apoorva/greenhouse
2
1
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

YOLOv5 v5.0 release compatibility update for YOLOv3

Browse Source
This commit is contained in:
Glenn Jocher
2021-05-30 18:55:56 +02:00
parent 47ac6833ca
commit 4d0c2e6eee
38 changed files with 1192 additions and 528 deletions
Download Patch File Download Diff File Expand all files Collapse all files
models/common.py
+30 -21
View File
@@ -13,8 +13,8 @@ from PIL import Image
from torch.cuda import amp
from utils.datasets import letterbox
from utils.general import non_max_suppression, make_divisible, scale_coords, increment_path, xyxy2xywh
from utils.plots import color_list, plot_one_box
from utils.general import non_max_suppression, make_divisible, scale_coords, increment_path, xyxy2xywh, save_one_box
from utils.plots import colors, plot_one_box
from utils.torch_utils import time_synchronized
@@ -215,32 +215,34 @@ class NMS(nn.Module):
conf = 0.25 # confidence threshold
iou = 0.45 # IoU threshold
classes = None # (optional list) filter by class
max_det = 1000 # maximum number of detections per image
def __init__(self):
super(NMS, self).__init__()
def forward(self, x):
return non_max_suppression(x[0], conf_thres=self.conf, iou_thres=self.iou, classes=self.classes)
return non_max_suppression(x[0], self.conf, iou_thres=self.iou, classes=self.classes, max_det=self.max_det)
class autoShape(nn.Module):
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
max_det = 1000 # maximum number of detections per image
def __init__(self, model):
super(autoShape, self).__init__()
super(AutoShape, self).__init__()
self.model = model.eval()
def autoshape(self):
print('autoShape already enabled, skipping... ') # model already converted to model.autoshape()
print('AutoShape already enabled, skipping... ') # model already converted to model.autoshape()
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:
# filename: imgs = 'data/samples/zidane.jpg'
# filename: imgs = 'data/images/zidane.jpg'
# URI: = 'https://github.com/ultralytics/yolov5/releases/download/v1.0/zidane.jpg'
# OpenCV: = cv2.imread('image.jpg')[:,:,::-1] # HWC BGR to RGB x(640,1280,3)
# PIL: = Image.open('image.jpg') # HWC x(640,1280,3)
@@ -271,7 +273,7 @@ class autoShape(nn.Module):
shape0.append(s) # image shape
g = (size / max(s)) # gain
shape1.append([y * g for y in s])
imgs[i] = im # update
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
@@ -285,7 +287,7 @@ class autoShape(nn.Module):
t.append(time_synchronized())
# Post-process
y = non_max_suppression(y, conf_thres=self.conf, iou_thres=self.iou, classes=self.classes) # NMS
y = non_max_suppression(y, self.conf, iou_thres=self.iou, classes=self.classes, max_det=self.max_det) # NMS
for i in range(n):
scale_coords(shape1, y[i][:, :4], shape0[i])
@@ -311,29 +313,32 @@ class Detections:
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, render=False, save_dir=''):
colors = color_list()
for i, (img, pred) in enumerate(zip(self.imgs, self.pred)):
str = f'image {i + 1}/{len(self.pred)}: {img.shape[0]}x{img.shape[1]} '
def display(self, pprint=False, show=False, save=False, crop=False, render=False, save_dir=Path('')):
for i, (im, pred) in enumerate(zip(self.imgs, self.pred)):
str = f'image {i + 1}/{len(self.pred)}: {im.shape[0]}x{im.shape[1]} '
if pred is not None:
for c in pred[:, -1].unique():
n = (pred[:, -1] == c).sum() # detections per class
str += f"{n} {self.names[int(c)]}{'s' * (n > 1)}, " # add to string
if show or save or render:
if show or save or render or crop:
for *box, conf, cls in pred: # xyxy, confidence, class
label = f'{self.names[int(cls)]} {conf:.2f}'
plot_one_box(box, img, label=label, color=colors[int(cls) % 10])
img = Image.fromarray(img.astype(np.uint8)) if isinstance(img, np.ndarray) else img # from np
if crop:
save_one_box(box, im, file=save_dir / 'crops' / self.names[int(cls)] / self.files[i])
else: # all others
plot_one_box(box, im, label=label, color=colors(cls))
im = Image.fromarray(im.astype(np.uint8)) if isinstance(im, np.ndarray) else im # from np
if pprint:
print(str.rstrip(', '))
if show:
img.show(self.files[i]) # show
im.show(self.files[i]) # show
if save:
f = self.files[i]
img.save(Path(save_dir) / f) # save
im.save(save_dir / f) # save
print(f"{'Saved' * (i == 0)} {f}", end=',' if i < self.n - 1 else f' to {save_dir}\n')
if render:
self.imgs[i] = np.asarray(img)
self.imgs[i] = np.asarray(im)
def print(self):
self.display(pprint=True) # print results
@@ -343,10 +348,14 @@ class Detections:
self.display(show=True) # show results
def save(self, save_dir='runs/hub/exp'):
save_dir = increment_path(save_dir, exist_ok=save_dir != 'runs/hub/exp') # increment save_dir
Path(save_dir).mkdir(parents=True, exist_ok=True)
save_dir = increment_path(save_dir, exist_ok=save_dir != 'runs/hub/exp', mkdir=True) # increment save_dir
self.display(save=True, save_dir=save_dir) # save results
def crop(self, save_dir='runs/hub/exp'):
save_dir = increment_path(save_dir, exist_ok=save_dir != 'runs/hub/exp', mkdir=True) # increment save_dir
self.display(crop=True, save_dir=save_dir) # crop results
print(f'Saved results to {save_dir}\n')
def render(self):
self.display(render=True) # render results
return self.imgs
models/experimental.py
+9 -7
View File
@@ -110,25 +110,27 @@ class Ensemble(nn.ModuleList):
return y, None # inference, train output
def attempt_load(weights, map_location=None):
def attempt_load(weights, map_location=None, inplace=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]:
attempt_download(w)
ckpt = torch.load(w, map_location=map_location) # load
ckpt = torch.load(attempt_download(w), map_location=map_location) # load
model.append(ckpt['ema' if ckpt.get('ema') else 'model'].float().fuse().eval()) # FP32 model
# Compatibility updates
for m in model.modules():
if type(m) in [nn.Hardswish, nn.LeakyReLU, nn.ReLU, nn.ReLU6, nn.SiLU]:
m.inplace = True # pytorch 1.7.0 compatibility
if type(m) in [nn.Hardswish, nn.LeakyReLU, nn.ReLU, nn.ReLU6, nn.SiLU, Detect, Model]:
m.inplace = inplace # pytorch 1.7.0 compatibility
elif type(m) is Conv:
m._non_persistent_buffers_set = set() # pytorch 1.6.0 compatibility
if len(model) == 1:
return model[-1] # return model
else:
print('Ensemble created with %s\n' % weights)
for k in ['names', 'stride']:
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
models/export.py
+89 -48
View File
@@ -1,34 +1,43 @@
"""Exports a YOLOv3 *.pt model to ONNX and TorchScript formats
"""Exports a YOLOv3 *.pt model to TorchScript, ONNX, CoreML formats
Usage:
$ export PYTHONPATH="$PWD" && python models/export.py --weights ./weights/yolov3.pt --img 640 --batch 1
$ python path/to/models/export.py --weights yolov3.pt --img 640 --batch 1
"""
import argparse
import sys
import time
from pathlib import Path
sys.path.append('./') # to run '$ python *.py' files in subdirectories
sys.path.append(Path(__file__).parent.parent.absolute().__str__()) # to run '$ python *.py' files in subdirectories
import torch
import torch.nn as nn
from torch.utils.mobile_optimizer import optimize_for_mobile
import models
from models.experimental import attempt_load
from utils.activations import Hardswish, SiLU
from utils.general import set_logging, check_img_size
from utils.general import colorstr, check_img_size, check_requirements, file_size, set_logging
from utils.torch_utils import select_device
if __name__ == '__main__':
parser = argparse.ArgumentParser()
parser.add_argument('--weights', type=str, default='./yolov3.pt', help='weights path') # from yolov3/models/
parser.add_argument('--weights', type=str, default='./yolov3.pt', help='weights path')
parser.add_argument('--img-size', nargs='+', type=int, default=[640, 640], help='image size') # height, width
parser.add_argument('--batch-size', type=int, default=1, help='batch size')
parser.add_argument('--dynamic', action='store_true', help='dynamic ONNX axes')
parser.add_argument('--grid', action='store_true', help='export Detect() layer grid')
parser.add_argument('--device', default='cpu', help='cuda device, i.e. 0 or 0,1,2,3 or cpu')
parser.add_argument('--include', nargs='+', default=['torchscript', 'onnx', 'coreml'], help='include formats')
parser.add_argument('--half', action='store_true', help='FP16 half-precision export')
parser.add_argument('--inplace', action='store_true', help='set YOLOv3 Detect() inplace=True')
parser.add_argument('--train', action='store_true', help='model.train() mode')
parser.add_argument('--optimize', action='store_true', help='optimize TorchScript for mobile') # TorchScript-only
parser.add_argument('--dynamic', action='store_true', help='dynamic ONNX axes') # ONNX-only
parser.add_argument('--simplify', action='store_true', help='simplify ONNX model') # ONNX-only
parser.add_argument('--opset-version', type=int, default=12, help='ONNX opset version') # ONNX-only
opt = parser.parse_args()
opt.img_size *= 2 if len(opt.img_size) == 1 else 1 # expand
opt.include = [x.lower() for x in opt.include]
print(opt)
set_logging()
t = time.time()
@@ -41,11 +50,16 @@ if __name__ == '__main__':
# Checks
gs = int(max(model.stride)) # grid size (max stride)
opt.img_size = [check_img_size(x, gs) for x in opt.img_size] # verify img_size are gs-multiples
assert not (opt.device.lower() == 'cpu' and opt.half), '--half only compatible with GPU export, i.e. use --device 0'
# Input
img = torch.zeros(opt.batch_size, 3, *opt.img_size).to(device) # image size(1,3,320,192) iDetection
# Update model
if opt.half:
img, model = img.half(), model.half() # to FP16
if opt.train:
model.train() # training mode (no grid construction in Detect layer)
for k, m in model.named_modules():
m._non_persistent_buffers_set = set() # pytorch 1.6.0 compatibility
if isinstance(m, models.common.Conv): # assign export-friendly activations
@@ -53,52 +67,79 @@ if __name__ == '__main__':
m.act = Hardswish()
elif isinstance(m.act, nn.SiLU):
m.act = SiLU()
# elif isinstance(m, models.yolo.Detect):
# m.forward = m.forward_export # assign forward (optional)
model.model[-1].export = not opt.grid # set Detect() layer grid export
y = model(img) # dry run
elif isinstance(m, models.yolo.Detect):
m.inplace = opt.inplace
m.onnx_dynamic = opt.dynamic
# m.forward = m.forward_export # assign forward (optional)
# TorchScript export
try:
print('\nStarting TorchScript export with torch %s...' % torch.__version__)
f = opt.weights.replace('.pt', '.torchscript.pt') # filename
ts = torch.jit.trace(model, img, strict=False)
ts.save(f)
print('TorchScript export success, saved as %s' % f)
except Exception as e:
print('TorchScript export failure: %s' % e)
for _ in range(2):
y = model(img) # dry runs
print(f"\n{colorstr('PyTorch:')} starting from {opt.weights} ({file_size(opt.weights):.1f} MB)")
# ONNX export
try:
import onnx
# TorchScript export -----------------------------------------------------------------------------------------------
if 'torchscript' in opt.include or 'coreml' in opt.include:
prefix = colorstr('TorchScript:')
try:
print(f'\n{prefix} starting export with torch {torch.__version__}...')
f = opt.weights.replace('.pt', '.torchscript.pt') # filename
ts = torch.jit.trace(model, img, strict=False)
(optimize_for_mobile(ts) if opt.optimize else ts).save(f)
print(f'{prefix} export success, saved as {f} ({file_size(f):.1f} MB)')
except Exception as e:
print(f'{prefix} export failure: {e}')
print('\nStarting ONNX export with onnx %s...' % onnx.__version__)
f = opt.weights.replace('.pt', '.onnx') # filename
torch.onnx.export(model, img, f, verbose=False, opset_version=12, input_names=['images'],
output_names=['classes', 'boxes'] if y is None else ['output'],
dynamic_axes={'images': {0: 'batch', 2: 'height', 3: 'width'}, # size(1,3,640,640)
'output': {0: 'batch', 2: 'y', 3: 'x'}} if opt.dynamic else None)
# ONNX export ------------------------------------------------------------------------------------------------------
if 'onnx' in opt.include:
prefix = colorstr('ONNX:')
try:
import onnx
# Checks
onnx_model = onnx.load(f) # load onnx model
onnx.checker.check_model(onnx_model) # check onnx model
# print(onnx.helper.printable_graph(onnx_model.graph)) # print a human readable model
print('ONNX export success, saved as %s' % f)
except Exception as e:
print('ONNX export failure: %s' % e)
print(f'{prefix} starting export with onnx {onnx.__version__}...')
f = opt.weights.replace('.pt', '.onnx') # filename
torch.onnx.export(model, img, f, verbose=False, opset_version=opt.opset_version, input_names=['images'],
training=torch.onnx.TrainingMode.TRAINING if opt.train else torch.onnx.TrainingMode.EVAL,
do_constant_folding=not opt.train,
dynamic_axes={'images': {0: 'batch', 2: 'height', 3: 'width'}, # size(1,3,640,640)
'output': {0: 'batch', 2: 'y', 3: 'x'}} if opt.dynamic else None)
# CoreML export
try:
import coremltools as ct
# Checks
model_onnx = onnx.load(f) # load onnx model
onnx.checker.check_model(model_onnx) # check onnx model
# print(onnx.helper.printable_graph(model_onnx.graph)) # print
print('\nStarting CoreML export with coremltools %s...' % ct.__version__)
# convert model from torchscript and apply pixel scaling as per detect.py
model = ct.convert(ts, inputs=[ct.ImageType(name='image', shape=img.shape, scale=1 / 255.0, bias=[0, 0, 0])])
f = opt.weights.replace('.pt', '.mlmodel') # filename
model.save(f)
print('CoreML export success, saved as %s' % f)
except Exception as e:
print('CoreML export failure: %s' % e)
# Simplify
if opt.simplify:
try:
check_requirements(['onnx-simplifier'])
import onnxsim
print(f'{prefix} simplifying with onnx-simplifier {onnxsim.__version__}...')
model_onnx, check = onnxsim.simplify(
model_onnx,
dynamic_input_shape=opt.dynamic,
input_shapes={'images': list(img.shape)} if opt.dynamic else None)
assert check, 'assert check failed'
onnx.save(model_onnx, f)
except Exception as e:
print(f'{prefix} simplifier failure: {e}')
print(f'{prefix} export success, saved as {f} ({file_size(f):.1f} MB)')
except Exception as e:
print(f'{prefix} export failure: {e}')
# CoreML export ----------------------------------------------------------------------------------------------------
if 'coreml' in opt.include:
prefix = colorstr('CoreML:')
try:
import coremltools as ct
print(f'{prefix} starting export with coremltools {ct.__version__}...')
assert opt.train, 'CoreML exports should be placed in model.train() mode with `python export.py --train`'
model = ct.convert(ts, inputs=[ct.ImageType('image', shape=img.shape, scale=1 / 255.0, bias=[0, 0, 0])])
f = opt.weights.replace('.pt', '.mlmodel') # filename
model.save(f)
print(f'{prefix} export success, saved as {f} ({file_size(f):.1f} MB)')
except Exception as e:
print(f'{prefix} export failure: {e}')
# Finish
print('\nExport complete (%.2fs). Visualize with https://github.com/lutzroeder/netron.' % (time.time() - t))
print(f'\nExport complete ({time.time() - t:.2f}s). Visualize with https://github.com/lutzroeder/netron.')
models/yolo.py
+72 -41
View File
@@ -1,11 +1,16 @@
# YOLOv3 YOLO-specific modules
"""YOLOv3-specific modules
Usage:
$ python path/to/models/yolo.py --cfg yolov3.yaml
"""
import argparse
import logging
import sys
from copy import deepcopy
from pathlib import Path
sys.path.append('./') # to run '$ python *.py' files in subdirectories
sys.path.append(Path(__file__).parent.parent.absolute().__str__()) # to run '$ python *.py' files in subdirectories
logger = logging.getLogger(__name__)
from models.common import *
@@ -23,9 +28,9 @@ except ImportError:
class Detect(nn.Module):
stride = None # strides computed during build
export = False # onnx export
onnx_dynamic = False # ONNX export parameter
def __init__(self, nc=80, anchors=(), ch=()): # detection layer
def __init__(self, nc=80, anchors=(), ch=(), inplace=True): # detection layer
super(Detect, self).__init__()
self.nc = nc # number of classes
self.no = nc + 5 # number of outputs per anchor
@@ -36,23 +41,28 @@ class Detect(nn.Module):
self.register_buffer('anchors', a) # shape(nl,na,2)
self.register_buffer('anchor_grid', a.clone().view(self.nl, 1, -1, 1, 1, 2)) # shape(nl,1,na,1,1,2)
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):
# x = x.copy() # for profiling
z = [] # inference output
self.training |= self.export
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.grid[i].shape[2:4] != x[i].shape[2:4]:
if self.grid[i].shape[2:4] != x[i].shape[2:4] or self.onnx_dynamic:
self.grid[i] = self._make_grid(nx, ny).to(x[i].device)
y = x[i].sigmoid()
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
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 YOLOv5 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].view(1, self.na, 1, 1, 2) # 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)
@@ -72,7 +82,7 @@ class Model(nn.Module):
import yaml # for torch hub
self.yaml_file = Path(cfg).name
with open(cfg) as f:
self.yaml = yaml.load(f, Loader=yaml.SafeLoader) # model dict
self.yaml = yaml.safe_load(f) # model dict
# Define model
ch = self.yaml['ch'] = self.yaml.get('ch', ch) # input channels
@@ -84,18 +94,20 @@ class Model(nn.Module):
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
# print([x.shape for x in self.forward(torch.zeros(1, ch, 64, 64))])
self.inplace = self.yaml.get('inplace', True)
# logger.info([x.shape for x in self.forward(torch.zeros(1, ch, 64, 64))])
# 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
# print('Strides: %s' % m.stride.tolist())
# logger.info('Strides: %s' % m.stride.tolist())
# Init weights, biases
initialize_weights(self)
@@ -104,24 +116,23 @@ class Model(nn.Module):
def forward(self, x, augment=False, profile=False):
if augment:
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[..., :4] /= si # de-scale
if fi == 2:
yi[..., 1] = img_size[0] - yi[..., 1] # de-flip ud
elif fi == 3:
yi[..., 0] = img_size[1] - yi[..., 0] # de-flip lr
y.append(yi)
return torch.cat(y, 1), None # augmented inference, train
return self.forward_augment(x) # augmented inference, None
else:
return self.forward_once(x, profile) # 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)
return torch.cat(y, 1), None # augmented inference, train
def forward_once(self, x, profile=False):
y, dt = [], [] # outputs
for m in self.model:
@@ -134,15 +145,34 @@ class Model(nn.Module):
for _ in range(10):
_ = m(x)
dt.append((time_synchronized() - t) * 100)
print('%10.1f%10.0f%10.1fms %-40s' % (o, m.np, dt[-1], m.type))
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}')
x = m(x) # run
y.append(x if m.i in self.save else None) # save output
if profile:
print('%.1fms total' % sum(dt))
logger.info('%.1fms total' % sum(dt))
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 _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.
@@ -157,15 +187,16 @@ class Model(nn.Module):
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)
print(('%6g Conv2d.bias:' + '%10.3g' * 6) % (mi.weight.shape[1], *b[:5].mean(1).tolist(), b[5:].mean()))
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:
# print('%10.3g' % (m.w.detach().sigmoid() * 2)) # shortcut weights
# logger.info('%10.3g' % (m.w.detach().sigmoid() * 2)) # shortcut weights
def fuse(self): # fuse model Conv2d() + BatchNorm2d() layers
print('Fusing layers... ')
logger.info('Fusing layers... ')
for m in self.model.modules():
if type(m) is Conv and hasattr(m, 'bn'):
m.conv = fuse_conv_and_bn(m.conv, m.bn) # update conv
@@ -177,20 +208,20 @@ class Model(nn.Module):
def nms(self, mode=True): # add or remove NMS module
present = type(self.model[-1]) is NMS # last layer is NMS
if mode and not present:
print('Adding NMS... ')
logger.info('Adding NMS... ')
m = NMS() # module
m.f = -1 # from
m.i = self.model[-1].i + 1 # index
self.model.add_module(name='%s' % m.i, module=m) # add
self.eval()
elif not mode and present:
print('Removing NMS... ')
logger.info('Removing NMS... ')
self.model = self.model[:-1] # remove
return self
def autoshape(self): # add autoShape module
print('Adding autoShape... ')
m = autoShape(self) # wrap model
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
@@ -266,12 +297,12 @@ if __name__ == '__main__':
model.train()
# Profile
# img = torch.rand(8 if torch.cuda.is_available() else 1, 3, 640, 640).to(device)
# img = torch.rand(8 if torch.cuda.is_available() else 1, 3, 320, 320).to(device)
# y = model(img, profile=True)
# Tensorboard
# Tensorboard (not working https://github.com/ultralytics/yolov5/issues/2898)
# from torch.utils.tensorboard import SummaryWriter
# tb_writer = SummaryWriter()
# print("Run 'tensorboard --logdir=models/runs' to view tensorboard at http://localhost:6006/")
# tb_writer.add_graph(model.model, img) # add model to tensorboard
# 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
# tb_writer.add_image('test', img[0], dataformats='CWH') # add model to tensorboard