YOLOv5 🚀 by Ultralytics, GPL-3.0 license """ Train a YOLOv5 model on a custom dataset.…
- User
YOLOv5 🚀 by Ultralytics, GPL-3.0 license
""" Train a YOLOv5 model on a custom dataset. Models and datasets download automatically from the latest YOLOv5 release.
Usage - Single-GPU training: python train.py --data coco128.yaml --weights yolov5s.pt --img 640 # from pretrained (recommended) python train.py --data coco128.yaml --weights '' --cfg yolov5s.yaml --img 640 # from scratch
Usage - Multi-GPU DDP training: $ python -m torch.distributed.run --nproc_per_node 4 --master_port 1 train.py --data coco128.yaml --weights yolov5s.pt --img 640 --device 0,1,2,3
Models: https://github.com/ultralytics/yolov5/tree/master/models Datasets: https://github.com/ultralytics/yolov5/tree/master/data Tutorial: https://github.com/ultralytics/yolov5/wiki/Train-Custom-Data """
import argparse import math import os import random import sys import time import traceback
from copy import deepcopy from datetime import datetime from pathlib import Path
import numpy as np import torch import torch.distributed as dist import torch.nn as nn import yaml from torch.optim import lr_scheduler from tqdm import tqdm
FILE = Path(file).resolve() ROOT = FILE.parents[0] # YOLOv5 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
import val as validate # for end-of-epoch mAP from models.experimental import attempt_load from models.yolo import Model from utils.autoanchor import check_anchors from utils.autobatch import check_train_batch_size from utils.callbacks import Callbacks from utils.dataloaders import create_dataloader from utils.downloads import attempt_download, is_url from utils.general import (LOGGER, TQDM_BAR_FORMAT, check_amp, check_dataset, check_file, check_git_info, check_git_status, check_img_size, check_requirements, check_suffix, check_yaml, colorstr, get_latest_run, increment_path, init_seeds, intersect_dicts, labels_to_class_weights, labels_to_image_weights, methods, one_cycle, print_args, print_mutation, strip_optimizer, yaml_save) from utils.loggers import Loggers from utils.loggers.comet.comet_utils import check_comet_resume from utils.loss import ComputeLoss from utils.metrics import fitness from utils.plots import plot_evolve from utils.torch_utils import (EarlyStopping, ModelEMA, de_parallel, select_device, smart_DDP, smart_optimizer, smart_resume, torch_distributed_zero_first)
LOCAL_RANK = int(os.getenv('LOCAL_RANK', -1)) # https://pytorch.org/docs/stable/elastic/run.html RANK = int(os.getenv('RANK', -1)) WORLD_SIZE = int(os.getenv('WORLD_SIZE', 1)) GIT_INFO = check_git_info()
def train(hyp, opt, device, callbacks): # hyp is path/to/hyp.yaml or hyp dictionary save_dir, epochs, batch_size, weights, single_cls, evolve, data, cfg, resume, noval, nosave, workers, freeze =
Path(opt.save_dir), opt.epochs, opt.batch_size, opt.weights, opt.single_cls, opt.evolve, opt.data, opt.cfg,
opt.resume, opt.noval, opt.nosave, opt.workers, opt.freeze callbacks.run('on_pretrain_routine_start')# Directories w = save_dir / 'weights' # weights dir (w.parent if evolve else w).mkdir(parents=True, exist_ok=True) # make dir last, best = w / 'last.pt', w / 'best.pt' # Hyperparameters if isinstance(hyp, str): with open(hyp, errors='ignore') as f: hyp = yaml.safe_load(f) # load hyps dict LOGGER.info(colorstr('hyperparameters: ') + ', '.join(f'{k}={v}' for k, v in hyp.items())) opt.hyp = hyp.copy() # for saving hyps to checkpoints # Save run settings if not evolve: yaml_save(save_dir / 'hyp.yaml', hyp) yaml_save(save_dir / 'opt.yaml', vars(opt)) # Loggers data_dict = None if RANK in {-1, 0}: loggers = Loggers(save_dir, weights, opt, hyp, LOGGER) # loggers instance # Register actions for k in methods(loggers): callbacks.register_action(k, callback=getattr(loggers, k)) # Process custom dataset artifact link data_dict = loggers.remote_dataset if resume: # If resuming runs from remote artifact weights, epochs, hyp, batch_size = opt.weights, opt.epochs, opt.hyp, opt.batch_size # Config plots = not evolve and not opt.noplots # create plots cuda = device.type != 'cpu' init_seeds(opt.seed + 1 + RANK, deterministic=True) with torch_distributed_zero_first(LOCAL_RANK): data_dict = data_dict or check_dataset(data) # check if None train_path, val_path = data_dict['train'], data_dict['val'] nc = 1 if single_cls else int(data_dict['nc']) # number of classes names = {0: 'item'} if single_cls and len(data_dict['names']) != 1 else data_dict['names'] # class names is_coco = isinstance(val_path, str) and val_path.endswith('coco/val2017.txt') # COCO dataset # Model check_suffix(weights, '.pt') # check weights pretrained = weights.endswith('.pt') if pretrained: with torch_distributed_zero_first(LOCAL_RANK): weights = attempt_download(weights) # download if not found locally ckpt = torch.load(weights, map_location='cpu') # load checkpoint to CPU to avoid CUDA memory leak model = Model(cfg or ckpt['model'].yaml, ch=3, nc=nc, anchors=hyp.get('anchors')).to(device) # create exclude = ['anchor'] if (cfg or hyp.get('anchors')) and not resume else [] # exclude keys csd = ckpt['model'].float().state_dict() # checkpoint state_dict as FP32 csd = intersect_dicts(csd, model.state_dict(), exclude=exclude) # intersect model.load_state_dict(csd, strict=False) # load LOGGER.info(f'Transferred {len(csd)}/{len(model.state_dict())} items from {weights}') # report else: model = Model(cfg, ch=3, nc=nc, anchors=hyp.get('anchors')).to(device) # create amp = check_amp(model) # check AMP # Freeze freeze = [f'model.{x}.' for x in (freeze if len(freeze) > 1 else range(freeze[0]))] # layers to freeze for k, v in model.named_parameters(): v.requires_grad = True # train all layers # v.register_hook(lambda x: torch.nan_to_num(x)) # NaN to 0 (commented for erratic training results) if any(x in k for x in freeze): LOGGER.info(f'freezing {k}') v.requires_grad = False # Image size gs = max(int(model.stride.max()), 32) # grid size (max stride) imgsz = check_img_size(opt.imgsz, gs, floor=gs * 2) # verify imgsz is gs-multiple # Batch size if RANK == -1 and batch_size == -1: # single-GPU only, estimate best batch size batch_size = check_train_batch_size(model, imgsz, amp) loggers.on_params_update({"batch_size": batch_size}) # Optimizer nbs = 64 # nominal batch size accumulate = max(round(nbs / batch_size), 1) # accumulate loss before optimizing hyp['weight_decay'] *= batch_size * accumulate / nbs # scale weight_decay optimizer = smart_optimizer(model, opt.optimizer, hyp['lr0'], hyp['momentum'], hyp['weight_decay']) # Scheduler if opt.cos_lr: lf = one_cycle(1, hyp['lrf'], epochs) # cosine 1->hyp['lrf'] else: lf = lambda x: (1 - x / epochs) * (1.0 - hyp['lrf']) + hyp['lrf'] # linear scheduler = lr_scheduler.LambdaLR(optimizer, lr_lambda=lf) # plot_lr_scheduler(optimizer, scheduler, epochs) # EMA ema = ModelEMA(model) if RANK in {-1, 0} else None # Resume best_fitness, start_epoch = 0.0, 0 if pretrained: if resume: best_fitness, start_epoch, epochs = smart_resume(ckpt, optimizer, ema, weights, epochs, resume) del ckpt, csd # DP mode if cuda and RANK == -1 and torch.cuda.device_count() > 1: LOGGER.warning('WARNING ⚠️ DP not recommended, use torch.distributed.run for best DDP Multi-GPU results.\n' 'See Multi-GPU Tutorial at https://github.com/ultralytics/yolov5/issues/475 to get started.') model = torch.nn.DataParallel(model) # SyncBatchNorm if opt.sync_bn and cuda and RANK != -1: model = torch.nn.SyncBatchNorm.convert_sync_batchnorm(model).to(device) LOGGER.info('Using SyncBatchNorm()') # Trainloader train_loader, dataset = create_dataloader(train_path, imgsz, batch_size // WORLD_SIZE, gs, single_cls, hyp=hyp, augment=True, cache=None if opt.cache == 'val' else opt.cache, rect=opt.rect, rank=LOCAL_RANK, workers=workers, image_weights=opt.image_weights, quad=opt.quad, prefix=colorstr('train: '), shuffle=True) labels = np.concatenate(dataset.labels, 0) mlc = int(labels[:, 0].max()) # max label class assert mlc < nc, f'Label class {mlc} exceeds nc={nc} in {data}. Possible class labels are 0-{nc - 1}' # Process 0 if RANK in {-1, 0}: val_loader = create_dataloader(val_path, imgsz, batch_size // WORLD_SIZE * 2, gs, single_cls, hyp=hyp, cache=None if noval else opt.cache, rect=True, rank=-1, workers=workers * 2, pad=0.5, prefix=colorstr('val: '))[0] if not resume: if not opt.noautoanchor: check_anchors(dataset, model=model, thr=hyp['anchor_t'], imgsz=imgsz) # run AutoAnchor model.half().float() # pre-reduce anchor precision callbacks.run('on_pretrain_routine_end', labels, names) # DDP mode if cuda and RANK != -1: model = smart_DDP(model) # Model attributes nl = de_parallel(model).model[-1].nl # number of detection layers (to scale hyps) hyp['box'] *= 3 / nl # scale to layers hyp['cls'] *= nc / 80 * 3 / nl # scale to classes and layers hyp['obj'] *= (imgsz / 640) ** 2 * 3 / nl # scale to image size and layers hyp['label_smoothing'] = opt.label_smoothing model.nc = nc # attach number of classes to model model.hyp = hyp # attach hyperparameters to model model.class_weights = labels_to_class_weights(dataset.labels, nc).to(device) * nc # attach class weights model.names = names # Start training t0 = time.time() nb = len(train_loader) # number of batches nw = max(round(hyp['warmup_epochs'] * nb), 100) # number of warmup iterations, max(3 epochs, 100 iterations) # nw = min(nw, (epochs - start_epoch) / 2 * nb) # limit warmup to < 1/2 of training last_opt_step = -1 maps = np.zeros(nc) # mAP per class results = (0, 0, 0, 0, 0, 0, 0) # P, R, mAP@.5, mAP@.5-.95, val_loss(box, obj, cls) scheduler.last_epoch = start_epoch - 1 # do not move scaler = torch.cuda.amp.GradScaler(enabled=amp) stopper, stop = EarlyStopping(patience=opt.patience), False compute_loss = ComputeLoss(model) # init loss class callbacks.run('on_train_start') LOGGER.info(f'Image sizes {imgsz} train, {imgsz} val\n' f'Using {train_loader.num_workers * WORLD_SIZE} dataloader workers\n' f"Logging results to {colorstr('bold', save_dir)}\n" f'Starting training for {epochs} epochs...') for epoch in range(start_epoch, epochs): # epoch ------------------------------------------------------------------ callbacks.run('on_train_epoch_start') model.train() # Update image weights (optional, single-GPU only) if opt.image_weights: cw = model.class_weights.cpu().numpy() * (1 - maps) ** 2 / nc # class weights iw = labels_to_image_weights(dataset.labels, nc=nc, class_weights=cw) # image weights dataset.indices = random.choices(range(dataset.n), weights=iw, k=dataset.n) # rand weighted idx # Update mosaic border (optional) # b = int(random.uniform(0.25 * imgsz, 0.75 * imgsz + gs) // gs * gs) # dataset.mosaic_border = [b - imgsz, -b] # height, width borders mloss = torch.zeros(3, device=device) # mean losses if RANK != -1: train_loader.sampler.set_epoch(epoch) pbar = enumerate(train_loader) LOGGER.info(('\n' + '%11s' * 7) % ('Epoch', 'GPU_mem', 'box_loss', 'obj_loss', 'cls_loss', 'Instances', 'Size')) if RANK in {-1, 0}: pbar = tqdm(pbar, total=nb, bar_format=TQDM_BAR_FORMAT) # progress bar optimizer.zero_grad() for i, (imgs, targets, paths, _) in pbar: # batch ------------------------------------------------------------- callbacks.run('on_train_batch_start') ni = i + nb * epoch # number integrated batches (since train start) imgs = imgs.to(device, non_blocking=True).float() / 255 # uint8 to float32, 0-255 to 0.0-1.0 # Warmup if ni <= nw: xi = [0, nw] # x interp # compute_loss.gr = np.interp(ni, xi, [0.0, 1.0]) # iou loss ratio (obj_loss = 1.0 or iou) accumulate = max(1, np.interp(ni, xi, [1, nbs / batch_size]).round()) for j, x in enumerate(optimizer.param_groups): # bias lr falls from 0.1 to lr0, all other lrs rise from 0.0 to lr0 x['lr'] = np.interp(ni, xi, [hyp['warmup_bias_lr'] if j == 0 else 0.0, x['initial_lr'] * lf(epoch)]) if 'momentum' in x: x['momentum'] = np.interp(ni, xi, [hyp['warmup_momentum'], hyp['momentum']]) # Multi-scale if opt.multi_scale: sz = random.randrange(imgsz * 0.5, imgsz * 1.5 + gs) // gs * gs # size sf = sz / max(imgs.shape[2:]) # scale factor if sf != 1: ns = [math.ceil(x * sf / gs) * gs for x in imgs.shape[2:]] # new shape (stretched to gs-multiple) imgs = nn.functional.interpolate(imgs, size=ns, mode='bilinear', align_corners=False) # Forward with torch.cuda.amp.autocast(amp): pred = model(imgs) # forward loss, loss_items = compute_loss(pred, targets.to(device)) # loss scaled by batch_size if RANK != -1: loss *= WORLD_SIZE # gradient averaged between devices in DDP mode if opt.quad: loss *= 4. # Backward scaler.scale(loss).backward() # Optimize - https://pytorch.org/docs/master/notes/amp_examples.html if ni - last_opt_step >= accumulate: scaler.unscale_(optimizer) # unscale gradients torch.nn.utils.clip_grad_norm_(model.parameters(), max_norm=10.0) # clip gradients scaler.step(optimizer) # optimizer.step scaler.update() optimizer.zero_grad() if ema: ema.update(model) last_opt_step = ni # Log if RANK in {-1, 0}: mloss = (mloss * i + loss_items) / (i + 1) # update mean losses mem = f'{torch.cuda.memory_reserved() / 1E9 if torch.cuda.is_available() else 0:.3g}G' # (GB) pbar.set_description(('%11s' * 2 + '%11.4g' * 5) % (f'{epoch}/{epochs - 1}', mem, *mloss, targets.shape[0], imgs.shape[-1])) callbacks.run('on_train_batch_end', model, ni, imgs, targets, paths, list(mloss)) if callbacks.stop_training: return # end batch ------------------------------------------------------------------------------------------------ # Scheduler lr = [x['lr'] for x in optimizer.param_groups] # for loggers scheduler.step() if RANK in {-1, 0}: # mAP callbacks.run('on_train_epoch_end', epoch=epoch) ema.update_attr(model, include=['yaml', 'nc', 'hyp', 'names', 'stride', 'class_weights']) final_epoch = (epoch + 1 == epochs) or stopper.possible_stop if not noval or final_epoch: # Calculate mAP results, maps, _ = validate.run(data_dict, batch_size=batch_size // WORLD_SIZE * 2, imgsz=imgsz, half=amp, model=ema.ema, single_cls=single_cls, dataloader=val_loader, save_dir=save_dir, plots=False, callbacks=callbacks, compute_loss=compute_loss) # Update best mAP fi = fitness(np.array(results).reshape(1, -1)) # weighted combination of [P, R, mAP@.5, mAP@.5-.95] stop = stopper(epoch=epoch, fitness=fi) # early stop check if fi > best_fitness: best_fitness = fi log_vals = list(mloss) + list(results) + lr callbacks.run('on_fit_epoch_end', log_vals, epoch, best_fitness, fi) # Save model if (not nosave) or (final_epoch and not evolve): # if save ckpt = { 'epoch': epoch, 'best_fitness': best_fitness, 'model': deepcopy(de_parallel(model)).half(), 'ema': deepcopy(ema.ema).half(), 'updates': ema.updates, 'optimizer': optimizer.state_dict(), 'opt': vars(opt), 'git': GIT_INFO, # {remote, branch, commit} if a git repo 'date': datetime.now().isoformat()} # Save last, best and delete torch.save(ckpt, last) if best_fitness == fi: torch.save(ckpt, best) if opt.save_period > 0 and epoch % opt.save_period == 0: torch.save(ckpt, w / f'epoch{epoch}.pt') del ckpt callbacks.run('on_model_save', last, epoch, final_epoch, best_fitness, fi) # EarlyStopping if RANK != -1: # if DDP training broadcast_list = [stop if RANK == 0 else None] dist.broadcast_object_list(broadcast_list, 0) # broadcast 'stop' to all ranks if RANK != 0: stop = broadcast_list[0] if stop: break # must break all DDP ranks # end epoch ---------------------------------------------------------------------------------------------------- # end training ----------------------------------------------------------------------------------------------------- if RANK in {-1, 0}: LOGGER.info(f'\n{epoch - start_epoch + 1} epochs completed in {(time.time() - t0) / 3600:.3f} hours.') for f in last, best: if f.exists(): strip_optimizer(f) # strip optimizers if f is best: LOGGER.info(f'\nValidating {f}...') results, _, _ = validate.run( data_dict, batch_size=batch_size // WORLD_SIZE * 2, imgsz=imgsz, model=attempt_load(f, device).half(), iou_thres=0.65 if is_coco else 0.60, # best pycocotools at iou 0.65 single_cls=single_cls, dataloader=val_loader, save_dir=save_dir, save_json=is_coco, verbose=True, plots=plots, callbacks=callbacks, compute_loss=compute_loss) # val best model with plots if is_coco: callbacks.run('on_fit_epoch_end', list(mloss) + list(results) + lr, epoch, best_fitness, fi) callbacks.run('on_train_end', last, best, epoch, results) torch.cuda.empty_cache() return resultsdef parse_opt(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=100, 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='image --cache ram/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')
# Logger arguments parser.add_argument('--entity', default=None, help='Entity') parser.add_argument('--upload_dataset', nargs='?', const=True, default=False, help='Upload data, "val" option') parser.add_argument('--bbox_interval', type=int, default=-1, help='Set bounding-box image logging interval') parser.add_argument('--artifact_alias', type=str, default='latest', help='Version of dataset artifact to use') return parser.parse_known_args()[0] if known else parser.parse_args()def main(opt, callbacks=Callbacks()): # Checks if RANK in {-1, 0}: print_args(vars(opt)) check_git_status() check_requirements()
# Resume (from specified or most recent last.pt) if opt.resume and not check_comet_resume(opt) and not opt.evolve: last = Path(check_file(opt.resume) if isinstance(opt.resume, str) else get_latest_run()) opt_yaml = last.parent.parent / 'opt.yaml' # train options yaml opt_data = opt.data # original dataset if opt_yaml.is_file(): with open(opt_yaml, errors='ignore') as f: d = yaml.safe_load(f) else: d = torch.load(last, map_location='cpu')['opt'] opt = argparse.Namespace(**d) # replace opt.cfg, opt.weights, opt.resume = '', str(last), True # reinstate if is_url(opt_data): opt.data = check_file(opt_data) # avoid HUB resume auth timeout 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 if opt.name == 'cfg': opt.name = Path(opt.cfg).stem # use model.yaml as name 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) # 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 if opt.noautoanchor: del hyp['anchors'], meta['anchors'] 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 {evolve_csv}') # 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 keys = ('metrics/precision', 'metrics/recall', 'metrics/mAP_0.5', 'metrics/mAP_0.5:0.95', 'val/box_loss', 'val/obj_loss', 'val/cls_loss') print_mutation(keys, 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}')def run(**kwargs): # Usage: import train; train.run(data='coco128.yaml', imgsz=320, weights='yolov5m.pt') opt = parse_opt(True) for k, v in kwargs.items(): setattr(opt, k, v) main(opt) return opt
if name == "main": try: opt = parse_opt(True) main(opt) except Exception as error: traceback.print_exception(error) os.system("pause")
- Assistant
The script you provided appears to be the training script for the YOLOv5 (You Only Look Once version 5) object detection model, developed by Ultralytics. It allows users to train a custom YOLOv5 model on their datasets or use predefined datasets like COCO. Here is a high-level breakdown of its functionalities and key components:
Key Components of the Script
-
Argument Parsing:
- The script utilizes
argparseto handle command-line arguments, allowing users to specify various configuration options like weights path, data configuration, hyperparameters, training epochs, batch sizes, and more.
- The script utilizes
-
Training Function:
- The
trainfunction implements the training loop. It takes hyperparameters, command-line options, device specifications (CPU/GPU), and callbacks as inputs. - It initializes directories for saving weights, sets up the model, and checks the dataset's integrity.
- The training process includes model forward and backward passes, loss calculation, optimization steps, and validation.
- The
-
Model Configuration:
- Models can be either loaded from pre-trained weights or trained from scratch based on user input.
- The script supports multi-GPU training using Distributed Data Parallel (DDP) and can also run on a single GPU.
-
Hyperparameter Management:
- Users can specify hyperparameters through a YAML file, and there is also support for automatic hyperparameter evolution.
-
Logging:
- The script incorporates logging functionality to keep track of training progress, which can be helpful for analyzing performance metrics.
-
Callbacks:
- The script allows for callbacks (functions that can be called at certain points during training), which can be used for logging, early stopping, and other functionalities.
-
Data Handling:
- Functions to create data loaders for both training and validation datasets, which support various configurations like image augmentation and mosaic training for better data diversity.
-
Validation:
- At the end of each epoch, the trained model can be validated on a separate validation dataset to evaluate its performance, with metrics like Precision, Recall, and mAP (mean Average Precision) reported.
-
Error Handling:
- The script has error handling to catch unexpected issues during execution.
Usage Examples
The script can be run from the command line with several options, such as:
-
Training with Pre-trained Weights:
python train.py --data coco128.yaml --weights yolov5s.pt --img 640 -
Training from Scratch:
python train.py --data coco128.yaml --weights '' --cfg yolov5s.yaml --img 640 -
Multi-GPU Training:
python -m torch.distributed.run --nproc_per_node 4 train.py --data coco128.yaml --weights yolov5s.pt --img 640 --device 0,1,2,3
Conclusion
This script is a comprehensive training program for YOLOv5, designed to be flexible for various training configurations and user requirements. The modular structure allows users to adapt the training process to specific datasets and training requirements. If you need further explanation on a specific part of the script or how to use it, feel free to ask!
-
- User
51/99 0G 0.03786 0.04469 0.006686 248 640: 75%|███████▌ | 6/8 00:58d:\yolo\yolov5-7.0\train.py:309: FutureWarning:
t orch.cuda.amp.autocast(args...)is deprecated. Please usetorch.amp.autocast('cuda', args...)instead. with torch.cuda.amp.autocast(amp): - Assistant
The warning message you're seeing indicates that the way Amphrock's automatic mixed precision (AMP) is being used in your training script is outdated. The
torch.cuda.amp.autocast()function is deprecated, and you should now usetorch.amp.autocast()instead.Here's how you can update the relevant part of your code to avoid receiving this warning in the future:
Updated Code Snippet
Replace:
with torch.cuda.amp.autocast(amp):With:
with torch.amp.autocast(amp):Explanation
- Context Manager: The
autocast()function allows PyTorch to automatically choose whether to use 16-bit floating point (half precision) or 32-bit floating point (single precision) for your model's computations, which can improve performance while maintaining numerical accuracy during training. - Update Requirement: The function name change is part of PyTorch's ongoing improvements and updates. To ensure compatibility with future versions of PyTorch, it's always good to consult the official PyTorch documentation to keep your code up-to-date.
Recommended Steps
- Apply the change in your script wherever the warning occurs.
- Test the updated code to ensure that your model trains as expected without any compatibility issues.
- Keep your PyTorch library up to date to incorporate the latest features and performance optimizations.
By making this change, you should eliminate the FutureWarning and ensure that your code uses the most current API for mixed precision training.
- Context Manager: The
- User
中文回答
- Assistant
这个警告信息说明你在训练脚本中使用的自动混合精度(AMP)的方法已经过时。
torch.cuda.amp.autocast()函数已被弃用,建议使用torch.amp.autocast()。更新代码示例
将以下代码:
with torch.cuda.amp.autocast(amp):替换为:
with torch.amp.autocast(amp):解释
- 上下文管理器:
autocast()函数允许 PyTorch 自动选择使用 16 位浮点数(半精度)或 32 位浮点数(单精度)进行模型计算,这可以在保持数值精度的同时提高性能。 - 更新要求:函数名的变更是 PyTorch 持续改进和更新的一部分。为了确保代码与未来版本的 PyTorch 兼容,建议查看 PyTorch 的官方文档,保持代码更新。
推荐步骤
- 在你的脚本中应用改动,替换出现警告的地方。
- 测试更新后的代码,确保模型正常训练,没有兼容性问题。
- 保持你的 PyTorch 库更新,以便利用最新的功能和性能优化。
通过做出这个修改,你应该能够消除 FutureWarning,并确保代码使用最新的混合精度训练 API。
- 上下文管理器: