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

yolo with runs.zip file exp 14 is the best weight

Browse Source
This commit is contained in:
Apoorva Gupta
2023-02-21 21:43:51 +05:30
parent 34abb2b0dd
commit dbe80aca78
43 changed files with 3670 additions and 5669 deletions
Download Patch File Download Diff File Expand all files Collapse all files
yolov3/utils/loggers/__init__.py
+52 -294
View File
@@ -5,26 +5,25 @@ Logging utils
import os
import warnings
from pathlib import Path
from threading import Thread
import pkg_resources as pkg
import torch
from torch.utils.tensorboard import SummaryWriter
from utils.general import LOGGER, colorstr, cv2
from utils.loggers.clearml.clearml_utils import ClearmlLogger
from utils.general import colorstr, emojis
from utils.loggers.wandb.wandb_utils import WandbLogger
from utils.plots import plot_images, plot_labels, plot_results
from utils.plots import plot_images, plot_results
from utils.torch_utils import de_parallel
LOGGERS = ('csv', 'tb', 'wandb', 'clearml', 'comet') # *.csv, TensorBoard, Weights & Biases, ClearML
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}:
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
@@ -34,64 +33,30 @@ try:
except (ImportError, AssertionError):
wandb = None
try:
import clearml
assert hasattr(clearml, '__version__') # verify package import not local dir
except (ImportError, AssertionError):
clearml = None
try:
if RANK not in [0, -1]:
comet_ml = None
else:
import comet_ml
assert hasattr(comet_ml, '__version__') # verify package import not local dir
from utils.loggers.comet import CometLogger
except (ModuleNotFoundError, ImportError, AssertionError):
comet_ml = None
class Loggers():
# YOLOv3 Loggers class
# 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.plots = not opt.noplots # plot results
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
self.best_keys = ['best/epoch', 'best/precision', 'best/recall', 'best/mAP_0.5', 'best/mAP_0.5:0.95']
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
# Messages
if not clearml:
prefix = colorstr('ClearML: ')
s = f"{prefix}run 'pip install clearml' to automatically track, visualize and remotely train YOLOv3 🚀 in ClearML"
self.logger.info(s)
if not comet_ml:
prefix = colorstr('Comet: ')
s = f"{prefix}run 'pip install comet_ml' to automatically track and visualize YOLOv3 🚀 runs in Comet"
self.logger.info(s)
# 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:
@@ -101,127 +66,53 @@ class Loggers():
# 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)
self.wandb = WandbLogger(self.opt, run_id)
else:
self.wandb = None
# ClearML
if clearml and 'clearml' in self.include:
try:
self.clearml = ClearmlLogger(self.opt, self.hyp)
except Exception:
self.clearml = None
prefix = colorstr('ClearML: ')
LOGGER.warning(f'{prefix}WARNING ⚠️ ClearML is installed but not configured, skipping ClearML logging.'
f' See https://github.com/ultralytics/yolov5/tree/master/utils/loggers/clearml#readme')
else:
self.clearml = None
# Comet
if comet_ml and 'comet' in self.include:
if isinstance(self.opt.resume, str) and self.opt.resume.startswith('comet://'):
run_id = self.opt.resume.split('/')[-1]
self.comet_logger = CometLogger(self.opt, self.hyp, run_id=run_id)
else:
self.comet_logger = CometLogger(self.opt, self.hyp)
else:
self.comet_logger = None
@property
def remote_dataset(self):
# Get data_dict if custom dataset artifact link is provided
data_dict = None
if self.clearml:
data_dict = self.clearml.data_dict
if self.wandb:
data_dict = self.wandb.data_dict
if self.comet_logger:
data_dict = self.comet_logger.data_dict
return data_dict
def on_train_start(self):
if self.comet_logger:
self.comet_logger.on_train_start()
def on_pretrain_routine_start(self):
if self.comet_logger:
self.comet_logger.on_pretrain_routine_start()
def on_pretrain_routine_end(self, labels, names):
def on_pretrain_routine_end(self):
# Callback runs on pre-train routine end
if self.plots:
plot_labels(labels, names, self.save_dir)
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]})
# if self.clearml:
# pass # ClearML saves these images automatically using hooks
if self.comet_logger:
self.comet_logger.on_pretrain_routine_end(paths)
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, model, ni, imgs, targets, paths, vals):
log_dict = dict(zip(self.keys[:3], vals))
def on_train_batch_end(self, ni, model, imgs, targets, paths, plots, sync_bn):
# Callback runs on train batch end
# ni: number integrated batches (since train start)
if self.plots:
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
plot_images(imgs, targets, paths, f)
if ni == 0 and self.tb and not self.opt.sync_bn:
log_tensorboard_graph(self.tb, model, imgsz=(self.opt.imgsz, self.opt.imgsz))
if ni == 10 and (self.wandb or self.clearml):
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'))
if self.wandb:
self.wandb.log({'Mosaics': [wandb.Image(str(f), caption=f.name) for f in files if f.exists()]})
if self.clearml:
self.clearml.log_debug_samples(files, title='Mosaics')
if self.comet_logger:
self.comet_logger.on_train_batch_end(log_dict, step=ni)
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
if self.comet_logger:
self.comet_logger.on_train_epoch_end(epoch)
def on_val_start(self):
if self.comet_logger:
self.comet_logger.on_val_start()
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)
if self.clearml:
self.clearml.log_image_with_boxes(path, pred, names, im)
def on_val_batch_end(self, batch_i, im, targets, paths, shapes, out):
if self.comet_logger:
self.comet_logger.on_val_batch_end(batch_i, im, targets, paths, shapes, out)
def on_val_end(self, nt, tp, fp, p, r, f1, ap, ap50, ap_class, confusion_matrix):
def on_val_end(self):
# Callback runs on val end
if self.wandb or self.clearml:
files = sorted(self.save_dir.glob('val*.jpg'))
if self.wandb:
self.wandb.log({'Validation': [wandb.Image(str(f), caption=f.name) for f in files]})
if self.clearml:
self.clearml.log_debug_samples(files, title='Validation')
if self.comet_logger:
self.comet_logger.on_val_end(nt, tp, fp, p, r, f1, ap, ap50, ap_class, confusion_matrix)
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 = dict(zip(self.keys, vals))
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
@@ -232,170 +123,37 @@ class Loggers():
if self.tb:
for k, v in x.items():
self.tb.add_scalar(k, v, epoch)
elif self.clearml: # log to ClearML if TensorBoard not used
for k, v in x.items():
title, series = k.split('/')
self.clearml.task.get_logger().report_scalar(title, series, v, epoch)
if self.wandb:
if best_fitness == fi:
best_results = [epoch] + vals[3:7]
for i, name in enumerate(self.best_keys):
self.wandb.wandb_run.summary[name] = best_results[i] # log best results in the summary
self.wandb.log(x)
self.wandb.end_epoch()
if self.clearml:
self.clearml.current_epoch_logged_images = set() # reset epoch image limit
self.clearml.current_epoch += 1
if self.comet_logger:
self.comet_logger.on_fit_epoch_end(x, epoch=epoch)
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 (epoch + 1) % self.opt.save_period == 0 and not final_epoch and self.opt.save_period != -1:
if self.wandb:
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)
if self.clearml:
self.clearml.task.update_output_model(model_path=str(last),
model_name='Latest Model',
auto_delete_file=False)
if self.comet_logger:
self.comet_logger.on_model_save(last, epoch, final_epoch, best_fitness, fi)
def on_train_end(self, last, best, epoch, results):
# Callback runs on training end, i.e. saving best model
if self.plots:
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
self.logger.info(f"Results saved to {colorstr('bold', self.save_dir)}")
if self.tb and not self.clearml: # These images are already captured by ClearML by now, we don't want doubles
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(dict(zip(self.keys[3:10], results)))
self.wandb.log({'Results': [wandb.Image(str(f), caption=f.name) for f in files]})
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=f'run_{self.wandb.wandb_run.id}_model',
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()
if self.clearml and not self.opt.evolve:
self.clearml.task.update_output_model(model_path=str(best if best.exists() else last),
name='Best Model',
auto_delete_file=False)
if self.comet_logger:
final_results = dict(zip(self.keys[3:10], results))
self.comet_logger.on_train_end(files, self.save_dir, last, best, epoch, final_results)
def on_params_update(self, params: dict):
# Update hyperparams or configs of the experiment
if self.wandb:
self.wandb.wandb_run.config.update(params, allow_val_change=True)
if self.comet_logger:
self.comet_logger.on_params_update(params)
class GenericLogger:
"""
YOLOv5 General purpose logger for non-task specific logging
Usage: from utils.loggers import GenericLogger; logger = GenericLogger(...)
Arguments
opt: Run arguments
console_logger: Console logger
include: loggers to include
"""
def __init__(self, opt, console_logger, include=('tb', 'wandb')):
# init default loggers
self.save_dir = Path(opt.save_dir)
self.include = include
self.console_logger = console_logger
self.csv = self.save_dir / 'results.csv' # CSV logger
if 'tb' in self.include:
prefix = colorstr('TensorBoard: ')
self.console_logger.info(
f"{prefix}Start with 'tensorboard --logdir {self.save_dir.parent}', view at http://localhost:6006/")
self.tb = SummaryWriter(str(self.save_dir))
if wandb and 'wandb' in self.include:
self.wandb = wandb.init(project=web_project_name(str(opt.project)),
name=None if opt.name == 'exp' else opt.name,
config=opt)
else:
self.wandb = None
def log_metrics(self, metrics, epoch):
# Log metrics dictionary to all loggers
if self.csv:
keys, vals = list(metrics.keys()), list(metrics.values())
n = len(metrics) + 1 # number of cols
s = '' if self.csv.exists() else (('%23s,' * n % tuple(['epoch'] + keys)).rstrip(',') + '\n') # header
with open(self.csv, 'a') as f:
f.write(s + ('%23.5g,' * n % tuple([epoch] + vals)).rstrip(',') + '\n')
if self.tb:
for k, v in metrics.items():
self.tb.add_scalar(k, v, epoch)
if self.wandb:
self.wandb.log(metrics, step=epoch)
def log_images(self, files, name='Images', epoch=0):
# Log images to all loggers
files = [Path(f) for f in (files if isinstance(files, (tuple, list)) else [files])] # to Path
files = [f for f in files if f.exists()] # filter by exists
if self.tb:
for f in files:
self.tb.add_image(f.stem, cv2.imread(str(f))[..., ::-1], epoch, dataformats='HWC')
if self.wandb:
self.wandb.log({name: [wandb.Image(str(f), caption=f.name) for f in files]}, step=epoch)
def log_graph(self, model, imgsz=(640, 640)):
# Log model graph to all loggers
if self.tb:
log_tensorboard_graph(self.tb, model, imgsz)
def log_model(self, model_path, epoch=0, metadata={}):
# Log model to all loggers
if self.wandb:
art = wandb.Artifact(name=f'run_{wandb.run.id}_model', type='model', metadata=metadata)
art.add_file(str(model_path))
wandb.log_artifact(art)
def update_params(self, params):
# Update the parameters logged
if self.wandb:
wandb.run.config.update(params, allow_val_change=True)
def log_tensorboard_graph(tb, model, imgsz=(640, 640)):
# Log model graph to TensorBoard
try:
p = next(model.parameters()) # for device, type
imgsz = (imgsz, imgsz) if isinstance(imgsz, int) else imgsz # expand
im = torch.zeros((1, 3, *imgsz)).to(p.device).type_as(p) # input image (WARNING: must be zeros, not empty)
with warnings.catch_warnings():
warnings.simplefilter('ignore') # suppress jit trace warning
tb.add_graph(torch.jit.trace(de_parallel(model), im, strict=False), [])
except Exception as e:
LOGGER.warning(f'WARNING ⚠️ TensorBoard graph visualization failure {e}')
def web_project_name(project):
# Convert local project name to web project name
if not project.startswith('runs/train'):
return project
suffix = '-Classify' if project.endswith('-cls') else '-Segment' if project.endswith('-seg') else ''
return f'YOLOv5{suffix}'
self.wandb.finish_run()
else:
self.wandb.finish_run()
self.wandb = WandbLogger(self.opt)
yolov3/utils/loggers/wandb/wandb_utils.py
+382 -43
View File
@@ -1,32 +1,108 @@
# YOLOv3 🚀 by Ultralytics, GPL-3.0 license
# WARNING ⚠️ wandb is deprecated and will be removed in future release.
# See supported integrations at https://github.com/ultralytics/yolov5#integrations
"""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
from utils.general import LOGGER, colorstr
import pkg_resources as pkg
import yaml
from tqdm import tqdm
FILE = Path(__file__).resolve()
ROOT = FILE.parents[3] # YOLOv5 root directory
ROOT = FILE.parents[3] # root directory
if str(ROOT) not in sys.path:
sys.path.append(str(ROOT)) # add ROOT to PATH
RANK = int(os.getenv('RANK', -1))
DEPRECATION_WARNING = f"{colorstr('wandb')}: WARNING ⚠️ wandb is deprecated and will be removed in a future release. " \
f'See supported integrations at https://github.com/ultralytics/yolov5#integrations.'
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
LOGGER.warning(DEPRECATION_WARNING)
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.
@@ -46,7 +122,7 @@ class WandbLogger():
"""
- Initialize WandbLogger instance
- Upload dataset if opt.upload_dataset is True
- Setup training processes if job_type is 'Training'
- Setup trainig processes if job_type is 'Training'
arguments:
opt (namespace) -- Commandline arguments for this run
@@ -56,31 +132,82 @@ class WandbLogger():
"""
# Pre-training routine --
self.job_type = job_type
self.wandb, self.wandb_run = wandb, wandb.run if wandb else None
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
if self.wandb:
# 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='YOLOv5' if opt.project == 'runs/train' else Path(opt.project).stem,
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 isinstance(opt.data, dict):
# This means another dataset manager has already processed the dataset info (e.g. ClearML)
# and they will have stored the already processed dict in opt.data
self.data_dict = opt.data
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:
@@ -95,18 +222,77 @@ class WandbLogger():
self.log_dict, self.current_epoch = {}, 0
self.bbox_interval = opt.bbox_interval
if isinstance(opt.resume, str):
model_dir, _ = self.download_model_artifact(opt)
if model_dir:
self.weights = Path(model_dir) / 'last.pt'
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, opt.imgsz = str(
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, config.imgsz
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
if opt.evolve or opt.noplots:
self.bbox_interval = opt.bbox_interval = opt.epochs + 1 # disable bbox_interval
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):
"""
@@ -119,22 +305,166 @@ class WandbLogger():
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 = 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}')
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):
pass
"""
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):
"""
@@ -147,7 +477,7 @@ class WandbLogger():
for key, value in log_dict.items():
self.log_dict[key] = value
def end_epoch(self):
def end_epoch(self, best_result=False):
"""
commit the log_dict, model artifacts and Tables to W&B and flush the log_dict.
@@ -156,15 +486,25 @@ class WandbLogger():
"""
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}'
)
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):
"""
@@ -175,7 +515,6 @@ class WandbLogger():
with all_logging_disabled():
wandb.log(self.log_dict)
wandb.run.finish()
LOGGER.warning(DEPRECATION_WARNING)
@contextmanager