilter('ignore') # suppress empty matrix RuntimeWarning: All-NaN slice encountered
+ sn.heatmap(array, annot=self.nc < 30, annot_kws={"size": 8}, cmap='Blues', fmt='.2f', square=True,
+ xticklabels=names + ['background FP'] if labels else "auto",
+ yticklabels=names + ['background FN'] if labels else "auto").set_facecolor((1, 1, 1))
+ fig.axes[0].set_xlabel('True')
+ fig.axes[0].set_ylabel('Predicted')
+ fig.savefig(Path(save_dir) / 'confusion_matrix.png', dpi=250)
+ plt.close()
+ except Exception as e:
+ print(f'WARNING: ConfusionMatrix plot failure: {e}')
+
+ def print(self):
+ for i in range(self.nc + 1):
+ print(' '.join(map(str, self.matrix[i])))
+
+
+def bbox_iou(box1, box2, xywh=True, GIoU=False, DIoU=False, CIoU=False, eps=1e-7):
+ # Returns Intersection over Union (IoU) of box1(1,4) to box2(n,4)
+
+ # Get the coordinates of bounding boxes
+ if xywh: # transform from xywh to xyxy
+ (x1, y1, w1, h1), (x2, y2, w2, h2) = box1.chunk(4, 1), box2.chunk(4, 1)
+ w1_, h1_, w2_, h2_ = w1 / 2, h1 / 2, w2 / 2, h2 / 2
+ b1_x1, b1_x2, b1_y1, b1_y2 = x1 - w1_, x1 + w1_, y1 - h1_, y1 + h1_
+ b2_x1, b2_x2, b2_y1, b2_y2 = x2 - w2_, x2 + w2_, y2 - h2_, y2 + h2_
+ else: # x1, y1, x2, y2 = box1
+ b1_x1, b1_y1, b1_x2, b1_y2 = box1.chunk(4, 1)
+ b2_x1, b2_y1, b2_x2, b2_y2 = box2.chunk(4, 1)
+ w1, h1 = b1_x2 - b1_x1, b1_y2 - b1_y1 + eps
+ w2, h2 = b2_x2 - b2_x1, b2_y2 - b2_y1 + eps
+
+ # Intersection area
+ inter = (torch.min(b1_x2, b2_x2) - torch.max(b1_x1, b2_x1)).clamp(0) * \
+ (torch.min(b1_y2, b2_y2) - torch.max(b1_y1, b2_y1)).clamp(0)
+
+ # Union Area
+ union = w1 * h1 + w2 * h2 - inter + eps
+
+ # IoU
+ iou = inter / union
+ if CIoU or DIoU or GIoU:
+ cw = torch.max(b1_x2, b2_x2) - torch.min(b1_x1, b2_x1) # convex (smallest enclosing box) width
+ ch = torch.max(b1_y2, b2_y2) - torch.min(b1_y1, b2_y1) # convex height
+ if CIoU or DIoU: # Distance or Complete IoU https://arxiv.org/abs/1911.08287v1
+ c2 = cw ** 2 + ch ** 2 + eps # convex diagonal squared
+ rho2 = ((b2_x1 + b2_x2 - b1_x1 - b1_x2) ** 2 + (b2_y1 + b2_y2 - b1_y1 - b1_y2) ** 2) / 4 # center dist ** 2
+ if CIoU: # https://github.com/Zzh-tju/DIoU-SSD-pytorch/blob/master/utils/box/box_utils.py#L47
+ v = (4 / math.pi ** 2) * torch.pow(torch.atan(w2 / h2) - torch.atan(w1 / h1), 2)
+ with torch.no_grad():
+ alpha = v / (v - iou + (1 + eps))
+ return iou - (rho2 / c2 + v * alpha) # CIoU
+ return iou - rho2 / c2 # DIoU
+ c_area = cw * ch + eps # convex area
+ return iou - (c_area - union) / c_area # GIoU https://arxiv.org/pdf/1902.09630.pdf
+ return iou # IoU
+
+
+def box_iou(box1, box2):
+ # https://github.com/pytorch/vision/blob/master/torchvision/ops/boxes.py
+ """
+ Return intersection-over-union (Jaccard index) of boxes.
+ Both sets of boxes are expected to be in (x1, y1, x2, y2) format.
+ Arguments:
+ box1 (Tensor[N, 4])
+ box2 (Tensor[M, 4])
+ Returns:
+ iou (Tensor[N, M]): the NxM matrix containing the pairwise
+ IoU values for every element in boxes1 and boxes2
+ """
+
+ def box_area(box):
+ # box = 4xn
+ return (box[2] - box[0]) * (box[3] - box[1])
+
+ area1 = box_area(box1.T)
+ area2 = box_area(box2.T)
+
+ # inter(N,M) = (rb(N,M,2) - lt(N,M,2)).clamp(0).prod(2)
+ inter = (torch.min(box1[:, None, 2:], box2[:, 2:]) - torch.max(box1[:, None, :2], box2[:, :2])).clamp(0).prod(2)
+ return inter / (area1[:, None] + area2 - inter) # iou = inter / (area1 + area2 - inter)
+
+
+def bbox_ioa(box1, box2, eps=1E-7):
+ """ Returns the intersection over box2 area given box1, box2. Boxes are x1y1x2y2
+ box1: np.array of shape(4)
+ box2: np.array of shape(nx4)
+ returns: np.array of shape(n)
+ """
+
+ box2 = box2.transpose()
+
+ # Get the coordinates of bounding boxes
+ b1_x1, b1_y1, b1_x2, b1_y2 = box1[0], box1[1], box1[2], box1[3]
+ b2_x1, b2_y1, b2_x2, b2_y2 = box2[0], box2[1], box2[2], box2[3]
+
+ # Intersection area
+ inter_area = (np.minimum(b1_x2, b2_x2) - np.maximum(b1_x1, b2_x1)).clip(0) * \
+ (np.minimum(b1_y2, b2_y2) - np.maximum(b1_y1, b2_y1)).clip(0)
+
+ # box2 area
+ box2_area = (b2_x2 - b2_x1) * (b2_y2 - b2_y1) + eps
+
+ # Intersection over box2 area
+ return inter_area / box2_area
+
+
+def wh_iou(wh1, wh2):
+ # Returns the nxm IoU matrix. wh1 is nx2, wh2 is mx2
+ wh1 = wh1[:, None] # [N,1,2]
+ wh2 = wh2[None] # [1,M,2]
+ inter = torch.min(wh1, wh2).prod(2) # [N,M]
+ return inter / (wh1.prod(2) + wh2.prod(2) - inter) # iou = inter / (area1 + area2 - inter)
+
+
+# Plots ----------------------------------------------------------------------------------------------------------------
+
+def plot_pr_curve(px, py, ap, save_dir='pr_curve.png', names=()):
+ # Precision-recall curve
+ fig, ax = plt.subplots(1, 1, figsize=(9, 6), tight_layout=True)
+ py = np.stack(py, axis=1)
+
+ if 0 < len(names) < 21: # display per-class legend if < 21 classes
+ for i, y in enumerate(py.T):
+ ax.plot(px, y, linewidth=1, label=f'{names[i]} {ap[i, 0]:.3f}') # plot(recall, precision)
+ else:
+ ax.plot(px, py, linewidth=1, color='grey') # plot(recall, precision)
+
+ ax.plot(px, py.mean(1), linewidth=3, color='blue', label='all classes %.3f mAP@0.5' % ap[:, 0].mean())
+ ax.set_xlabel('Recall')
+ ax.set_ylabel('Precision')
+ ax.set_xlim(0, 1)
+ ax.set_ylim(0, 1)
+ plt.legend(bbox_to_anchor=(1.04, 1), loc="upper left")
+ fig.savefig(Path(save_dir), dpi=250)
+ plt.close()
+
+
+def plot_mc_curve(px, py, save_dir='mc_curve.png', names=(), xlabel='Confidence', ylabel='Metric'):
+ # Metric-confidence curve
+ fig, ax = plt.subplots(1, 1, figsize=(9, 6), tight_layout=True)
+
+ if 0 < len(names) < 21: # display per-class legend if < 21 classes
+ for i, y in enumerate(py):
+ ax.plot(px, y, linewidth=1, label=f'{names[i]}') # plot(confidence, metric)
+ else:
+ ax.plot(px, py.T, linewidth=1, color='grey') # plot(confidence, metric)
+
+ y = py.mean(0)
+ ax.plot(px, y, linewidth=3, color='blue', label=f'all classes {y.max():.2f} at {px[y.argmax()]:.3f}')
+ ax.set_xlabel(xlabel)
+ ax.set_ylabel(ylabel)
+ ax.set_xlim(0, 1)
+ ax.set_ylim(0, 1)
+ plt.legend(bbox_to_anchor=(1.04, 1), loc="upper left")
+ fig.savefig(Path(save_dir), dpi=250)
+ plt.close()
diff --git a/ros2_ws/src/yolov3_ros/utils/plots.py b/ros2_ws/src/yolov3_ros/utils/plots.py
new file mode 100644
index 00000000..16ae44a7
--- /dev/null
+++ b/ros2_ws/src/yolov3_ros/utils/plots.py
@@ -0,0 +1,469 @@
+# YOLOv3 🚀 by Ultralytics, GPL-3.0 license
+"""
+Plotting utils
+"""
+
+import math
+import os
+from copy import copy
+from pathlib import Path
+
+import cv2
+import matplotlib
+import matplotlib.pyplot as plt
+import numpy as np
+import pandas as pd
+import seaborn as sn
+import torch
+from PIL import Image, ImageDraw, ImageFont
+
+from utils.general import (LOGGER, Timeout, check_requirements, clip_coords, increment_path, is_ascii, is_chinese,
+ try_except, user_config_dir, xywh2xyxy, xyxy2xywh)
+from utils.metrics import fitness
+
+# Settings
+CONFIG_DIR = user_config_dir() # Ultralytics settings dir
+RANK = int(os.getenv('RANK', -1))
+matplotlib.rc('font', **{'size': 11})
+matplotlib.use('Agg') # for writing to files only
+
+
+class Colors:
+ # Ultralytics color palette https://ultralytics.com/
+ def __init__(self):
+ # hex = matplotlib.colors.TABLEAU_COLORS.values()
+ hex = ('FF3838', 'FF9D97', 'FF701F', 'FFB21D', 'CFD231', '48F90A', '92CC17', '3DDB86', '1A9334', '00D4BB',
+ '2C99A8', '00C2FF', '344593', '6473FF', '0018EC', '8438FF', '520085', 'CB38FF', 'FF95C8', 'FF37C7')
+ self.palette = [self.hex2rgb('#' + c) for c in hex]
+ self.n = len(self.palette)
+
+ def __call__(self, i, bgr=False):
+ c = self.palette[int(i) % self.n]
+ return (c[2], c[1], c[0]) if bgr else c
+
+ @staticmethod
+ def hex2rgb(h): # rgb order (PIL)
+ return tuple(int(h[1 + i:1 + i + 2], 16) for i in (0, 2, 4))
+
+
+colors = Colors() # create instance for 'from utils.plots import colors'
+
+
+def check_font(font='Arial.ttf', size=10):
+ # Return a PIL TrueType Font, downloading to CONFIG_DIR if necessary
+ font = Path(font)
+ font = font if font.exists() else (CONFIG_DIR / font.name)
+ try:
+ return ImageFont.truetype(str(font) if font.exists() else font.name, size)
+ except Exception as e: # download if missing
+ url = "https://ultralytics.com/assets/" + font.name
+ print(f'Downloading {url} to {font}...')
+ torch.hub.download_url_to_file(url, str(font), progress=False)
+ try:
+ return ImageFont.truetype(str(font), size)
+ except TypeError:
+ check_requirements('Pillow>=8.4.0') # known issue https://github.com/ultralytics/yolov5/issues/5374
+
+
+class Annotator:
+ if RANK in (-1, 0):
+ check_font() # download TTF if necessary
+
+ # Annotator for train/val mosaics and jpgs and detect/hub inference annotations
+ def __init__(self, im, line_width=None, font_size=None, font='Arial.ttf', pil=False, example='abc'):
+ assert im.data.contiguous, 'Image not contiguous. Apply np.ascontiguousarray(im) to Annotator() input images.'
+ self.pil = pil or not is_ascii(example) or is_chinese(example)
+ if self.pil: # use PIL
+ self.im = im if isinstance(im, Image.Image) else Image.fromarray(im)
+ self.draw = ImageDraw.Draw(self.im)
+ self.font = check_font(font='Arial.Unicode.ttf' if is_chinese(example) else font,
+ size=font_size or max(round(sum(self.im.size) / 2 * 0.035), 12))
+ else: # use cv2
+ self.im = im
+ self.lw = line_width or max(round(sum(im.shape) / 2 * 0.003), 2) # line width
+
+ def box_label(self, box, label='', color=(128, 128, 128), txt_color=(255, 255, 255)):
+ # Add one xyxy box to image with label
+ if self.pil or not is_ascii(label):
+ self.draw.rectangle(box, width=self.lw, outline=color) # box
+ if label:
+ w, h = self.font.getsize(label) # text width, height
+ outside = box[1] - h >= 0 # label fits outside box
+ self.draw.rectangle([box[0],
+ box[1] - h if outside else box[1],
+ box[0] + w + 1,
+ box[1] + 1 if outside else box[1] + h + 1], fill=color)
+ # self.draw.text((box[0], box[1]), label, fill=txt_color, font=self.font, anchor='ls') # for PIL>8.0
+ self.draw.text((box[0], box[1] - h if outside else box[1]), label, fill=txt_color, font=self.font)
+ else: # cv2
+ p1, p2 = (int(box[0]), int(box[1])), (int(box[2]), int(box[3]))
+ cv2.rectangle(self.im, p1, p2, color, thickness=self.lw, lineType=cv2.LINE_AA)
+ if label:
+ tf = max(self.lw - 1, 1) # font thickness
+ w, h = cv2.getTextSize(label, 0, fontScale=self.lw / 3, thickness=tf)[0] # text width, height
+ outside = p1[1] - h - 3 >= 0 # label fits outside box
+ p2 = p1[0] + w, p1[1] - h - 3 if outside else p1[1] + h + 3
+ cv2.rectangle(self.im, p1, p2, color, -1, cv2.LINE_AA) # filled
+ cv2.putText(self.im, label, (p1[0], p1[1] - 2 if outside else p1[1] + h + 2), 0, self.lw / 3, txt_color,
+ thickness=tf, lineType=cv2.LINE_AA)
+
+ def rectangle(self, xy, fill=None, outline=None, width=1):
+ # Add rectangle to image (PIL-only)
+ self.draw.rectangle(xy, fill, outline, width)
+
+ def text(self, xy, text, txt_color=(255, 255, 255)):
+ # Add text to image (PIL-only)
+ w, h = self.font.getsize(text) # text width, height
+ self.draw.text((xy[0], xy[1] - h + 1), text, fill=txt_color, font=self.font)
+
+ def result(self):
+ # Return annotated image as array
+ return np.asarray(self.im)
+
+
+def feature_visualization(x, module_type, stage, n=32, save_dir=Path('runs/detect/exp')):
+ """
+ x: Features to be visualized
+ module_type: Module type
+ stage: Module stage within model
+ n: Maximum number of feature maps to plot
+ save_dir: Directory to save results
+ """
+ if 'Detect' not in module_type:
+ batch, channels, height, width = x.shape # batch, channels, height, width
+ if height > 1 and width > 1:
+ f = f"stage{stage}_{module_type.split('.')[-1]}_features.png" # filename
+
+ blocks = torch.chunk(x[0].cpu(), channels, dim=0) # select batch index 0, block by channels
+ n = min(n, channels) # number of plots
+ fig, ax = plt.subplots(math.ceil(n / 8), 8, tight_layout=True) # 8 rows x n/8 cols
+ ax = ax.ravel()
+ plt.subplots_adjust(wspace=0.05, hspace=0.05)
+ for i in range(n):
+ ax[i].imshow(blocks[i].squeeze()) # cmap='gray'
+ ax[i].axis('off')
+
+ print(f'Saving {save_dir / f}... ({n}/{channels})')
+ plt.savefig(save_dir / f, dpi=300, bbox_inches='tight')
+ plt.close()
+
+
+def hist2d(x, y, n=100):
+ # 2d histogram used in labels.png and evolve.png
+ xedges, yedges = np.linspace(x.min(), x.max(), n), np.linspace(y.min(), y.max(), n)
+ hist, xedges, yedges = np.histogram2d(x, y, (xedges, yedges))
+ xidx = np.clip(np.digitize(x, xedges) - 1, 0, hist.shape[0] - 1)
+ yidx = np.clip(np.digitize(y, yedges) - 1, 0, hist.shape[1] - 1)
+ return np.log(hist[xidx, yidx])
+
+
+def butter_lowpass_filtfilt(data, cutoff=1500, fs=50000, order=5):
+ from scipy.signal import butter, filtfilt
+
+ # https://stackoverflow.com/questions/28536191/how-to-filter-smooth-with-scipy-numpy
+ def butter_lowpass(cutoff, fs, order):
+ nyq = 0.5 * fs
+ normal_cutoff = cutoff / nyq
+ return butter(order, normal_cutoff, btype='low', analog=False)
+
+ b, a = butter_lowpass(cutoff, fs, order=order)
+ return filtfilt(b, a, data) # forward-backward filter
+
+
+def output_to_target(output):
+ # Convert model output to target format [batch_id, class_id, x, y, w, h, conf]
+ targets = []
+ for i, o in enumerate(output):
+ for *box, conf, cls in o.cpu().numpy():
+ targets.append([i, cls, *list(*xyxy2xywh(np.array(box)[None])), conf])
+ return np.array(targets)
+
+
+def plot_images(images, targets, paths=None, fname='images.jpg', names=None, max_size=1920, max_subplots=16):
+ # Plot image grid with labels
+ if isinstance(images, torch.Tensor):
+ images = images.cpu().float().numpy()
+ if isinstance(targets, torch.Tensor):
+ targets = targets.cpu().numpy()
+ if np.max(images[0]) <= 1:
+ images *= 255 # de-normalise (optional)
+ bs, _, h, w = images.shape # batch size, _, height, width
+ bs = min(bs, max_subplots) # limit plot images
+ ns = np.ceil(bs ** 0.5) # number of subplots (square)
+
+ # Build Image
+ mosaic = np.full((int(ns * h), int(ns * w), 3), 255, dtype=np.uint8) # init
+ for i, im in enumerate(images):
+ if i == max_subplots: # if last batch has fewer images than we expect
+ break
+ x, y = int(w * (i // ns)), int(h * (i % ns)) # block origin
+ im = im.transpose(1, 2, 0)
+ mosaic[y:y + h, x:x + w, :] = im
+
+ # Resize (optional)
+ scale = max_size / ns / max(h, w)
+ if scale < 1:
+ h = math.ceil(scale * h)
+ w = math.ceil(scale * w)
+ mosaic = cv2.resize(mosaic, tuple(int(x * ns) for x in (w, h)))
+
+ # Annotate
+ fs = int((h + w) * ns * 0.01) # font size
+ annotator = Annotator(mosaic, line_width=round(fs / 10), font_size=fs, pil=True)
+ for i in range(i + 1):
+ x, y = int(w * (i // ns)), int(h * (i % ns)) # block origin
+ annotator.rectangle([x, y, x + w, y + h], None, (255, 255, 255), width=2) # borders
+ if paths:
+ annotator.text((x + 5, y + 5 + h), text=Path(paths[i]).name[:40], txt_color=(220, 220, 220)) # filenames
+ if len(targets) > 0:
+ ti = targets[targets[:, 0] == i] # image targets
+ boxes = xywh2xyxy(ti[:, 2:6]).T
+ classes = ti[:, 1].astype('int')
+ labels = ti.shape[1] == 6 # labels if no conf column
+ conf = None if labels else ti[:, 6] # check for confidence presence (label vs pred)
+
+ if boxes.shape[1]:
+ if boxes.max() <= 1.01: # if normalized with tolerance 0.01
+ boxes[[0, 2]] *= w # scale to pixels
+ boxes[[1, 3]] *= h
+ elif scale < 1: # absolute coords need scale if image scales
+ boxes *= scale
+ boxes[[0, 2]] += x
+ boxes[[1, 3]] += y
+ for j, box in enumerate(boxes.T.tolist()):
+ cls = classes[j]
+ color = colors(cls)
+ cls = names[cls] if names else cls
+ if labels or conf[j] > 0.25: # 0.25 conf thresh
+ label = f'{cls}' if labels else f'{cls} {conf[j]:.1f}'
+ annotator.box_label(box, label, color=color)
+ annotator.im.save(fname) # save
+
+
+def plot_lr_scheduler(optimizer, scheduler, epochs=300, save_dir=''):
+ # Plot LR simulating training for full epochs
+ optimizer, scheduler = copy(optimizer), copy(scheduler) # do not modify originals
+ y = []
+ for _ in range(epochs):
+ scheduler.step()
+ y.append(optimizer.param_groups[0]['lr'])
+ plt.plot(y, '.-', label='LR')
+ plt.xlabel('epoch')
+ plt.ylabel('LR')
+ plt.grid()
+ plt.xlim(0, epochs)
+ plt.ylim(0)
+ plt.savefig(Path(save_dir) / 'LR.png', dpi=200)
+ plt.close()
+
+
+def plot_val_txt(): # from utils.plots import *; plot_val()
+ # Plot val.txt histograms
+ x = np.loadtxt('val.txt', dtype=np.float32)
+ box = xyxy2xywh(x[:, :4])
+ cx, cy = box[:, 0], box[:, 1]
+
+ fig, ax = plt.subplots(1, 1, figsize=(6, 6), tight_layout=True)
+ ax.hist2d(cx, cy, bins=600, cmax=10, cmin=0)
+ ax.set_aspect('equal')
+ plt.savefig('hist2d.png', dpi=300)
+
+ fig, ax = plt.subplots(1, 2, figsize=(12, 6), tight_layout=True)
+ ax[0].hist(cx, bins=600)
+ ax[1].hist(cy, bins=600)
+ plt.savefig('hist1d.png', dpi=200)
+
+
+def plot_targets_txt(): # from utils.plots import *; plot_targets_txt()
+ # Plot targets.txt histograms
+ x = np.loadtxt('targets.txt', dtype=np.float32).T
+ s = ['x targets', 'y targets', 'width targets', 'height targets']
+ fig, ax = plt.subplots(2, 2, figsize=(8, 8), tight_layout=True)
+ ax = ax.ravel()
+ for i in range(4):
+ ax[i].hist(x[i], bins=100, label=f'{x[i].mean():.3g} +/- {x[i].std():.3g}')
+ ax[i].legend()
+ ax[i].set_title(s[i])
+ plt.savefig('targets.jpg', dpi=200)
+
+
+def plot_val_study(file='', dir='', x=None): # from utils.plots import *; plot_val_study()
+ # Plot file=study.txt generated by val.py (or plot all study*.txt in dir)
+ save_dir = Path(file).parent if file else Path(dir)
+ plot2 = False # plot additional results
+ if plot2:
+ ax = plt.subplots(2, 4, figsize=(10, 6), tight_layout=True)[1].ravel()
+
+ fig2, ax2 = plt.subplots(1, 1, figsize=(8, 4), tight_layout=True)
+ # for f in [save_dir / f'study_coco_{x}.txt' for x in ['yolov3', 'yolov3-spp', 'yolov3-tiny']]:
+ for f in sorted(save_dir.glob('study*.txt')):
+ y = np.loadtxt(f, dtype=np.float32, usecols=[0, 1, 2, 3, 7, 8, 9], ndmin=2).T
+ x = np.arange(y.shape[1]) if x is None else np.array(x)
+ if plot2:
+ s = ['P', 'R', 'mAP@.5', 'mAP@.5:.95', 't_preprocess (ms/img)', 't_inference (ms/img)', 't_NMS (ms/img)']
+ for i in range(7):
+ ax[i].plot(x, y[i], '.-', linewidth=2, markersize=8)
+ ax[i].set_title(s[i])
+
+ j = y[3].argmax() + 1
+ ax2.plot(y[5, 1:j], y[3, 1:j] * 1E2, '.-', linewidth=2, markersize=8,
+ label=f.stem.replace('study_coco_', '').replace('yolo', 'YOLO'))
+
+ ax2.plot(1E3 / np.array([209, 140, 97, 58, 35, 18]), [34.6, 40.5, 43.0, 47.5, 49.7, 51.5],
+ 'k.-', linewidth=2, markersize=8, alpha=.25, label='EfficientDet')
+
+ ax2.grid(alpha=0.2)
+ ax2.set_yticks(np.arange(20, 60, 5))
+ ax2.set_xlim(0, 57)
+ ax2.set_ylim(25, 55)
+ ax2.set_xlabel('GPU Speed (ms/img)')
+ ax2.set_ylabel('COCO AP val')
+ ax2.legend(loc='lower right')
+ f = save_dir / 'study.png'
+ print(f'Saving {f}...')
+ plt.savefig(f, dpi=300)
+
+
+@try_except # known issue https://github.com/ultralytics/yolov5/issues/5395
+@Timeout(30) # known issue https://github.com/ultralytics/yolov5/issues/5611
+def plot_labels(labels, names=(), save_dir=Path('')):
+ # plot dataset labels
+ LOGGER.info(f"Plotting labels to {save_dir / 'labels.jpg'}... ")
+ c, b = labels[:, 0], labels[:, 1:].transpose() # classes, boxes
+ nc = int(c.max() + 1) # number of classes
+ x = pd.DataFrame(b.transpose(), columns=['x', 'y', 'width', 'height'])
+
+ # seaborn correlogram
+ sn.pairplot(x, corner=True, diag_kind='auto', kind='hist', diag_kws=dict(bins=50), plot_kws=dict(pmax=0.9))
+ plt.savefig(save_dir / 'labels_correlogram.jpg', dpi=200)
+ plt.close()
+
+ # matplotlib labels
+ matplotlib.use('svg') # faster
+ ax = plt.subplots(2, 2, figsize=(8, 8), tight_layout=True)[1].ravel()
+ y = ax[0].hist(c, bins=np.linspace(0, nc, nc + 1) - 0.5, rwidth=0.8)
+ # [y[2].patches[i].set_color([x / 255 for x in colors(i)]) for i in range(nc)] # update colors bug #3195
+ ax[0].set_ylabel('instances')
+ if 0 < len(names) < 30:
+ ax[0].set_xticks(range(len(names)))
+ ax[0].set_xticklabels(names, rotation=90, fontsize=10)
+ else:
+ ax[0].set_xlabel('classes')
+ sn.histplot(x, x='x', y='y', ax=ax[2], bins=50, pmax=0.9)
+ sn.histplot(x, x='width', y='height', ax=ax[3], bins=50, pmax=0.9)
+
+ # rectangles
+ labels[:, 1:3] = 0.5 # center
+ labels[:, 1:] = xywh2xyxy(labels[:, 1:]) * 2000
+ img = Image.fromarray(np.ones((2000, 2000, 3), dtype=np.uint8) * 255)
+ for cls, *box in labels[:1000]:
+ ImageDraw.Draw(img).rectangle(box, width=1, outline=colors(cls)) # plot
+ ax[1].imshow(img)
+ ax[1].axis('off')
+
+ for a in [0, 1, 2, 3]:
+ for s in ['top', 'right', 'left', 'bottom']:
+ ax[a].spines[s].set_visible(False)
+
+ plt.savefig(save_dir / 'labels.jpg', dpi=200)
+ matplotlib.use('Agg')
+ plt.close()
+
+
+def plot_evolve(evolve_csv='path/to/evolve.csv'): # from utils.plots import *; plot_evolve()
+ # Plot evolve.csv hyp evolution results
+ evolve_csv = Path(evolve_csv)
+ data = pd.read_csv(evolve_csv)
+ keys = [x.strip() for x in data.columns]
+ x = data.values
+ f = fitness(x)
+ j = np.argmax(f) # max fitness index
+ plt.figure(figsize=(10, 12), tight_layout=True)
+ matplotlib.rc('font', **{'size': 8})
+ for i, k in enumerate(keys[7:]):
+ v = x[:, 7 + i]
+ mu = v[j] # best single result
+ plt.subplot(6, 5, i + 1)
+ plt.scatter(v, f, c=hist2d(v, f, 20), cmap='viridis', alpha=.8, edgecolors='none')
+ plt.plot(mu, f.max(), 'k+', markersize=15)
+ plt.title(f'{k} = {mu:.3g}', fontdict={'size': 9}) # limit to 40 characters
+ if i % 5 != 0:
+ plt.yticks([])
+ print(f'{k:>15}: {mu:.3g}')
+ f = evolve_csv.with_suffix('.png') # filename
+ plt.savefig(f, dpi=200)
+ plt.close()
+ print(f'Saved {f}')
+
+
+def plot_results(file='path/to/results.csv', dir=''):
+ # Plot training results.csv. Usage: from utils.plots import *; plot_results('path/to/results.csv')
+ save_dir = Path(file).parent if file else Path(dir)
+ fig, ax = plt.subplots(2, 5, figsize=(12, 6), tight_layout=True)
+ ax = ax.ravel()
+ files = list(save_dir.glob('results*.csv'))
+ assert len(files), f'No results.csv files found in {save_dir.resolve()}, nothing to plot.'
+ for fi, f in enumerate(files):
+ try:
+ data = pd.read_csv(f)
+ s = [x.strip() for x in data.columns]
+ x = data.values[:, 0]
+ for i, j in enumerate([1, 2, 3, 4, 5, 8, 9, 10, 6, 7]):
+ y = data.values[:, j]
+ # y[y == 0] = np.nan # don't show zero values
+ ax[i].plot(x, y, marker='.', label=f.stem, linewidth=2, markersize=8)
+ ax[i].set_title(s[j], fontsize=12)
+ # if j in [8, 9, 10]: # share train and val loss y axes
+ # ax[i].get_shared_y_axes().join(ax[i], ax[i - 5])
+ except Exception as e:
+ print(f'Warning: Plotting error for {f}: {e}')
+ ax[1].legend()
+ fig.savefig(save_dir / 'results.png', dpi=200)
+ plt.close()
+
+
+def profile_idetection(start=0, stop=0, labels=(), save_dir=''):
+ # Plot iDetection '*.txt' per-image logs. from utils.plots import *; profile_idetection()
+ ax = plt.subplots(2, 4, figsize=(12, 6), tight_layout=True)[1].ravel()
+ s = ['Images', 'Free Storage (GB)', 'RAM Usage (GB)', 'Battery', 'dt_raw (ms)', 'dt_smooth (ms)', 'real-world FPS']
+ files = list(Path(save_dir).glob('frames*.txt'))
+ for fi, f in enumerate(files):
+ try:
+ results = np.loadtxt(f, ndmin=2).T[:, 90:-30] # clip first and last rows
+ n = results.shape[1] # number of rows
+ x = np.arange(start, min(stop, n) if stop else n)
+ results = results[:, x]
+ t = (results[0] - results[0].min()) # set t0=0s
+ results[0] = x
+ for i, a in enumerate(ax):
+ if i < len(results):
+ label = labels[fi] if len(labels) else f.stem.replace('frames_', '')
+ a.plot(t, results[i], marker='.', label=label, linewidth=1, markersize=5)
+ a.set_title(s[i])
+ a.set_xlabel('time (s)')
+ # if fi == len(files) - 1:
+ # a.set_ylim(bottom=0)
+ for side in ['top', 'right']:
+ a.spines[side].set_visible(False)
+ else:
+ a.remove()
+ except Exception as e:
+ print(f'Warning: Plotting error for {f}; {e}')
+ ax[1].legend()
+ plt.savefig(Path(save_dir) / 'idetection_profile.png', dpi=200)
+
+
+def save_one_box(xyxy, im, file='image.jpg', gain=1.02, pad=10, square=False, BGR=False, save=True):
+ # Save image crop as {file} with crop size multiple {gain} and {pad} pixels. Save and/or return crop
+ xyxy = torch.tensor(xyxy).view(-1, 4)
+ b = xyxy2xywh(xyxy) # boxes
+ if square:
+ b[:, 2:] = b[:, 2:].max(1)[0].unsqueeze(1) # attempt rectangle to square
+ b[:, 2:] = b[:, 2:] * gain + pad # box wh * gain + pad
+ xyxy = xywh2xyxy(b).long()
+ clip_coords(xyxy, im.shape)
+ crop = im[int(xyxy[0, 1]):int(xyxy[0, 3]), int(xyxy[0, 0]):int(xyxy[0, 2]), ::(1 if BGR else -1)]
+ if save:
+ file.parent.mkdir(parents=True, exist_ok=True) # make directory
+ cv2.imwrite(str(increment_path(file).with_suffix('.jpg')), crop)
+ return crop
diff --git a/ros2_ws/src/yolov3_ros/utils/segment/__init__.py b/ros2_ws/src/yolov3_ros/utils/segment/__init__.py
new file mode 100644
index 00000000..e69de29b
diff --git a/ros2_ws/src/yolov3_ros/utils/segment/augmentations.py b/ros2_ws/src/yolov3_ros/utils/segment/augmentations.py
new file mode 100644
index 00000000..2897b7f4
--- /dev/null
+++ b/ros2_ws/src/yolov3_ros/utils/segment/augmentations.py
@@ -0,0 +1,104 @@
+# YOLOv3 🚀 by Ultralytics, GPL-3.0 license
+"""
+Image augmentation functions
+"""
+
+import math
+import random
+
+import cv2
+import numpy as np
+
+from ..augmentations import box_candidates
+from ..general import resample_segments, segment2box
+
+
+def mixup(im, labels, segments, im2, labels2, segments2):
+ # Applies MixUp augmentation https://arxiv.org/pdf/1710.09412.pdf
+ r = np.random.beta(32.0, 32.0) # mixup ratio, alpha=beta=32.0
+ im = (im * r + im2 * (1 - r)).astype(np.uint8)
+ labels = np.concatenate((labels, labels2), 0)
+ segments = np.concatenate((segments, segments2), 0)
+ return im, labels, segments
+
+
+def random_perspective(im,
+ targets=(),
+ segments=(),
+ degrees=10,
+ translate=.1,
+ scale=.1,
+ shear=10,
+ perspective=0.0,
+ border=(0, 0)):
+ # torchvision.transforms.RandomAffine(degrees=(-10, 10), translate=(.1, .1), scale=(.9, 1.1), shear=(-10, 10))
+ # targets = [cls, xyxy]
+
+ height = im.shape[0] + border[0] * 2 # shape(h,w,c)
+ width = im.shape[1] + border[1] * 2
+
+ # Center
+ C = np.eye(3)
+ C[0, 2] = -im.shape[1] / 2 # x translation (pixels)
+ C[1, 2] = -im.shape[0] / 2 # y translation (pixels)
+
+ # Perspective
+ P = np.eye(3)
+ P[2, 0] = random.uniform(-perspective, perspective) # x perspective (about y)
+ P[2, 1] = random.uniform(-perspective, perspective) # y perspective (about x)
+
+ # Rotation and Scale
+ R = np.eye(3)
+ a = random.uniform(-degrees, degrees)
+ # a += random.choice([-180, -90, 0, 90]) # add 90deg rotations to small rotations
+ s = random.uniform(1 - scale, 1 + scale)
+ # s = 2 ** random.uniform(-scale, scale)
+ R[:2] = cv2.getRotationMatrix2D(angle=a, center=(0, 0), scale=s)
+
+ # Shear
+ S = np.eye(3)
+ S[0, 1] = math.tan(random.uniform(-shear, shear) * math.pi / 180) # x shear (deg)
+ S[1, 0] = math.tan(random.uniform(-shear, shear) * math.pi / 180) # y shear (deg)
+
+ # Translation
+ T = np.eye(3)
+ T[0, 2] = (random.uniform(0.5 - translate, 0.5 + translate) * width) # x translation (pixels)
+ T[1, 2] = (random.uniform(0.5 - translate, 0.5 + translate) * height) # y translation (pixels)
+
+ # Combined rotation matrix
+ M = T @ S @ R @ P @ C # order of operations (right to left) is IMPORTANT
+ if (border[0] != 0) or (border[1] != 0) or (M != np.eye(3)).any(): # image changed
+ if perspective:
+ im = cv2.warpPerspective(im, M, dsize=(width, height), borderValue=(114, 114, 114))
+ else: # affine
+ im = cv2.warpAffine(im, M[:2], dsize=(width, height), borderValue=(114, 114, 114))
+
+ # Visualize
+ # import matplotlib.pyplot as plt
+ # ax = plt.subplots(1, 2, figsize=(12, 6))[1].ravel()
+ # ax[0].imshow(im[:, :, ::-1]) # base
+ # ax[1].imshow(im2[:, :, ::-1]) # warped
+
+ # Transform label coordinates
+ n = len(targets)
+ new_segments = []
+ if n:
+ new = np.zeros((n, 4))
+ segments = resample_segments(segments) # upsample
+ for i, segment in enumerate(segments):
+ xy = np.ones((len(segment), 3))
+ xy[:, :2] = segment
+ xy = xy @ M.T # transform
+ xy = (xy[:, :2] / xy[:, 2:3] if perspective else xy[:, :2]) # perspective rescale or affine
+
+ # clip
+ new[i] = segment2box(xy, width, height)
+ new_segments.append(xy)
+
+ # filter candidates
+ i = box_candidates(box1=targets[:, 1:5].T * s, box2=new.T, area_thr=0.01)
+ targets = targets[i]
+ targets[:, 1:5] = new[i]
+ new_segments = np.array(new_segments)[i]
+
+ return im, targets, new_segments
diff --git a/ros2_ws/src/yolov3_ros/utils/segment/dataloaders.py b/ros2_ws/src/yolov3_ros/utils/segment/dataloaders.py
new file mode 100644
index 00000000..d0f59562
--- /dev/null
+++ b/ros2_ws/src/yolov3_ros/utils/segment/dataloaders.py
@@ -0,0 +1,332 @@
+# YOLOv3 🚀 by Ultralytics, GPL-3.0 license
+"""
+Dataloaders
+"""
+
+import os
+import random
+
+import cv2
+import numpy as np
+import torch
+from torch.utils.data import DataLoader, distributed
+
+from ..augmentations import augment_hsv, copy_paste, letterbox
+from ..dataloaders import InfiniteDataLoader, LoadImagesAndLabels, seed_worker
+from ..general import LOGGER, xyn2xy, xywhn2xyxy, xyxy2xywhn
+from ..torch_utils import torch_distributed_zero_first
+from .augmentations import mixup, random_perspective
+
+RANK = int(os.getenv('RANK', -1))
+
+
+def create_dataloader(path,
+ imgsz,
+ batch_size,
+ stride,
+ single_cls=False,
+ hyp=None,
+ augment=False,
+ cache=False,
+ pad=0.0,
+ rect=False,
+ rank=-1,
+ workers=8,
+ image_weights=False,
+ quad=False,
+ prefix='',
+ shuffle=False,
+ mask_downsample_ratio=1,
+ overlap_mask=False,
+ seed=0):
+ if rect and shuffle:
+ LOGGER.warning('WARNING ⚠️ --rect is incompatible with DataLoader shuffle, setting shuffle=False')
+ shuffle = False
+ with torch_distributed_zero_first(rank): # init dataset *.cache only once if DDP
+ dataset = LoadImagesAndLabelsAndMasks(
+ path,
+ imgsz,
+ batch_size,
+ augment=augment, # augmentation
+ hyp=hyp, # hyperparameters
+ rect=rect, # rectangular batches
+ cache_images=cache,
+ single_cls=single_cls,
+ stride=int(stride),
+ pad=pad,
+ image_weights=image_weights,
+ prefix=prefix,
+ downsample_ratio=mask_downsample_ratio,
+ overlap=overlap_mask)
+
+ batch_size = min(batch_size, len(dataset))
+ nd = torch.cuda.device_count() # number of CUDA devices
+ nw = min([os.cpu_count() // max(nd, 1), batch_size if batch_size > 1 else 0, workers]) # number of workers
+ sampler = None if rank == -1 else distributed.DistributedSampler(dataset, shuffle=shuffle)
+ loader = DataLoader if image_weights else InfiniteDataLoader # only DataLoader allows for attribute updates
+ generator = torch.Generator()
+ generator.manual_seed(6148914691236517205 + seed + RANK)
+ return loader(
+ dataset,
+ batch_size=batch_size,
+ shuffle=shuffle and sampler is None,
+ num_workers=nw,
+ sampler=sampler,
+ pin_memory=True,
+ collate_fn=LoadImagesAndLabelsAndMasks.collate_fn4 if quad else LoadImagesAndLabelsAndMasks.collate_fn,
+ worker_init_fn=seed_worker,
+ generator=generator,
+ ), dataset
+
+
+class LoadImagesAndLabelsAndMasks(LoadImagesAndLabels): # for training/testing
+
+ def __init__(
+ self,
+ path,
+ img_size=640,
+ batch_size=16,
+ augment=False,
+ hyp=None,
+ rect=False,
+ image_weights=False,
+ cache_images=False,
+ single_cls=False,
+ stride=32,
+ pad=0,
+ min_items=0,
+ prefix='',
+ downsample_ratio=1,
+ overlap=False,
+ ):
+ super().__init__(path, img_size, batch_size, augment, hyp, rect, image_weights, cache_images, single_cls,
+ stride, pad, min_items, prefix)
+ self.downsample_ratio = downsample_ratio
+ self.overlap = overlap
+
+ def __getitem__(self, index):
+ index = self.indices[index] # linear, shuffled, or image_weights
+
+ hyp = self.hyp
+ mosaic = self.mosaic and random.random() < hyp['mosaic']
+ masks = []
+ if mosaic:
+ # Load mosaic
+ img, labels, segments = self.load_mosaic(index)
+ shapes = None
+
+ # MixUp augmentation
+ if random.random() < hyp['mixup']:
+ img, labels, segments = mixup(img, labels, segments, *self.load_mosaic(random.randint(0, self.n - 1)))
+
+ else:
+ # Load image
+ img, (h0, w0), (h, w) = self.load_image(index)
+
+ # Letterbox
+ shape = self.batch_shapes[self.batch[index]] if self.rect else self.img_size # final letterboxed shape
+ img, ratio, pad = letterbox(img, shape, auto=False, scaleup=self.augment)
+ shapes = (h0, w0), ((h / h0, w / w0), pad) # for COCO mAP rescaling
+
+ labels = self.labels[index].copy()
+ # [array, array, ....], array.shape=(num_points, 2), xyxyxyxy
+ segments = self.segments[index].copy()
+ if len(segments):
+ for i_s in range(len(segments)):
+ segments[i_s] = xyn2xy(
+ segments[i_s],
+ ratio[0] * w,
+ ratio[1] * h,
+ padw=pad[0],
+ padh=pad[1],
+ )
+ if labels.size: # normalized xywh to pixel xyxy format
+ labels[:, 1:] = xywhn2xyxy(labels[:, 1:], ratio[0] * w, ratio[1] * h, padw=pad[0], padh=pad[1])
+
+ if self.augment:
+ img, labels, segments = random_perspective(img,
+ labels,
+ segments=segments,
+ degrees=hyp['degrees'],
+ translate=hyp['translate'],
+ scale=hyp['scale'],
+ shear=hyp['shear'],
+ perspective=hyp['perspective'])
+
+ nl = len(labels) # number of labels
+ if nl:
+ labels[:, 1:5] = xyxy2xywhn(labels[:, 1:5], w=img.shape[1], h=img.shape[0], clip=True, eps=1e-3)
+ if self.overlap:
+ masks, sorted_idx = polygons2masks_overlap(img.shape[:2],
+ segments,
+ downsample_ratio=self.downsample_ratio)
+ masks = masks[None] # (640, 640) -> (1, 640, 640)
+ labels = labels[sorted_idx]
+ else:
+ masks = polygons2masks(img.shape[:2], segments, color=1, downsample_ratio=self.downsample_ratio)
+
+ masks = (torch.from_numpy(masks) if len(masks) else torch.zeros(1 if self.overlap else nl, img.shape[0] //
+ self.downsample_ratio, img.shape[1] //
+ self.downsample_ratio))
+ # TODO: albumentations support
+ if self.augment:
+ # Albumentations
+ # there are some augmentation that won't change boxes and masks,
+ # so just be it for now.
+ img, labels = self.albumentations(img, labels)
+ nl = len(labels) # update after albumentations
+
+ # HSV color-space
+ augment_hsv(img, hgain=hyp['hsv_h'], sgain=hyp['hsv_s'], vgain=hyp['hsv_v'])
+
+ # Flip up-down
+ if random.random() < hyp['flipud']:
+ img = np.flipud(img)
+ if nl:
+ labels[:, 2] = 1 - labels[:, 2]
+ masks = torch.flip(masks, dims=[1])
+
+ # Flip left-right
+ if random.random() < hyp['fliplr']:
+ img = np.fliplr(img)
+ if nl:
+ labels[:, 1] = 1 - labels[:, 1]
+ masks = torch.flip(masks, dims=[2])
+
+ # Cutouts # labels = cutout(img, labels, p=0.5)
+
+ labels_out = torch.zeros((nl, 6))
+ if nl:
+ labels_out[:, 1:] = torch.from_numpy(labels)
+
+ # Convert
+ img = img.transpose((2, 0, 1))[::-1] # HWC to CHW, BGR to RGB
+ img = np.ascontiguousarray(img)
+
+ return (torch.from_numpy(img), labels_out, self.im_files[index], shapes, masks)
+
+ def load_mosaic(self, index):
+ # YOLOv5 4-mosaic loader. Loads 1 image + 3 random images into a 4-image mosaic
+ labels4, segments4 = [], []
+ s = self.img_size
+ yc, xc = (int(random.uniform(-x, 2 * s + x)) for x in self.mosaic_border) # mosaic center x, y
+
+ # 3 additional image indices
+ indices = [index] + random.choices(self.indices, k=3) # 3 additional image indices
+ for i, index in enumerate(indices):
+ # Load image
+ img, _, (h, w) = self.load_image(index)
+
+ # place img in img4
+ if i == 0: # top left
+ img4 = np.full((s * 2, s * 2, img.shape[2]), 114, dtype=np.uint8) # base image with 4 tiles
+ x1a, y1a, x2a, y2a = max(xc - w, 0), max(yc - h, 0), xc, yc # xmin, ymin, xmax, ymax (large image)
+ x1b, y1b, x2b, y2b = w - (x2a - x1a), h - (y2a - y1a), w, h # xmin, ymin, xmax, ymax (small image)
+ elif i == 1: # top right
+ x1a, y1a, x2a, y2a = xc, max(yc - h, 0), min(xc + w, s * 2), yc
+ x1b, y1b, x2b, y2b = 0, h - (y2a - y1a), min(w, x2a - x1a), h
+ elif i == 2: # bottom left
+ x1a, y1a, x2a, y2a = max(xc - w, 0), yc, xc, min(s * 2, yc + h)
+ x1b, y1b, x2b, y2b = w - (x2a - x1a), 0, w, min(y2a - y1a, h)
+ elif i == 3: # bottom right
+ x1a, y1a, x2a, y2a = xc, yc, min(xc + w, s * 2), min(s * 2, yc + h)
+ x1b, y1b, x2b, y2b = 0, 0, min(w, x2a - x1a), min(y2a - y1a, h)
+
+ img4[y1a:y2a, x1a:x2a] = img[y1b:y2b, x1b:x2b] # img4[ymin:ymax, xmin:xmax]
+ padw = x1a - x1b
+ padh = y1a - y1b
+
+ labels, segments = self.labels[index].copy(), self.segments[index].copy()
+
+ if labels.size:
+ labels[:, 1:] = xywhn2xyxy(labels[:, 1:], w, h, padw, padh) # normalized xywh to pixel xyxy format
+ segments = [xyn2xy(x, w, h, padw, padh) for x in segments]
+ labels4.append(labels)
+ segments4.extend(segments)
+
+ # Concat/clip labels
+ labels4 = np.concatenate(labels4, 0)
+ for x in (labels4[:, 1:], *segments4):
+ np.clip(x, 0, 2 * s, out=x) # clip when using random_perspective()
+ # img4, labels4 = replicate(img4, labels4) # replicate
+
+ # Augment
+ img4, labels4, segments4 = copy_paste(img4, labels4, segments4, p=self.hyp['copy_paste'])
+ img4, labels4, segments4 = random_perspective(img4,
+ labels4,
+ segments4,
+ degrees=self.hyp['degrees'],
+ translate=self.hyp['translate'],
+ scale=self.hyp['scale'],
+ shear=self.hyp['shear'],
+ perspective=self.hyp['perspective'],
+ border=self.mosaic_border) # border to remove
+ return img4, labels4, segments4
+
+ @staticmethod
+ def collate_fn(batch):
+ img, label, path, shapes, masks = zip(*batch) # transposed
+ batched_masks = torch.cat(masks, 0)
+ for i, l in enumerate(label):
+ l[:, 0] = i # add target image index for build_targets()
+ return torch.stack(img, 0), torch.cat(label, 0), path, shapes, batched_masks
+
+
+def polygon2mask(img_size, polygons, color=1, downsample_ratio=1):
+ """
+ Args:
+ img_size (tuple): The image size.
+ polygons (np.ndarray): [N, M], N is the number of polygons,
+ M is the number of points(Be divided by 2).
+ """
+ mask = np.zeros(img_size, dtype=np.uint8)
+ polygons = np.asarray(polygons)
+ polygons = polygons.astype(np.int32)
+ shape = polygons.shape
+ polygons = polygons.reshape(shape[0], -1, 2)
+ cv2.fillPoly(mask, polygons, color=color)
+ nh, nw = (img_size[0] // downsample_ratio, img_size[1] // downsample_ratio)
+ # NOTE: fillPoly firstly then resize is trying the keep the same way
+ # of loss calculation when mask-ratio=1.
+ mask = cv2.resize(mask, (nw, nh))
+ return mask
+
+
+def polygons2masks(img_size, polygons, color, downsample_ratio=1):
+ """
+ Args:
+ img_size (tuple): The image size.
+ polygons (list[np.ndarray]): each polygon is [N, M],
+ N is the number of polygons,
+ M is the number of points(Be divided by 2).
+ """
+ masks = []
+ for si in range(len(polygons)):
+ mask = polygon2mask(img_size, [polygons[si].reshape(-1)], color, downsample_ratio)
+ masks.append(mask)
+ return np.array(masks)
+
+
+def polygons2masks_overlap(img_size, segments, downsample_ratio=1):
+ """Return a (640, 640) overlap mask."""
+ masks = np.zeros((img_size[0] // downsample_ratio, img_size[1] // downsample_ratio),
+ dtype=np.int32 if len(segments) > 255 else np.uint8)
+ areas = []
+ ms = []
+ for si in range(len(segments)):
+ mask = polygon2mask(
+ img_size,
+ [segments[si].reshape(-1)],
+ downsample_ratio=downsample_ratio,
+ color=1,
+ )
+ ms.append(mask)
+ areas.append(mask.sum())
+ areas = np.asarray(areas)
+ index = np.argsort(-areas)
+ ms = np.array(ms)[index]
+ for i in range(len(segments)):
+ mask = ms[i] * (i + 1)
+ masks = masks + mask
+ masks = np.clip(masks, a_min=0, a_max=i + 1)
+ return masks, index
diff --git a/ros2_ws/src/yolov3_ros/utils/segment/general.py b/ros2_ws/src/yolov3_ros/utils/segment/general.py
new file mode 100644
index 00000000..9da89453
--- /dev/null
+++ b/ros2_ws/src/yolov3_ros/utils/segment/general.py
@@ -0,0 +1,160 @@
+import cv2
+import numpy as np
+import torch
+import torch.nn.functional as F
+
+
+def crop_mask(masks, boxes):
+ """
+ "Crop" predicted masks by zeroing out everything not in the predicted bbox.
+ Vectorized by Chong (thanks Chong).
+
+ Args:
+ - masks should be a size [h, w, n] tensor of masks
+ - boxes should be a size [n, 4] tensor of bbox coords in relative point form
+ """
+
+ n, h, w = masks.shape
+ x1, y1, x2, y2 = torch.chunk(boxes[:, :, None], 4, 1) # x1 shape(1,1,n)
+ r = torch.arange(w, device=masks.device, dtype=x1.dtype)[None, None, :] # rows shape(1,w,1)
+ c = torch.arange(h, device=masks.device, dtype=x1.dtype)[None, :, None] # cols shape(h,1,1)
+
+ return masks * ((r >= x1) * (r < x2) * (c >= y1) * (c < y2))
+
+
+def process_mask_upsample(protos, masks_in, bboxes, shape):
+ """
+ Crop after upsample.
+ protos: [mask_dim, mask_h, mask_w]
+ masks_in: [n, mask_dim], n is number of masks after nms
+ bboxes: [n, 4], n is number of masks after nms
+ shape: input_image_size, (h, w)
+
+ return: h, w, n
+ """
+
+ c, mh, mw = protos.shape # CHW
+ masks = (masks_in @ protos.float().view(c, -1)).sigmoid().view(-1, mh, mw)
+ masks = F.interpolate(masks[None], shape, mode='bilinear', align_corners=False)[0] # CHW
+ masks = crop_mask(masks, bboxes) # CHW
+ return masks.gt_(0.5)
+
+
+def process_mask(protos, masks_in, bboxes, shape, upsample=False):
+ """
+ Crop before upsample.
+ proto_out: [mask_dim, mask_h, mask_w]
+ out_masks: [n, mask_dim], n is number of masks after nms
+ bboxes: [n, 4], n is number of masks after nms
+ shape:input_image_size, (h, w)
+
+ return: h, w, n
+ """
+
+ c, mh, mw = protos.shape # CHW
+ ih, iw = shape
+ masks = (masks_in @ protos.float().view(c, -1)).sigmoid().view(-1, mh, mw) # CHW
+
+ downsampled_bboxes = bboxes.clone()
+ downsampled_bboxes[:, 0] *= mw / iw
+ downsampled_bboxes[:, 2] *= mw / iw
+ downsampled_bboxes[:, 3] *= mh / ih
+ downsampled_bboxes[:, 1] *= mh / ih
+
+ masks = crop_mask(masks, downsampled_bboxes) # CHW
+ if upsample:
+ masks = F.interpolate(masks[None], shape, mode='bilinear', align_corners=False)[0] # CHW
+ return masks.gt_(0.5)
+
+
+def process_mask_native(protos, masks_in, bboxes, shape):
+ """
+ Crop after upsample.
+ protos: [mask_dim, mask_h, mask_w]
+ masks_in: [n, mask_dim], n is number of masks after nms
+ bboxes: [n, 4], n is number of masks after nms
+ shape: input_image_size, (h, w)
+
+ return: h, w, n
+ """
+ c, mh, mw = protos.shape # CHW
+ masks = (masks_in @ protos.float().view(c, -1)).sigmoid().view(-1, mh, mw)
+ gain = min(mh / shape[0], mw / shape[1]) # gain = old / new
+ pad = (mw - shape[1] * gain) / 2, (mh - shape[0] * gain) / 2 # wh padding
+ top, left = int(pad[1]), int(pad[0]) # y, x
+ bottom, right = int(mh - pad[1]), int(mw - pad[0])
+ masks = masks[:, top:bottom, left:right]
+
+ masks = F.interpolate(masks[None], shape, mode='bilinear', align_corners=False)[0] # CHW
+ masks = crop_mask(masks, bboxes) # CHW
+ return masks.gt_(0.5)
+
+
+def scale_image(im1_shape, masks, im0_shape, ratio_pad=None):
+ """
+ img1_shape: model input shape, [h, w]
+ img0_shape: origin pic shape, [h, w, 3]
+ masks: [h, w, num]
+ """
+ # Rescale coordinates (xyxy) from im1_shape to im0_shape
+ if ratio_pad is None: # calculate from im0_shape
+ gain = min(im1_shape[0] / im0_shape[0], im1_shape[1] / im0_shape[1]) # gain = old / new
+ pad = (im1_shape[1] - im0_shape[1] * gain) / 2, (im1_shape[0] - im0_shape[0] * gain) / 2 # wh padding
+ else:
+ pad = ratio_pad[1]
+ top, left = int(pad[1]), int(pad[0]) # y, x
+ bottom, right = int(im1_shape[0] - pad[1]), int(im1_shape[1] - pad[0])
+
+ if len(masks.shape) < 2:
+ raise ValueError(f'"len of masks shape" should be 2 or 3, but got {len(masks.shape)}')
+ masks = masks[top:bottom, left:right]
+ # masks = masks.permute(2, 0, 1).contiguous()
+ # masks = F.interpolate(masks[None], im0_shape[:2], mode='bilinear', align_corners=False)[0]
+ # masks = masks.permute(1, 2, 0).contiguous()
+ masks = cv2.resize(masks, (im0_shape[1], im0_shape[0]))
+
+ if len(masks.shape) == 2:
+ masks = masks[:, :, None]
+ return masks
+
+
+def mask_iou(mask1, mask2, eps=1e-7):
+ """
+ mask1: [N, n] m1 means number of predicted objects
+ mask2: [M, n] m2 means number of gt objects
+ Note: n means image_w x image_h
+
+ return: masks iou, [N, M]
+ """
+ intersection = torch.matmul(mask1, mask2.t()).clamp(0)
+ union = (mask1.sum(1)[:, None] + mask2.sum(1)[None]) - intersection # (area1 + area2) - intersection
+ return intersection / (union + eps)
+
+
+def masks_iou(mask1, mask2, eps=1e-7):
+ """
+ mask1: [N, n] m1 means number of predicted objects
+ mask2: [N, n] m2 means number of gt objects
+ Note: n means image_w x image_h
+
+ return: masks iou, (N, )
+ """
+ intersection = (mask1 * mask2).sum(1).clamp(0) # (N, )
+ union = (mask1.sum(1) + mask2.sum(1))[None] - intersection # (area1 + area2) - intersection
+ return intersection / (union + eps)
+
+
+def masks2segments(masks, strategy='largest'):
+ # Convert masks(n,160,160) into segments(n,xy)
+ segments = []
+ for x in masks.int().cpu().numpy().astype('uint8'):
+ c = cv2.findContours(x, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE)[0]
+ if c:
+ if strategy == 'concat': # concatenate all segments
+ c = np.concatenate([x.reshape(-1, 2) for x in c])
+ elif strategy == 'largest': # select largest segment
+ c = np.array(c[np.array([len(x) for x in c]).argmax()]).reshape(-1, 2)
+ else:
+ c = np.zeros((0, 2)) # no segments found
+ segments.append(c.astype('float32'))
+ return segments
diff --git a/ros2_ws/src/yolov3_ros/utils/segment/loss.py b/ros2_ws/src/yolov3_ros/utils/segment/loss.py
new file mode 100644
index 00000000..2a8a4c68
--- /dev/null
+++ b/ros2_ws/src/yolov3_ros/utils/segment/loss.py
@@ -0,0 +1,186 @@
+import torch
+import torch.nn as nn
+import torch.nn.functional as F
+
+from ..general import xywh2xyxy
+from ..loss import FocalLoss, smooth_BCE
+from ..metrics import bbox_iou
+from ..torch_utils import de_parallel
+from .general import crop_mask
+
+
+class ComputeLoss:
+ # Compute losses
+ def __init__(self, model, autobalance=False, overlap=False):
+ self.sort_obj_iou = False
+ self.overlap = overlap
+ device = next(model.parameters()).device # get model device
+ h = model.hyp # hyperparameters
+ self.device = device
+
+ # Define criteria
+ BCEcls = nn.BCEWithLogitsLoss(pos_weight=torch.tensor([h['cls_pw']], device=device))
+ BCEobj = nn.BCEWithLogitsLoss(pos_weight=torch.tensor([h['obj_pw']], device=device))
+
+ # Class label smoothing https://arxiv.org/pdf/1902.04103.pdf eqn 3
+ self.cp, self.cn = smooth_BCE(eps=h.get('label_smoothing', 0.0)) # positive, negative BCE targets
+
+ # Focal loss
+ g = h['fl_gamma'] # focal loss gamma
+ if g > 0:
+ BCEcls, BCEobj = FocalLoss(BCEcls, g), FocalLoss(BCEobj, g)
+
+ m = de_parallel(model).model[-1] # Detect() module
+ self.balance = {3: [4.0, 1.0, 0.4]}.get(m.nl, [4.0, 1.0, 0.25, 0.06, 0.02]) # P3-P7
+ self.ssi = list(m.stride).index(16) if autobalance else 0 # stride 16 index
+ self.BCEcls, self.BCEobj, self.gr, self.hyp, self.autobalance = BCEcls, BCEobj, 1.0, h, autobalance
+ self.na = m.na # number of anchors
+ self.nc = m.nc # number of classes
+ self.nl = m.nl # number of layers
+ self.nm = m.nm # number of masks
+ self.anchors = m.anchors
+ self.device = device
+
+ def __call__(self, preds, targets, masks): # predictions, targets, model
+ p, proto = preds
+ bs, nm, mask_h, mask_w = proto.shape # batch size, number of masks, mask height, mask width
+ lcls = torch.zeros(1, device=self.device)
+ lbox = torch.zeros(1, device=self.device)
+ lobj = torch.zeros(1, device=self.device)
+ lseg = torch.zeros(1, device=self.device)
+ tcls, tbox, indices, anchors, tidxs, xywhn = self.build_targets(p, targets) # targets
+
+ # Losses
+ for i, pi in enumerate(p): # layer index, layer predictions
+ b, a, gj, gi = indices[i] # image, anchor, gridy, gridx
+ tobj = torch.zeros(pi.shape[:4], dtype=pi.dtype, device=self.device) # target obj
+
+ n = b.shape[0] # number of targets
+ if n:
+ pxy, pwh, _, pcls, pmask = pi[b, a, gj, gi].split((2, 2, 1, self.nc, nm), 1) # subset of predictions
+
+ # Box regression
+ pxy = pxy.sigmoid() * 2 - 0.5
+ pwh = (pwh.sigmoid() * 2) ** 2 * anchors[i]
+ pbox = torch.cat((pxy, pwh), 1) # predicted box
+ iou = bbox_iou(pbox, tbox[i], CIoU=True).squeeze() # iou(prediction, target)
+ lbox += (1.0 - iou).mean() # iou loss
+
+ # Objectness
+ iou = iou.detach().clamp(0).type(tobj.dtype)
+ if self.sort_obj_iou:
+ j = iou.argsort()
+ b, a, gj, gi, iou = b[j], a[j], gj[j], gi[j], iou[j]
+ if self.gr < 1:
+ iou = (1.0 - self.gr) + self.gr * iou
+ tobj[b, a, gj, gi] = iou # iou ratio
+
+ # Classification
+ if self.nc > 1: # cls loss (only if multiple classes)
+ t = torch.full_like(pcls, self.cn, device=self.device) # targets
+ t[range(n), tcls[i]] = self.cp
+ lcls += self.BCEcls(pcls, t) # BCE
+
+ # Mask regression
+ if tuple(masks.shape[-2:]) != (mask_h, mask_w): # downsample
+ masks = F.interpolate(masks[None], (mask_h, mask_w), mode='nearest')[0]
+ marea = xywhn[i][:, 2:].prod(1) # mask width, height normalized
+ mxyxy = xywh2xyxy(xywhn[i] * torch.tensor([mask_w, mask_h, mask_w, mask_h], device=self.device))
+ for bi in b.unique():
+ j = b == bi # matching index
+ if self.overlap:
+ mask_gti = torch.where(masks[bi][None] == tidxs[i][j].view(-1, 1, 1), 1.0, 0.0)
+ else:
+ mask_gti = masks[tidxs[i]][j]
+ lseg += self.single_mask_loss(mask_gti, pmask[j], proto[bi], mxyxy[j], marea[j])
+
+ obji = self.BCEobj(pi[..., 4], tobj)
+ lobj += obji * self.balance[i] # obj loss
+ if self.autobalance:
+ self.balance[i] = self.balance[i] * 0.9999 + 0.0001 / obji.detach().item()
+
+ if self.autobalance:
+ self.balance = [x / self.balance[self.ssi] for x in self.balance]
+ lbox *= self.hyp['box']
+ lobj *= self.hyp['obj']
+ lcls *= self.hyp['cls']
+ lseg *= self.hyp['box'] / bs
+
+ loss = lbox + lobj + lcls + lseg
+ return loss * bs, torch.cat((lbox, lseg, lobj, lcls)).detach()
+
+ def single_mask_loss(self, gt_mask, pred, proto, xyxy, area):
+ # Mask loss for one image
+ pred_mask = (pred @ proto.view(self.nm, -1)).view(-1, *proto.shape[1:]) # (n,32) @ (32,80,80) -> (n,80,80)
+ loss = F.binary_cross_entropy_with_logits(pred_mask, gt_mask, reduction='none')
+ return (crop_mask(loss, xyxy).mean(dim=(1, 2)) / area).mean()
+
+ def build_targets(self, p, targets):
+ # Build targets for compute_loss(), input targets(image,class,x,y,w,h)
+ na, nt = self.na, targets.shape[0] # number of anchors, targets
+ tcls, tbox, indices, anch, tidxs, xywhn = [], [], [], [], [], []
+ gain = torch.ones(8, device=self.device) # normalized to gridspace gain
+ ai = torch.arange(na, device=self.device).float().view(na, 1).repeat(1, nt) # same as .repeat_interleave(nt)
+ if self.overlap:
+ batch = p[0].shape[0]
+ ti = []
+ for i in range(batch):
+ num = (targets[:, 0] == i).sum() # find number of targets of each image
+ ti.append(torch.arange(num, device=self.device).float().view(1, num).repeat(na, 1) + 1) # (na, num)
+ ti = torch.cat(ti, 1) # (na, nt)
+ else:
+ ti = torch.arange(nt, device=self.device).float().view(1, nt).repeat(na, 1)
+ targets = torch.cat((targets.repeat(na, 1, 1), ai[..., None], ti[..., None]), 2) # append anchor indices
+
+ g = 0.5 # bias
+ off = torch.tensor(
+ [
+ [0, 0],
+ [1, 0],
+ [0, 1],
+ [-1, 0],
+ [0, -1], # j,k,l,m
+ # [1, 1], [1, -1], [-1, 1], [-1, -1], # jk,jm,lk,lm
+ ],
+ device=self.device).float() * g # offsets
+
+ for i in range(self.nl):
+ anchors, shape = self.anchors[i], p[i].shape
+ gain[2:6] = torch.tensor(shape)[[3, 2, 3, 2]] # xyxy gain
+
+ # Match targets to anchors
+ t = targets * gain # shape(3,n,7)
+ if nt:
+ # Matches
+ r = t[..., 4:6] / anchors[:, None] # wh ratio
+ j = torch.max(r, 1 / r).max(2)[0] < self.hyp['anchor_t'] # compare
+ # j = wh_iou(anchors, t[:, 4:6]) > model.hyp['iou_t'] # iou(3,n)=wh_iou(anchors(3,2), gwh(n,2))
+ t = t[j] # filter
+
+ # Offsets
+ gxy = t[:, 2:4] # grid xy
+ gxi = gain[[2, 3]] - gxy # inverse
+ j, k = ((gxy % 1 < g) & (gxy > 1)).T
+ l, m = ((gxi % 1 < g) & (gxi > 1)).T
+ j = torch.stack((torch.ones_like(j), j, k, l, m))
+ t = t.repeat((5, 1, 1))[j]
+ offsets = (torch.zeros_like(gxy)[None] + off[:, None])[j]
+ else:
+ t = targets[0]
+ offsets = 0
+
+ # Define
+ bc, gxy, gwh, at = t.chunk(4, 1) # (image, class), grid xy, grid wh, anchors
+ (a, tidx), (b, c) = at.long().T, bc.long().T # anchors, image, class
+ gij = (gxy - offsets).long()
+ gi, gj = gij.T # grid indices
+
+ # Append
+ indices.append((b, a, gj.clamp_(0, shape[2] - 1), gi.clamp_(0, shape[3] - 1))) # image, anchor, grid
+ tbox.append(torch.cat((gxy - gij, gwh), 1)) # box
+ anch.append(anchors[a]) # anchors
+ tcls.append(c) # class
+ tidxs.append(tidx)
+ xywhn.append(torch.cat((gxy, gwh), 1) / gain[2:6]) # xywh normalized
+
+ return tcls, tbox, indices, anch, tidxs, xywhn
diff --git a/ros2_ws/src/yolov3_ros/utils/segment/metrics.py b/ros2_ws/src/yolov3_ros/utils/segment/metrics.py
new file mode 100644
index 00000000..6c58dba6
--- /dev/null
+++ b/ros2_ws/src/yolov3_ros/utils/segment/metrics.py
@@ -0,0 +1,210 @@
+# YOLOv3 🚀 by Ultralytics, GPL-3.0 license
+"""
+Model validation metrics
+"""
+
+import numpy as np
+
+from ..metrics import ap_per_class
+
+
+def fitness(x):
+ # Model fitness as a weighted combination of metrics
+ w = [0.0, 0.0, 0.1, 0.9, 0.0, 0.0, 0.1, 0.9]
+ return (x[:, :8] * w).sum(1)
+
+
+def ap_per_class_box_and_mask(
+ tp_m,
+ tp_b,
+ conf,
+ pred_cls,
+ target_cls,
+ plot=False,
+ save_dir='.',
+ names=(),
+):
+ """
+ Args:
+ tp_b: tp of boxes.
+ tp_m: tp of masks.
+ other arguments see `func: ap_per_class`.
+ """
+ results_boxes = ap_per_class(tp_b,
+ conf,
+ pred_cls,
+ target_cls,
+ plot=plot,
+ save_dir=save_dir,
+ names=names,
+ prefix='Box')[2:]
+ results_masks = ap_per_class(tp_m,
+ conf,
+ pred_cls,
+ target_cls,
+ plot=plot,
+ save_dir=save_dir,
+ names=names,
+ prefix='Mask')[2:]
+
+ results = {
+ 'boxes': {
+ 'p': results_boxes[0],
+ 'r': results_boxes[1],
+ 'ap': results_boxes[3],
+ 'f1': results_boxes[2],
+ 'ap_class': results_boxes[4]},
+ 'masks': {
+ 'p': results_masks[0],
+ 'r': results_masks[1],
+ 'ap': results_masks[3],
+ 'f1': results_masks[2],
+ 'ap_class': results_masks[4]}}
+ return results
+
+
+class Metric:
+
+ def __init__(self) -> None:
+ self.p = [] # (nc, )
+ self.r = [] # (nc, )
+ self.f1 = [] # (nc, )
+ self.all_ap = [] # (nc, 10)
+ self.ap_class_index = [] # (nc, )
+
+ @property
+ def ap50(self):
+ """AP@0.5 of all classes.
+ Return:
+ (nc, ) or [].
+ """
+ return self.all_ap[:, 0] if len(self.all_ap) else []
+
+ @property
+ def ap(self):
+ """AP@0.5:0.95
+ Return:
+ (nc, ) or [].
+ """
+ return self.all_ap.mean(1) if len(self.all_ap) else []
+
+ @property
+ def mp(self):
+ """mean precision of all classes.
+ Return:
+ float.
+ """
+ return self.p.mean() if len(self.p) else 0.0
+
+ @property
+ def mr(self):
+ """mean recall of all classes.
+ Return:
+ float.
+ """
+ return self.r.mean() if len(self.r) else 0.0
+
+ @property
+ def map50(self):
+ """Mean AP@0.5 of all classes.
+ Return:
+ float.
+ """
+ return self.all_ap[:, 0].mean() if len(self.all_ap) else 0.0
+
+ @property
+ def map(self):
+ """Mean AP@0.5:0.95 of all classes.
+ Return:
+ float.
+ """
+ return self.all_ap.mean() if len(self.all_ap) else 0.0
+
+ def mean_results(self):
+ """Mean of results, return mp, mr, map50, map"""
+ return (self.mp, self.mr, self.map50, self.map)
+
+ def class_result(self, i):
+ """class-aware result, return p[i], r[i], ap50[i], ap[i]"""
+ return (self.p[i], self.r[i], self.ap50[i], self.ap[i])
+
+ def get_maps(self, nc):
+ maps = np.zeros(nc) + self.map
+ for i, c in enumerate(self.ap_class_index):
+ maps[c] = self.ap[i]
+ return maps
+
+ def update(self, results):
+ """
+ Args:
+ results: tuple(p, r, ap, f1, ap_class)
+ """
+ p, r, all_ap, f1, ap_class_index = results
+ self.p = p
+ self.r = r
+ self.all_ap = all_ap
+ self.f1 = f1
+ self.ap_class_index = ap_class_index
+
+
+class Metrics:
+ """Metric for boxes and masks."""
+
+ def __init__(self) -> None:
+ self.metric_box = Metric()
+ self.metric_mask = Metric()
+
+ def update(self, results):
+ """
+ Args:
+ results: Dict{'boxes': Dict{}, 'masks': Dict{}}
+ """
+ self.metric_box.update(list(results['boxes'].values()))
+ self.metric_mask.update(list(results['masks'].values()))
+
+ def mean_results(self):
+ return self.metric_box.mean_results() + self.metric_mask.mean_results()
+
+ def class_result(self, i):
+ return self.metric_box.class_result(i) + self.metric_mask.class_result(i)
+
+ def get_maps(self, nc):
+ return self.metric_box.get_maps(nc) + self.metric_mask.get_maps(nc)
+
+ @property
+ def ap_class_index(self):
+ # boxes and masks have the same ap_class_index
+ return self.metric_box.ap_class_index
+
+
+KEYS = [
+ 'train/box_loss',
+ 'train/seg_loss', # train loss
+ 'train/obj_loss',
+ 'train/cls_loss',
+ 'metrics/precision(B)',
+ 'metrics/recall(B)',
+ 'metrics/mAP_0.5(B)',
+ 'metrics/mAP_0.5:0.95(B)', # metrics
+ 'metrics/precision(M)',
+ 'metrics/recall(M)',
+ 'metrics/mAP_0.5(M)',
+ 'metrics/mAP_0.5:0.95(M)', # metrics
+ 'val/box_loss',
+ 'val/seg_loss', # val loss
+ 'val/obj_loss',
+ 'val/cls_loss',
+ 'x/lr0',
+ 'x/lr1',
+ 'x/lr2',]
+
+BEST_KEYS = [
+ 'best/epoch',
+ 'best/precision(B)',
+ 'best/recall(B)',
+ 'best/mAP_0.5(B)',
+ 'best/mAP_0.5:0.95(B)',
+ 'best/precision(M)',
+ 'best/recall(M)',
+ 'best/mAP_0.5(M)',
+ 'best/mAP_0.5:0.95(M)',]
diff --git a/ros2_ws/src/yolov3_ros/utils/segment/plots.py b/ros2_ws/src/yolov3_ros/utils/segment/plots.py
new file mode 100644
index 00000000..3ba09762
--- /dev/null
+++ b/ros2_ws/src/yolov3_ros/utils/segment/plots.py
@@ -0,0 +1,143 @@
+import contextlib
+import math
+from pathlib import Path
+
+import cv2
+import matplotlib.pyplot as plt
+import numpy as np
+import pandas as pd
+import torch
+
+from .. import threaded
+from ..general import xywh2xyxy
+from ..plots import Annotator, colors
+
+
+@threaded
+def plot_images_and_masks(images, targets, masks, paths=None, fname='images.jpg', names=None):
+ # Plot image grid with labels
+ if isinstance(images, torch.Tensor):
+ images = images.cpu().float().numpy()
+ if isinstance(targets, torch.Tensor):
+ targets = targets.cpu().numpy()
+ if isinstance(masks, torch.Tensor):
+ masks = masks.cpu().numpy().astype(int)
+
+ max_size = 1920 # max image size
+ max_subplots = 16 # max image subplots, i.e. 4x4
+ bs, _, h, w = images.shape # batch size, _, height, width
+ bs = min(bs, max_subplots) # limit plot images
+ ns = np.ceil(bs ** 0.5) # number of subplots (square)
+ if np.max(images[0]) <= 1:
+ images *= 255 # de-normalise (optional)
+
+ # Build Image
+ mosaic = np.full((int(ns * h), int(ns * w), 3), 255, dtype=np.uint8) # init
+ for i, im in enumerate(images):
+ if i == max_subplots: # if last batch has fewer images than we expect
+ break
+ x, y = int(w * (i // ns)), int(h * (i % ns)) # block origin
+ im = im.transpose(1, 2, 0)
+ mosaic[y:y + h, x:x + w, :] = im
+
+ # Resize (optional)
+ scale = max_size / ns / max(h, w)
+ if scale < 1:
+ h = math.ceil(scale * h)
+ w = math.ceil(scale * w)
+ mosaic = cv2.resize(mosaic, tuple(int(x * ns) for x in (w, h)))
+
+ # Annotate
+ fs = int((h + w) * ns * 0.01) # font size
+ annotator = Annotator(mosaic, line_width=round(fs / 10), font_size=fs, pil=True, example=names)
+ for i in range(i + 1):
+ x, y = int(w * (i // ns)), int(h * (i % ns)) # block origin
+ annotator.rectangle([x, y, x + w, y + h], None, (255, 255, 255), width=2) # borders
+ if paths:
+ annotator.text((x + 5, y + 5 + h), text=Path(paths[i]).name[:40], txt_color=(220, 220, 220)) # filenames
+ if len(targets) > 0:
+ idx = targets[:, 0] == i
+ ti = targets[idx] # image targets
+
+ boxes = xywh2xyxy(ti[:, 2:6]).T
+ classes = ti[:, 1].astype('int')
+ labels = ti.shape[1] == 6 # labels if no conf column
+ conf = None if labels else ti[:, 6] # check for confidence presence (label vs pred)
+
+ if boxes.shape[1]:
+ if boxes.max() <= 1.01: # if normalized with tolerance 0.01
+ boxes[[0, 2]] *= w # scale to pixels
+ boxes[[1, 3]] *= h
+ elif scale < 1: # absolute coords need scale if image scales
+ boxes *= scale
+ boxes[[0, 2]] += x
+ boxes[[1, 3]] += y
+ for j, box in enumerate(boxes.T.tolist()):
+ cls = classes[j]
+ color = colors(cls)
+ cls = names[cls] if names else cls
+ if labels or conf[j] > 0.25: # 0.25 conf thresh
+ label = f'{cls}' if labels else f'{cls} {conf[j]:.1f}'
+ annotator.box_label(box, label, color=color)
+
+ # Plot masks
+ if len(masks):
+ if masks.max() > 1.0: # mean that masks are overlap
+ image_masks = masks[[i]] # (1, 640, 640)
+ nl = len(ti)
+ index = np.arange(nl).reshape(nl, 1, 1) + 1
+ image_masks = np.repeat(image_masks, nl, axis=0)
+ image_masks = np.where(image_masks == index, 1.0, 0.0)
+ else:
+ image_masks = masks[idx]
+
+ im = np.asarray(annotator.im).copy()
+ for j, box in enumerate(boxes.T.tolist()):
+ if labels or conf[j] > 0.25: # 0.25 conf thresh
+ color = colors(classes[j])
+ mh, mw = image_masks[j].shape
+ if mh != h or mw != w:
+ mask = image_masks[j].astype(np.uint8)
+ mask = cv2.resize(mask, (w, h))
+ mask = mask.astype(bool)
+ else:
+ mask = image_masks[j].astype(bool)
+ with contextlib.suppress(Exception):
+ im[y:y + h, x:x + w, :][mask] = im[y:y + h, x:x + w, :][mask] * 0.4 + np.array(color) * 0.6
+ annotator.fromarray(im)
+ annotator.im.save(fname) # save
+
+
+def plot_results_with_masks(file='path/to/results.csv', dir='', best=True):
+ # Plot training results.csv. Usage: from utils.plots import *; plot_results('path/to/results.csv')
+ save_dir = Path(file).parent if file else Path(dir)
+ fig, ax = plt.subplots(2, 8, figsize=(18, 6), tight_layout=True)
+ ax = ax.ravel()
+ files = list(save_dir.glob('results*.csv'))
+ assert len(files), f'No results.csv files found in {save_dir.resolve()}, nothing to plot.'
+ for f in files:
+ try:
+ data = pd.read_csv(f)
+ index = np.argmax(0.9 * data.values[:, 8] + 0.1 * data.values[:, 7] + 0.9 * data.values[:, 12] +
+ 0.1 * data.values[:, 11])
+ s = [x.strip() for x in data.columns]
+ x = data.values[:, 0]
+ for i, j in enumerate([1, 2, 3, 4, 5, 6, 9, 10, 13, 14, 15, 16, 7, 8, 11, 12]):
+ y = data.values[:, j]
+ # y[y == 0] = np.nan # don't show zero values
+ ax[i].plot(x, y, marker='.', label=f.stem, linewidth=2, markersize=2)
+ if best:
+ # best
+ ax[i].scatter(index, y[index], color='r', label=f'best:{index}', marker='*', linewidth=3)
+ ax[i].set_title(s[j] + f'\n{round(y[index], 5)}')
+ else:
+ # last
+ ax[i].scatter(x[-1], y[-1], color='r', label='last', marker='*', linewidth=3)
+ ax[i].set_title(s[j] + f'\n{round(y[-1], 5)}')
+ # if j in [8, 9, 10]: # share train and val loss y axes
+ # ax[i].get_shared_y_axes().join(ax[i], ax[i - 5])
+ except Exception as e:
+ print(f'Warning: Plotting error for {f}: {e}')
+ ax[1].legend()
+ fig.savefig(save_dir / 'results.png', dpi=200)
+ plt.close()
diff --git a/ros2_ws/src/yolov3_ros/utils/torch_utils.py b/ros2_ws/src/yolov3_ros/utils/torch_utils.py
new file mode 100644
index 00000000..d3692297
--- /dev/null
+++ b/ros2_ws/src/yolov3_ros/utils/torch_utils.py
@@ -0,0 +1,318 @@
+# YOLOv3 🚀 by Ultralytics, GPL-3.0 license
+"""
+PyTorch utils
+"""
+
+import datetime
+import math
+import os
+import platform
+import subprocess
+import time
+from contextlib import contextmanager
+from copy import deepcopy
+from pathlib import Path
+
+import torch
+import torch.distributed as dist
+import torch.nn as nn
+import torch.nn.functional as F
+
+from utils.general import LOGGER
+
+try:
+ import thop # for FLOPs computation
+except ImportError:
+ thop = None
+
+
+@contextmanager
+def torch_distributed_zero_first(local_rank: int):
+ """
+ Decorator to make all processes in distributed training wait for each local_master to do something.
+ """
+ if local_rank not in [-1, 0]:
+ dist.barrier(device_ids=[local_rank])
+ yield
+ if local_rank == 0:
+ dist.barrier(device_ids=[0])
+
+
+def date_modified(path=__file__):
+ # return human-readable file modification date, i.e. '2021-3-26'
+ t = datetime.datetime.fromtimestamp(Path(path).stat().st_mtime)
+ return f'{t.year}-{t.month}-{t.day}'
+
+
+def git_describe(path=Path(__file__).parent): # path must be a directory
+ # return human-readable git description, i.e. v5.0-5-g3e25f1e https://git-scm.com/docs/git-describe
+ s = f'git -C {path} describe --tags --long --always'
+ try:
+ return subprocess.check_output(s, shell=True, stderr=subprocess.STDOUT).decode()[:-1]
+ except subprocess.CalledProcessError as e:
+ return '' # not a git repository
+
+
+def select_device(device='', batch_size=None, newline=True):
+ # device = 'cpu' or '0' or '0,1,2,3'
+ s = f'YOLOv3 🚀 {git_describe() or date_modified()} torch {torch.__version__} ' # string
+ device = str(device).strip().lower().replace('cuda:', '') # to string, 'cuda:0' to '0'
+ cpu = device == 'cpu'
+ if cpu:
+ os.environ['CUDA_VISIBLE_DEVICES'] = '-1' # force torch.cuda.is_available() = False
+ elif device: # non-cpu device requested
+ os.environ['CUDA_VISIBLE_DEVICES'] = device # set environment variable
+ assert torch.cuda.is_available(), f'CUDA unavailable, invalid device {device} requested' # check availability
+
+ cuda = not cpu and torch.cuda.is_available()
+ if cuda:
+ devices = device.split(',') if device else '0' # range(torch.cuda.device_count()) # i.e. 0,1,6,7
+ n = len(devices) # device count
+ if n > 1 and batch_size: # check batch_size is divisible by device_count
+ assert batch_size % n == 0, f'batch-size {batch_size} not multiple of GPU count {n}'
+ space = ' ' * (len(s) + 1)
+ for i, d in enumerate(devices):
+ p = torch.cuda.get_device_properties(i)
+ s += f"{'' if i == 0 else space}CUDA:{d} ({p.name}, {p.total_memory / 1024 ** 2:.0f}MiB)\n" # bytes to MB
+ else:
+ s += 'CPU\n'
+
+ if not newline:
+ s = s.rstrip()
+ LOGGER.info(s.encode().decode('ascii', 'ignore') if platform.system() == 'Windows' else s) # emoji-safe
+ return torch.device('cuda:0' if cuda else 'cpu')
+
+
+def time_sync():
+ # pytorch-accurate time
+ if torch.cuda.is_available():
+ torch.cuda.synchronize()
+ return time.time()
+
+
+def profile(input, ops, n=10, device=None):
+ # speed/memory/FLOPs profiler
+ #
+ # Usage:
+ # input = torch.randn(16, 3, 640, 640)
+ # m1 = lambda x: x * torch.sigmoid(x)
+ # m2 = nn.SiLU()
+ # profile(input, [m1, m2], n=100) # profile over 100 iterations
+
+ results = []
+ device = device or select_device()
+ print(f"{'Params':>12s}{'GFLOPs':>12s}{'GPU_mem (GB)':>14s}{'forward (ms)':>14s}{'backward (ms)':>14s}"
+ f"{'input':>24s}{'output':>24s}")
+
+ for x in input if isinstance(input, list) else [input]:
+ x = x.to(device)
+ x.requires_grad = True
+ for m in ops if isinstance(ops, list) else [ops]:
+ m = m.to(device) if hasattr(m, 'to') else m # device
+ m = m.half() if hasattr(m, 'half') and isinstance(x, torch.Tensor) and x.dtype is torch.float16 else m
+ tf, tb, t = 0, 0, [0, 0, 0] # dt forward, backward
+ try:
+ flops = thop.profile(m, inputs=(x,), verbose=False)[0] / 1E9 * 2 # GFLOPs
+ except:
+ flops = 0
+
+ try:
+ for _ in range(n):
+ t[0] = time_sync()
+ y = m(x)
+ t[1] = time_sync()
+ try:
+ _ = (sum(yi.sum() for yi in y) if isinstance(y, list) else y).sum().backward()
+ t[2] = time_sync()
+ except Exception as e: # no backward method
+ # print(e) # for debug
+ t[2] = float('nan')
+ tf += (t[1] - t[0]) * 1000 / n # ms per op forward
+ tb += (t[2] - t[1]) * 1000 / n # ms per op backward
+ mem = torch.cuda.memory_reserved() / 1E9 if torch.cuda.is_available() else 0 # (GB)
+ s_in = tuple(x.shape) if isinstance(x, torch.Tensor) else 'list'
+ s_out = tuple(y.shape) if isinstance(y, torch.Tensor) else 'list'
+ p = sum(list(x.numel() for x in m.parameters())) if isinstance(m, nn.Module) else 0 # parameters
+ print(f'{p:12}{flops:12.4g}{mem:>14.3f}{tf:14.4g}{tb:14.4g}{str(s_in):>24s}{str(s_out):>24s}')
+ results.append([p, flops, mem, tf, tb, s_in, s_out])
+ except Exception as e:
+ print(e)
+ results.append(None)
+ torch.cuda.empty_cache()
+ return results
+
+
+def is_parallel(model):
+ # Returns True if model is of type DP or DDP
+ return type(model) in (nn.parallel.DataParallel, nn.parallel.DistributedDataParallel)
+
+
+def de_parallel(model):
+ # De-parallelize a model: returns single-GPU model if model is of type DP or DDP
+ return model.module if is_parallel(model) else model
+
+
+def initialize_weights(model):
+ for m in model.modules():
+ t = type(m)
+ if t is nn.Conv2d:
+ pass # nn.init.kaiming_normal_(m.weight, mode='fan_out', nonlinearity='relu')
+ elif t is nn.BatchNorm2d:
+ m.eps = 1e-3
+ m.momentum = 0.03
+ elif t in [nn.Hardswish, nn.LeakyReLU, nn.ReLU, nn.ReLU6, nn.SiLU]:
+ m.inplace = True
+
+
+def find_modules(model, mclass=nn.Conv2d):
+ # Finds layer indices matching module class 'mclass'
+ return [i for i, m in enumerate(model.module_list) if isinstance(m, mclass)]
+
+
+def sparsity(model):
+ # Return global model sparsity
+ a, b = 0, 0
+ for p in model.parameters():
+ a += p.numel()
+ b += (p == 0).sum()
+ return b / a
+
+
+def prune(model, amount=0.3):
+ # Prune model to requested global sparsity
+ import torch.nn.utils.prune as prune
+ print('Pruning model... ', end='')
+ for name, m in model.named_modules():
+ if isinstance(m, nn.Conv2d):
+ prune.l1_unstructured(m, name='weight', amount=amount) # prune
+ prune.remove(m, 'weight') # make permanent
+ print(' %.3g global sparsity' % sparsity(model))
+
+
+def fuse_conv_and_bn(conv, bn):
+ # Fuse convolution and batchnorm layers https://tehnokv.com/posts/fusing-batchnorm-and-conv/
+ fusedconv = nn.Conv2d(conv.in_channels,
+ conv.out_channels,
+ kernel_size=conv.kernel_size,
+ stride=conv.stride,
+ padding=conv.padding,
+ groups=conv.groups,
+ bias=True).requires_grad_(False).to(conv.weight.device)
+
+ # prepare filters
+ w_conv = conv.weight.clone().view(conv.out_channels, -1)
+ w_bn = torch.diag(bn.weight.div(torch.sqrt(bn.eps + bn.running_var)))
+ fusedconv.weight.copy_(torch.mm(w_bn, w_conv).view(fusedconv.weight.shape))
+
+ # prepare spatial bias
+ b_conv = torch.zeros(conv.weight.size(0), device=conv.weight.device) if conv.bias is None else conv.bias
+ b_bn = bn.bias - bn.weight.mul(bn.running_mean).div(torch.sqrt(bn.running_var + bn.eps))
+ fusedconv.bias.copy_(torch.mm(w_bn, b_conv.reshape(-1, 1)).reshape(-1) + b_bn)
+
+ return fusedconv
+
+
+def model_info(model, verbose=False, img_size=640):
+ # Model information. img_size may be int or list, i.e. img_size=640 or img_size=[640, 320]
+ n_p = sum(x.numel() for x in model.parameters()) # number parameters
+ n_g = sum(x.numel() for x in model.parameters() if x.requires_grad) # number gradients
+ if verbose:
+ print(f"{'layer':>5} {'name':>40} {'gradient':>9} {'parameters':>12} {'shape':>20} {'mu':>10} {'sigma':>10}")
+ for i, (name, p) in enumerate(model.named_parameters()):
+ name = name.replace('module_list.', '')
+ print('%5g %40s %9s %12g %20s %10.3g %10.3g' %
+ (i, name, p.requires_grad, p.numel(), list(p.shape), p.mean(), p.std()))
+
+ try: # FLOPs
+ from thop import profile
+ stride = max(int(model.stride.max()), 32) if hasattr(model, 'stride') else 32
+ img = torch.zeros((1, model.yaml.get('ch', 3), stride, stride), device=next(model.parameters()).device) # input
+ flops = profile(deepcopy(model), inputs=(img,), verbose=False)[0] / 1E9 * 2 # stride GFLOPs
+ img_size = img_size if isinstance(img_size, list) else [img_size, img_size] # expand if int/float
+ fs = ', %.1f GFLOPs' % (flops * img_size[0] / stride * img_size[1] / stride) # 640x640 GFLOPs
+ except (ImportError, Exception):
+ fs = ''
+
+ LOGGER.info(f"Model Summary: {len(list(model.modules()))} layers, {n_p} parameters, {n_g} gradients{fs}")
+
+
+def scale_img(img, ratio=1.0, same_shape=False, gs=32): # img(16,3,256,416)
+ # scales img(bs,3,y,x) by ratio constrained to gs-multiple
+ if ratio == 1.0:
+ return img
+ else:
+ h, w = img.shape[2:]
+ s = (int(h * ratio), int(w * ratio)) # new size
+ img = F.interpolate(img, size=s, mode='bilinear', align_corners=False) # resize
+ if not same_shape: # pad/crop img
+ h, w = (math.ceil(x * ratio / gs) * gs for x in (h, w))
+ return F.pad(img, [0, w - s[1], 0, h - s[0]], value=0.447) # value = imagenet mean
+
+
+def copy_attr(a, b, include=(), exclude=()):
+ # Copy attributes from b to a, options to only include [...] and to exclude [...]
+ for k, v in b.__dict__.items():
+ if (len(include) and k not in include) or k.startswith('_') or k in exclude:
+ continue
+ else:
+ setattr(a, k, v)
+
+
+class EarlyStopping:
+ # simple early stopper
+ def __init__(self, patience=30):
+ self.best_fitness = 0.0 # i.e. mAP
+ self.best_epoch = 0
+ self.patience = patience or float('inf') # epochs to wait after fitness stops improving to stop
+ self.possible_stop = False # possible stop may occur next epoch
+
+ def __call__(self, epoch, fitness):
+ if fitness >= self.best_fitness: # >= 0 to allow for early zero-fitness stage of training
+ self.best_epoch = epoch
+ self.best_fitness = fitness
+ delta = epoch - self.best_epoch # epochs without improvement
+ self.possible_stop = delta >= (self.patience - 1) # possible stop may occur next epoch
+ stop = delta >= self.patience # stop training if patience exceeded
+ if stop:
+ LOGGER.info(f'Stopping training early as no improvement observed in last {self.patience} epochs. '
+ f'Best results observed at epoch {self.best_epoch}, best model saved as best.pt.\n'
+ f'To update EarlyStopping(patience={self.patience}) pass a new patience value, '
+ f'i.e. `python train.py --patience 300` or use `--patience 0` to disable EarlyStopping.')
+ return stop
+
+
+class ModelEMA:
+ """ Model Exponential Moving Average from https://github.com/rwightman/pytorch-image-models
+ Keep a moving average of everything in the model state_dict (parameters and buffers).
+ This is intended to allow functionality like
+ https://www.tensorflow.org/api_docs/python/tf/train/ExponentialMovingAverage
+ A smoothed version of the weights is necessary for some training schemes to perform well.
+ This class is sensitive where it is initialized in the sequence of model init,
+ GPU assignment and distributed training wrappers.
+ """
+
+ def __init__(self, model, decay=0.9999, updates=0):
+ # Create EMA
+ self.ema = deepcopy(model.module if is_parallel(model) else model).eval() # FP32 EMA
+ # if next(model.parameters()).device.type != 'cpu':
+ # self.ema.half() # FP16 EMA
+ self.updates = updates # number of EMA updates
+ self.decay = lambda x: decay * (1 - math.exp(-x / 2000)) # decay exponential ramp (to help early epochs)
+ for p in self.ema.parameters():
+ p.requires_grad_(False)
+
+ def update(self, model):
+ # Update EMA parameters
+ with torch.no_grad():
+ self.updates += 1
+ d = self.decay(self.updates)
+
+ msd = model.module.state_dict() if is_parallel(model) else model.state_dict() # model state_dict
+ for k, v in self.ema.state_dict().items():
+ if v.dtype.is_floating_point:
+ v *= d
+ v += (1 - d) * msd[k].detach()
+
+ def update_attr(self, model, include=(), exclude=('process_group', 'reducer')):
+ # Update EMA attributes
+ copy_attr(self.ema, model, include, exclude)
diff --git a/ros2_ws/src/yolov3_ros/utils/triton.py b/ros2_ws/src/yolov3_ros/utils/triton.py
new file mode 100644
index 00000000..87f1fdcd
--- /dev/null
+++ b/ros2_ws/src/yolov3_ros/utils/triton.py
@@ -0,0 +1,85 @@
+# YOLOv3 🚀 by Ultralytics, GPL-3.0 license
+""" Utils to interact with the Triton Inference Server
+"""
+
+import typing
+from urllib.parse import urlparse
+
+import torch
+
+
+class TritonRemoteModel:
+ """ A wrapper over a model served by the Triton Inference Server. It can
+ be configured to communicate over GRPC or HTTP. It accepts Torch Tensors
+ as input and returns them as outputs.
+ """
+
+ def __init__(self, url: str):
+ """
+ Keyword arguments:
+ url: Fully qualified address of the Triton server - for e.g. grpc://localhost:8000
+ """
+
+ parsed_url = urlparse(url)
+ if parsed_url.scheme == 'grpc':
+ from tritonclient.grpc import InferenceServerClient, InferInput
+
+ self.client = InferenceServerClient(parsed_url.netloc) # Triton GRPC client
+ model_repository = self.client.get_model_repository_index()
+ self.model_name = model_repository.models[0].name
+ self.metadata = self.client.get_model_metadata(self.model_name, as_json=True)
+
+ def create_input_placeholders() -> typing.List[InferInput]:
+ return [
+ InferInput(i['name'], [int(s) for s in i['shape']], i['datatype']) for i in self.metadata['inputs']]
+
+ else:
+ from tritonclient.http import InferenceServerClient, InferInput
+
+ self.client = InferenceServerClient(parsed_url.netloc) # Triton HTTP client
+ model_repository = self.client.get_model_repository_index()
+ self.model_name = model_repository[0]['name']
+ self.metadata = self.client.get_model_metadata(self.model_name)
+
+ def create_input_placeholders() -> typing.List[InferInput]:
+ return [
+ InferInput(i['name'], [int(s) for s in i['shape']], i['datatype']) for i in self.metadata['inputs']]
+
+ self._create_input_placeholders_fn = create_input_placeholders
+
+ @property
+ def runtime(self):
+ """Returns the model runtime"""
+ return self.metadata.get('backend', self.metadata.get('platform'))
+
+ def __call__(self, *args, **kwargs) -> typing.Union[torch.Tensor, typing.Tuple[torch.Tensor, ...]]:
+ """ Invokes the model. Parameters can be provided via args or kwargs.
+ args, if provided, are assumed to match the order of inputs of the model.
+ kwargs are matched with the model input names.
+ """
+ inputs = self._create_inputs(*args, **kwargs)
+ response = self.client.infer(model_name=self.model_name, inputs=inputs)
+ result = []
+ for output in self.metadata['outputs']:
+ tensor = torch.as_tensor(response.as_numpy(output['name']))
+ result.append(tensor)
+ return result[0] if len(result) == 1 else result
+
+ def _create_inputs(self, *args, **kwargs):
+ args_len, kwargs_len = len(args), len(kwargs)
+ if not args_len and not kwargs_len:
+ raise RuntimeError('No inputs provided.')
+ if args_len and kwargs_len:
+ raise RuntimeError('Cannot specify args and kwargs at the same time')
+
+ placeholders = self._create_input_placeholders_fn()
+ if args_len:
+ if args_len != len(placeholders):
+ raise RuntimeError(f'Expected {len(placeholders)} inputs, got {args_len}.')
+ for input, value in zip(placeholders, args):
+ input.set_data_from_numpy(value.cpu().numpy())
+ else:
+ for input in placeholders:
+ value = kwargs[input.name]
+ input.set_data_from_numpy(value.cpu().numpy())
+ return placeholders
diff --git a/ros2_ws/src/yolov3_ros/yolov3_ros/__init__.py b/ros2_ws/src/yolov3_ros/yolov3_ros/__init__.py
new file mode 100644
index 00000000..e69de29b
diff --git a/ros2_ws/src/yolov3_ros/yolov3_ros/yolov3_ros_node.py b/ros2_ws/src/yolov3_ros/yolov3_ros/yolov3_ros_node.py
new file mode 100644
index 00000000..6f9b81a8
--- /dev/null
+++ b/ros2_ws/src/yolov3_ros/yolov3_ros/yolov3_ros_node.py
@@ -0,0 +1,257 @@
+
+# Subscribe to input image topic.
+# object_detector ([std_msgs::Int8])
+
+# Publishes the number of detected objects.
+
+# bounding_boxes ([darknet_ros_msgs::BoundingBoxes])
+
+# Publishes an array of bounding boxes that gives information of the position and size of the bounding box in pixel coordinates.
+
+# detection_image ([sensor_msgs::Image])
+
+# Publishes an image of the detection image including the bounding boxes.
+
+import rclpy
+from rclpy.node import Node
+
+from std_msgs.msg import String
+from sensor_msgs.msg import Image
+from cv_bridge import CvBridge
+import argparse
+import os
+import sys
+from pathlib import Path
+
+import cv2
+import torch
+import torch.backends.cudnn as cudnn
+
+FILE = Path(__file__).resolve()
+ROOT = FILE.parents[0] # root directory
+if str(ROOT) not in sys.path:
+ sys.path.append(str(ROOT)) # add ROOT to PATH
+ROOT = Path(os.path.relpath(ROOT, Path.cwd())) # relative
+
+from models.common import DetectMultiBackend
+from utils.datasets import IMG_FORMATS, VID_FORMATS, LoadImages, LoadStreams
+from utils.general import (LOGGER, check_file, check_img_size, check_imshow, check_requirements, colorstr,
+ increment_path, non_max_suppression, print_args, scale_coords, strip_optimizer, xyxy2xywh)
+from utils.plots import Annotator, colors, save_one_box
+from utils.torch_utils import select_device, time_sync
+from utils.augmentations import Albumentations, augment_hsv, copy_paste, letterbox
+import numpy as np
+from pipe_msgs.msg import BoundingBox, BoundingBoxes
+from rclpy.clock import Clock
+from sensor_msgs.msg import CameraInfo
+
+@torch.no_grad()
+def run(weights=ROOT / 'yolov3.pt', # model.pt path(s)
+ source=ROOT / 'data/images', # file/dir/URL/glob, 0 for webcam
+ imgsz=1280, # inference size (pixels)
+ conf_thres=0.25, # confidence threshold
+ iou_thres=0.45, # NMS IOU threshold
+ max_det=1000, # maximum detections per image
+ device='', # cuda device, i.e. 0 or 0,1,2,3 or cpu
+ view_img=False, # show results
+ save_txt=False, # save results to *.txt
+ save_conf=False, # save confidences in --save-txt labels
+ save_crop=False, # save cropped prediction boxes
+ nosave=False, # do not save images/videos
+ classes=None, # filter by class: --class 0, or --class 0 2 3
+ agnostic_nms=False, # class-agnostic NMS
+ augment=False, # augmented inference
+ visualize=False, # visualize features
+ update=False, # update all models
+ project=ROOT / 'runs/detect', # save results to project/name
+ name='exp', # save results to project/name
+ exist_ok=False, # existing project/name ok, do not increment
+ line_thickness=3, # bounding box thickness (pixels)
+ hide_labels=False, # hide labels
+ hide_conf=False, # hide confidences
+ half=False, # use FP16 half-precision inference
+ dnn=False, # use OpenCV DNN for ONNX inference
+ ):
+
+ # Load model
+ device = select_device(device)
+ model = DetectMultiBackend(weights, device=device, dnn=dnn)
+ stride, names, pt, jit, onnx = model.stride, model.names, model.pt, model.jit, model.onnx
+ imgsz = check_img_size(imgsz, s=stride) # check image size
+
+ # Half
+ half &= pt and device.type != 'cpu' # half precision only supported by PyTorch on CUDA
+ if pt:
+ model.model.half() if half else model.model.float()
+
+ # Padded resize
+ dataset_img = letterbox(source, imgsz, stride=stride, auto=pt)[0]
+
+ # Convert
+ dataset_img = dataset_img.transpose((2, 0, 1))[::-1] # HWC to CHW, BGR to RGB
+ dataset_img = np.ascontiguousarray(dataset_img)
+ # Run inference
+ if pt and device.type != 'cpu':
+ model(torch.zeros(1, 3, *imgsz).to(device).type_as(next(model.model.parameters()))) # warmup
+ dt, seen = [0.0, 0.0, 0.0], 0
+ bs = 1
+ t1 = time_sync()
+ im = dataset_img
+ im = torch.from_numpy(im).to(device)
+ im = im.half() if half else im.float() # uint8 to fp16/32
+ im /= 255 # 0 - 255 to 0.0 - 1.0
+ if len(im.shape) == 3:
+ im = im[None] # expand for batch dim
+ t2 = time_sync()
+ dt[0] += t2 - t1
+ pred = model(im, augment=augment, visualize=visualize)
+ t3 = time_sync()
+ pred = non_max_suppression(pred, conf_thres, iou_thres, classes, agnostic_nms, max_det=max_det)
+ dt[2] += time_sync() - t3
+
+ ## iterate through detections
+ for i, det in enumerate(pred):
+ seen += 1
+ im0, frame = source.copy(), 'frame'
+ # p = Path(p) # to Path
+ # save_path = '/home/parallels/predict.jpeg'
+ annotator = Annotator(im0, line_width=line_thickness, example=str(names))
+
+ time_stamp = Clock().now()
+ bounding_boxes_msg = BoundingBoxes()
+ bounding_boxes_msg.header.stamp = time_stamp.to_msg()
+ bounding_boxes_msg.header.frame_id = 'detection'
+ s = ''
+ if len(det):
+ # Rescale boxes from img_size to im0 size
+ det[:, :4] = scale_coords(im.shape[2:], det[:, :4], im0.shape).round()
+ # Print results
+ number_of_uniq_det = {}
+ for c in det[:, -1].unique():
+ n = (det[:, -1] == c).sum() # detections per class
+ s += f"{n} {names[int(c)]}{'s' * (n > 1)}, " # add to string
+ number_of_uniq_det[names[int(c)]] = int(n)
+
+ # Write results
+ append_count = 0
+ last_name = ""
+ for *xyxy, conf, cls in reversed(det):
+ bounding_box = BoundingBox()
+ c = int(cls) # integer class
+ label = None if hide_labels else (names[c] if hide_conf else f'{names[c]} {conf:.2f}')
+ annotator.box_label(xyxy, label, color=colors(c, True))
+ bounding_box.probability = float(conf)
+ bounding_box.xmin = int(xyxy[0])
+ bounding_box.ymin = int(xyxy[1])
+ bounding_box.xmax = int(xyxy[2])
+ bounding_box.ymax = int(xyxy[3])
+ bounding_box.id = c
+ if last_name != names[c]:
+ append_count = 0
+ if number_of_uniq_det[names[c]] > 1:
+ bounding_box.class_id = names[c] + "_" + str(append_count)
+ append_count+=1
+ last_name = names[c]
+ else:
+ bounding_box.class_id = names[c]
+ append_count = 0
+ bounding_boxes_msg.bounding_boxes.append(bounding_box)
+ # Print time (inference-only)
+ LOGGER.info(f'{s}Done. ({t3 - t2:.3f}s)')
+ # Stream results
+ im0 = annotator.result()
+ if update:
+ strip_optimizer(weights) # update model (to fix SourceChangeWarning)
+ # cv2.imwrite(save_path, im0)
+ return im0, bounding_boxes_msg
+
+class DetectOnBag(Node):
+
+ def __init__(self, args):
+ super().__init__('detect_on_bag')
+ self.args = args
+ self.declare_parameter('best_weights', 'src/pipe_weights.pt')
+ self.best_weights = self.get_parameter('best_weights').get_parameter_value().string_value
+ self.camera_info = None
+ self.depth_img = None
+ self.subscription = self.create_subscription(
+ Image,
+ '/camera/color/image_raw',
+ self.image_callback,
+ 10)
+ self.subscription # prevent unused variable warning
+ self.subscription = self.create_subscription(
+ Image,
+ '/camera/aligned_depth_to_color/image_raw',
+ self.image_depth_callback,
+ 10)
+ self.subscription
+ self.subscription = self.create_subscription(
+ CameraInfo,
+ '/camera/color/camera_info',
+ self.camera_info_callback,
+ 10)
+ self.subscription
+ self.detected_img_pub = self.create_publisher(Image, '/detection_image', 10)
+ self.bboxes_pub = self.create_publisher(BoundingBoxes, '/bboxes', 10)
+ self.depth_pub = self.create_publisher(Image, '/depth_img', 10)
+ self.img_pub = self.create_publisher(Image, '/rgb_img', 10)
+ self.info_pub = self.create_publisher(CameraInfo, '/camera_info', 10)
+
+ def camera_info_callback(self, msg):
+ print("camera info cb")
+ # print(msg.header.stamp)
+ self.camera_info = msg
+
+ def image_depth_callback(self, msg):
+ print("depth info cb")
+ # print(msg.header.stamp)
+ self.depth_img = msg
+
+ def image_callback(self, msg):
+ print("rgb img cb")
+ # print(msg.header.stamp)
+
+ bridge = CvBridge()
+ cv_image = bridge.imgmsg_to_cv2(msg, desired_encoding='passthrough')
+ detected_img, bboxes = run(self.best_weights, cv_image)
+ self.detected_img_pub.publish(self.numpy_array_to_image_msg(detected_img))
+ bboxes.image_header = msg.header
+ bboxes.header.stamp = msg.header.stamp
+ bboxes.header.frame_id = 'detection'
+ self.bboxes_pub.publish(bboxes)
+ if self.depth_img:
+ self.depth_pub.publish(self.depth_img)
+ self.img_pub.publish(msg)
+ if self.camera_info:
+ self.info_pub.publish(self.camera_info)
+
+ def numpy_array_to_image_msg(self, numpy_array):
+ # Create a CvBridge object
+ bridge = CvBridge()
+
+ # Convert the numpy array to a cv image
+ cv_image = cv2.cvtColor(numpy_array, cv2.COLOR_RGB2BGR)
+
+ # Convert the cv image to a ROS message
+ ros_image = bridge.cv2_to_imgmsg(cv_image, encoding="bgr8")
+
+ return ros_image
+
+
+def main(args=None):
+ rclpy.init(args=args)
+
+ detect_on_bag = DetectOnBag(args)
+
+ rclpy.spin(detect_on_bag)
+
+ # Destroy the node explicitly
+ # (optional - otherwise it will be done automatically
+ # when the garbage collector destroys the node object)
+ # detect_on_bag.destroy_node()
+ rclpy.shutdown()
+
+
+if __name__ == '__main__':
+ main()
\ No newline at end of file