def parse_opt(): parser = argparse.ArgumentParser() parser.add_argument('--data', type=str, default=ROOT / 'data/coco128.yaml', help='dataset.yaml path') parser.add_argument('--weights', nargs='+', type=str, default=ROOT / 'yolov5s.pt', help='model.pt path(s)') parser.add_argument('--batch-size', type=int, default=32, help='batch size') parser.add_argument('--imgsz', '--img', '--img-size', type=int, default=640, help='inference size (pixels)') parser.add_argument('--conf-thres', type=float, default=0.001, help='confidence threshold') parser.add_argument('--iou-thres', type=float, default=0.6, help='NMS IoU threshold') parser.add_argument('--task', default='val', help='train, val, test, speed or study') parser.add_argument('--device', default='', help='cuda device, i.e. 0 or 0,1,2,3 or cpu') parser.add_argument('--single-cls', action='store_true', help='treat as single-class dataset') parser.add_argument('--augment', action='store_true', help='augmented inference') parser.add_argument('--verbose', action='store_true', help='report mAP by class') parser.add_argument('--save-txt', action='store_true', help='save results to *.txt') parser.add_argument('--save-hybrid', action='store_true', help='save label+prediction hybrid results to *.txt') parser.add_argument('--save-conf', action='store_true', help='save confidences in --save-txt labels') parser.add_argument('--save-json', action='store_true', help='save a COCO-JSON results file') parser.add_argument('--project', default=ROOT / 'runs/val', 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('--half', action='store_true', help='use FP16 half-precision inference') opt = parser.parse_args() opt.data = check_yaml(opt.data) # check YAML opt.save_json |= opt.data.endswith('coco.yaml') opt.save_txt |= opt.save_hybrid print_args(FILE.stem, opt) return opt
def main(opt, callbacks=Callbacks()): # Checks if RANK in [-1, 0]: print_args(FILE.stem, opt) check_git_status() check_requirements(exclude=['thop']) # Resume if opt.resume and not check_wandb_resume(opt): # resume an interrupted run ckpt = opt.resume if isinstance( opt.resume, str) else get_latest_run() # specified or most recent path assert os.path.isfile( ckpt), 'ERROR: --resume checkpoint does not exist' with open(Path(ckpt).parent.parent / 'opt.yaml', errors='ignore') as f: opt = argparse.Namespace(**yaml.safe_load(f)) # replace opt.cfg, opt.weights, opt.resume = '', ckpt, True # reinstate LOGGER.info(f'Resuming training from {ckpt}') else: opt.data, opt.cfg, opt.hyp, opt.weights, opt.project = \ check_file(opt.data), check_yaml(opt.cfg), check_yaml(opt.hyp), str(opt.weights), str(opt.project) # checks assert len(opt.cfg) or len( opt.weights), 'either --cfg or --weights must be specified' opt.save_dir = str( increment_path(Path(opt.project) / opt.name, exist_ok=opt.exist_ok)) # DDP mode device = select_device(opt.device, batch_size=opt.batch_size) if LOCAL_RANK != -1: assert torch.cuda.device_count( ) > LOCAL_RANK, 'insufficient CUDA devices for DDP command' assert opt.batch_size % WORLD_SIZE == 0, '--batch-size must be multiple of CUDA device count' assert not opt.image_weights, '--image-weights argument is not compatible with DDP training' torch.cuda.set_device(LOCAL_RANK) device = torch.device('cuda', LOCAL_RANK) dist.init_process_group( backend="nccl" if dist.is_nccl_available() else "gloo") # Train train(opt.hyp, opt, device, callbacks) if WORLD_SIZE > 1 and RANK == 0: LOGGER.info('Destroying process group... ') dist.destroy_process_group()
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/yolov5" 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
def main(opt, callbacks=Callbacks()): # Checks if RANK in [-1, 0]: print_args(FILE.stem, opt) check_git_status() check_requirements(exclude=['thop']) # Resume if opt.resume and not check_wandb_resume(opt) and not opt.evolve: # resume an interrupted run ckpt = opt.resume if isinstance(opt.resume, str) else get_latest_run() # specified or most recent path assert os.path.isfile(ckpt), 'ERROR: --resume checkpoint does not exist' with open(Path(ckpt).parent.parent / 'opt.yaml', errors='ignore') as f: opt = argparse.Namespace(**yaml.safe_load(f)) # replace opt.cfg, opt.weights, opt.resume = '', ckpt, True # reinstate LOGGER.info(f'Resuming training from {ckpt}') else: opt.data, opt.cfg, opt.hyp, opt.weights, opt.project = \ check_file(opt.data), check_yaml(opt.cfg), check_yaml(opt.hyp), str(opt.weights), str(opt.project) # checks assert len(opt.cfg) or len(opt.weights), 'either --cfg or --weights must be specified' if opt.evolve: if opt.project == str(ROOT / 'runs/train'): # if default project name, rename to runs/evolve opt.project = str(ROOT / 'runs/evolve') opt.exist_ok, opt.resume = opt.resume, False # pass resume to exist_ok and disable resume opt.save_dir = str(increment_path(Path(opt.project) / opt.name, exist_ok=opt.exist_ok)) # DDP mode device = select_device(opt.device, batch_size=opt.batch_size) if LOCAL_RANK != -1: msg = 'is not compatible with YOLOv5 Multi-GPU DDP training' assert not opt.image_weights, f'--image-weights {msg}' assert not opt.evolve, f'--evolve {msg}' assert opt.batch_size != -1, f'AutoBatch with --batch-size -1 {msg}, please pass a valid --batch-size' assert opt.batch_size % WORLD_SIZE == 0, f'--batch-size {opt.batch_size} must be multiple of WORLD_SIZE' assert torch.cuda.device_count() > LOCAL_RANK, 'insufficient CUDA devices for DDP command' torch.cuda.set_device(LOCAL_RANK) device = torch.device('cuda', LOCAL_RANK) dist.init_process_group(backend="nccl" if dist.is_nccl_available() else "gloo") # Train if not opt.evolve: train(opt.hyp, opt, device, callbacks) if WORLD_SIZE > 1 and RANK == 0: LOGGER.info('Destroying process group... ') dist.destroy_process_group() # Evolve hyperparameters (optional) else: # Hyperparameter evolution metadata (mutation scale 0-1, lower_limit, upper_limit) meta = {'lr0': (1, 1e-5, 1e-1), # initial learning rate (SGD=1E-2, Adam=1E-3) 'lrf': (1, 0.01, 1.0), # final OneCycleLR learning rate (lr0 * lrf) 'momentum': (0.3, 0.6, 0.98), # SGD momentum/Adam beta1 'weight_decay': (1, 0.0, 0.001), # optimizer weight decay 'warmup_epochs': (1, 0.0, 5.0), # warmup epochs (fractions ok) 'warmup_momentum': (1, 0.0, 0.95), # warmup initial momentum 'warmup_bias_lr': (1, 0.0, 0.2), # warmup initial bias lr 'box': (1, 0.02, 0.2), # box loss gain 'cls': (1, 0.2, 4.0), # cls loss gain 'cls_pw': (1, 0.5, 2.0), # cls BCELoss positive_weight 'obj': (1, 0.2, 4.0), # obj loss gain (scale with pixels) 'obj_pw': (1, 0.5, 2.0), # obj BCELoss positive_weight 'iou_t': (0, 0.1, 0.7), # IoU training threshold 'anchor_t': (1, 2.0, 8.0), # anchor-multiple threshold 'anchors': (2, 2.0, 10.0), # anchors per output grid (0 to ignore) 'fl_gamma': (0, 0.0, 2.0), # focal loss gamma (efficientDet default gamma=1.5) 'hsv_h': (1, 0.0, 0.1), # image HSV-Hue augmentation (fraction) 'hsv_s': (1, 0.0, 0.9), # image HSV-Saturation augmentation (fraction) 'hsv_v': (1, 0.0, 0.9), # image HSV-Value augmentation (fraction) 'degrees': (1, 0.0, 45.0), # image rotation (+/- deg) 'translate': (1, 0.0, 0.9), # image translation (+/- fraction) 'scale': (1, 0.0, 0.9), # image scale (+/- gain) 'shear': (1, 0.0, 10.0), # image shear (+/- deg) 'perspective': (0, 0.0, 0.001), # image perspective (+/- fraction), range 0-0.001 'flipud': (1, 0.0, 1.0), # image flip up-down (probability) 'fliplr': (0, 0.0, 1.0), # image flip left-right (probability) 'mosaic': (1, 0.0, 1.0), # image mixup (probability) 'mixup': (1, 0.0, 1.0), # image mixup (probability) 'copy_paste': (1, 0.0, 1.0)} # segment copy-paste (probability) with open(opt.hyp, errors='ignore') as f: hyp = yaml.safe_load(f) # load hyps dict if 'anchors' not in hyp: # anchors commented in hyp.yaml hyp['anchors'] = 3 opt.noval, opt.nosave, save_dir = True, True, Path(opt.save_dir) # only val/save final epoch # ei = [isinstance(x, (int, float)) for x in hyp.values()] # evolvable indices evolve_yaml, evolve_csv = save_dir / 'hyp_evolve.yaml', save_dir / 'evolve.csv' if opt.bucket: os.system(f'gsutil cp gs://{opt.bucket}/evolve.csv {save_dir}') # download evolve.csv if exists for _ in range(opt.evolve): # generations to evolve if evolve_csv.exists(): # if evolve.csv exists: select best hyps and mutate # Select parent(s) parent = 'single' # parent selection method: 'single' or 'weighted' x = np.loadtxt(evolve_csv, ndmin=2, delimiter=',', skiprows=1) n = min(5, len(x)) # number of previous results to consider x = x[np.argsort(-fitness(x))][:n] # top n mutations w = fitness(x) - fitness(x).min() + 1E-6 # weights (sum > 0) if parent == 'single' or len(x) == 1: # x = x[random.randint(0, n - 1)] # random selection x = x[random.choices(range(n), weights=w)[0]] # weighted selection elif parent == 'weighted': x = (x * w.reshape(n, 1)).sum(0) / w.sum() # weighted combination # Mutate mp, s = 0.8, 0.2 # mutation probability, sigma npr = np.random npr.seed(int(time.time())) g = np.array([meta[k][0] for k in hyp.keys()]) # gains 0-1 ng = len(meta) v = np.ones(ng) while all(v == 1): # mutate until a change occurs (prevent duplicates) v = (g * (npr.random(ng) < mp) * npr.randn(ng) * npr.random() * s + 1).clip(0.3, 3.0) for i, k in enumerate(hyp.keys()): # plt.hist(v.ravel(), 300) hyp[k] = float(x[i + 7] * v[i]) # mutate # Constrain to limits for k, v in meta.items(): hyp[k] = max(hyp[k], v[1]) # lower limit hyp[k] = min(hyp[k], v[2]) # upper limit hyp[k] = round(hyp[k], 5) # significant digits # Train mutation results = train(hyp.copy(), opt, device, callbacks) callbacks = Callbacks() # Write mutation results print_mutation(results, hyp.copy(), save_dir, opt.bucket) # Plot results plot_evolve(evolve_csv) LOGGER.info(f'Hyperparameter evolution finished {opt.evolve} generations\n' f"Results saved to {colorstr('bold', save_dir)}\n" f'Usage example: $ python train.py --hyp {evolve_yaml}')
parser = argparse.ArgumentParser() parser.add_argument('--cfg', type=str, default='yolov5s.yaml', 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: