def pre_load(self): #container for data self.files = [] for index, kind in enumerate(self.kind): current_path = os.path.join(self.data_path, kind) for data in os.listdir(current_path): if data.endswith('.jpg'): self.files.append({ 'img_path': os.path.join(current_path, data), 'label': index })
def train(hyp, # path/to/hyp.yaml or hyp dictionary opt, device, ): save_dir, epochs, batch_size, weights, single_cls, evolve, data, cfg, resume, notest, nosave, workers, = \ opt.save_dir, opt.epochs, opt.batch_size, opt.weights, opt.single_cls, opt.evolve, opt.data, opt.cfg, \ opt.resume, opt.notest, opt.nosave, opt.workers # Directories save_dir = Path(save_dir) wdir = save_dir / 'weights' wdir.mkdir(parents=True, exist_ok=True) # make dir last = wdir / 'last.pt' best = wdir / 'best.pt' results_file = save_dir / 'results.txt' # Hyperparameters if isinstance(hyp, str): with open(hyp) as f: hyp = yaml.safe_load(f) # load hyps dict logger.info(colorstr('hyperparameters: ') + ', '.join(f'{k}={v}' for k, v in hyp.items())) # Save run settings with open(save_dir / 'hyp.yaml', 'w') as f: yaml.safe_dump(hyp, f, sort_keys=False) with open(save_dir / 'opt.yaml', 'w') as f: yaml.safe_dump(vars(opt), f, sort_keys=False) # Configure plots = not evolve # create plots cuda = device.type != 'cpu' init_seeds(2 + RANK) with open(data) as f: data_dict = yaml.safe_load(f) # data dict # Loggers loggers = {'wandb': None, 'tb': None} # loggers dict if RANK in [-1, 0]: # TensorBoard if not evolve: prefix = colorstr('tensorboard: ') logger.info(f"{prefix}Start with 'tensorboard --logdir {opt.project}', view at http://localhost:6006/") loggers['tb'] = SummaryWriter(str(save_dir)) # W&B opt.hyp = hyp # add hyperparameters run_id = torch.load(weights).get('wandb_id') if weights.endswith('.pt') and os.path.isfile(weights) else None run_id = run_id if opt.resume else None # start fresh run if transfer learning wandb_logger = WandbLogger(opt, save_dir.stem, run_id, data_dict) loggers['wandb'] = wandb_logger.wandb if loggers['wandb']: data_dict = wandb_logger.data_dict weights, epochs, hyp = opt.weights, opt.epochs, opt.hyp # may update weights, epochs if resuming nc = 1 if single_cls else int(data_dict['nc']) # number of classes names = ['item'] if single_cls and len(data_dict['names']) != 1 else data_dict['names'] # class names assert len(names) == nc, '%g names found for nc=%g dataset in %s' % (len(names), nc, data) # check is_coco = data.endswith('coco.yaml') and nc == 80 # COCO dataset # Model pretrained = weights.endswith('.pt') if pretrained: with torch_distributed_zero_first(RANK): weights = attempt_download(weights) # download if not found locally ckpt = torch.load(weights, map_location=device) # load checkpoint 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 state_dict = ckpt['model'].float().state_dict() # to FP32 state_dict = intersect_dicts(state_dict, model.state_dict(), exclude=exclude) # intersect model.load_state_dict(state_dict, strict=False) # load logger.info('Transferred %g/%g items from %s' % (len(state_dict), len(model.state_dict()), weights)) # report else: model = Model(cfg, ch=3, nc=nc, anchors=hyp.get('anchors')).to(device) # create with torch_distributed_zero_first(RANK): check_dataset(data_dict) # check train_path = data_dict['train'] test_path = data_dict['val'] # Freeze freeze = [] # parameter names to freeze (full or partial) for k, v in model.named_parameters(): v.requires_grad = True # train all layers if any(x in k for x in freeze): print('freezing %s' % k) v.requires_grad = False # 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 logger.info(f"Scaled weight_decay = {hyp['weight_decay']}") pg0, pg1, pg2 = [], [], [] # optimizer parameter groups for k, v in model.named_modules(): if hasattr(v, 'bias') and isinstance(v.bias, nn.Parameter): pg2.append(v.bias) # biases if isinstance(v, nn.BatchNorm2d): pg0.append(v.weight) # no decay elif hasattr(v, 'weight') and isinstance(v.weight, nn.Parameter): pg1.append(v.weight) # apply decay if opt.adam: optimizer = optim.Adam(pg0, lr=hyp['lr0'], betas=(hyp['momentum'], 0.999)) # adjust beta1 to momentum else: optimizer = optim.SGD(pg0, lr=hyp['lr0'], momentum=hyp['momentum'], nesterov=True) optimizer.add_param_group({'params': pg1, 'weight_decay': hyp['weight_decay']}) # add pg1 with weight_decay optimizer.add_param_group({'params': pg2}) # add pg2 (biases) logger.info('Optimizer groups: %g .bias, %g conv.weight, %g other' % (len(pg2), len(pg1), len(pg0))) del pg0, pg1, pg2 # Scheduler https://arxiv.org/pdf/1812.01187.pdf # https://pytorch.org/docs/stable/_modules/torch/optim/lr_scheduler.html#OneCycleLR if opt.linear_lr: lf = lambda x: (1 - x / (epochs - 1)) * (1.0 - hyp['lrf']) + hyp['lrf'] # linear else: lf = one_cycle(1, hyp['lrf'], epochs) # cosine 1->hyp['lrf'] 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 start_epoch, best_fitness = 0, 0.0 if pretrained: # Optimizer if ckpt['optimizer'] is not None: optimizer.load_state_dict(ckpt['optimizer']) best_fitness = ckpt['best_fitness'] # EMA if ema and ckpt.get('ema'): ema.ema.load_state_dict(ckpt['ema'].float().state_dict()) ema.updates = ckpt['updates'] # Results if ckpt.get('training_results') is not None: results_file.write_text(ckpt['training_results']) # write results.txt # Epochs start_epoch = ckpt['epoch'] + 1 if resume: assert start_epoch > 0, '%s training to %g epochs is finished, nothing to resume.' % (weights, epochs) if epochs < start_epoch: logger.info('%s has been trained for %g epochs. Fine-tuning for %g additional epochs.' % (weights, ckpt['epoch'], epochs)) epochs += ckpt['epoch'] # finetune additional epochs del ckpt, state_dict # Image sizes gs = max(int(model.stride.max()), 32) # grid size (max stride) nl = model.model[-1].nl # number of detection layers (used for scaling hyp['obj']) imgsz, imgsz_test = [check_img_size(x, gs) for x in opt.img_size] # verify imgsz are gs-multiples # DP mode if cuda and RANK == -1 and torch.cuda.device_count() > 1: logging.warning('DP not recommended, instead 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 dataloader, dataset = create_dataloader(train_path, imgsz, batch_size // WORLD_SIZE, gs, single_cls, hyp=hyp, augment=True, cache=opt.cache_images, rect=opt.rect, rank=RANK, workers=workers, image_weights=opt.image_weights, quad=opt.quad, prefix=colorstr('train: ')) mlc = np.concatenate(dataset.labels, 0)[:, 0].max() # max label class nb = len(dataloader) # number of batches assert mlc < nc, 'Label class %g exceeds nc=%g in %s. Possible class labels are 0-%g' % (mlc, nc, data, nc - 1) # Process 0 if RANK in [-1, 0]: testloader = create_dataloader(test_path, imgsz_test, batch_size // WORLD_SIZE * 2, gs, single_cls, hyp=hyp, cache=opt.cache_images and not notest, rect=True, rank=-1, workers=workers, pad=0.5, prefix=colorstr('val: '))[0] if not resume: labels = np.concatenate(dataset.labels, 0) c = torch.tensor(labels[:, 0]) # classes # cf = torch.bincount(c.long(), minlength=nc) + 1. # frequency # model._initialize_biases(cf.to(device)) if plots: plot_labels(labels, names, save_dir, loggers) if loggers['tb']: loggers['tb'].add_histogram('classes', c, 0) # TensorBoard # Anchors if not opt.noautoanchor: check_anchors(dataset, model=model, thr=hyp['anchor_t'], imgsz=imgsz) model.half().float() # pre-reduce anchor precision # DDP mode if cuda and RANK != -1: model = DDP(model, device_ids=[LOCAL_RANK], output_device=LOCAL_RANK) # Model parameters 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.gr = 1.0 # iou loss ratio (obj_loss = 1.0 or iou) model.class_weights = labels_to_class_weights(dataset.labels, nc).to(device) * nc # attach class weights model.names = names # Start training t0 = time.time() nw = max(round(hyp['warmup_epochs'] * nb), 1000) # number of warmup iterations, max(3 epochs, 1k iterations) # nw = min(nw, (epochs - start_epoch) / 2 * nb) # limit warmup to < 1/2 of training maps = np.zeros(nc) # mAP per class results = (0, 0, 0, 0, 0, 0, 0) # P, R, [email protected], [email protected], val_loss(box, obj, cls) scheduler.last_epoch = start_epoch - 1 # do not move scaler = amp.GradScaler(enabled=cuda) compute_loss = ComputeLoss(model) # init loss class logger.info(f'Image sizes {imgsz} train, {imgsz_test} test\n' f'Using {dataloader.num_workers} dataloader workers\n' f'Logging results to {save_dir}\n' f'Starting training for {epochs} epochs...') for epoch in range(start_epoch, epochs): # epoch ------------------------------------------------------------------ model.train() # Update image weights (optional) if opt.image_weights: # Generate indices if RANK in [-1, 0]: 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 # Broadcast if DDP if RANK != -1: indices = (torch.tensor(dataset.indices) if RANK == 0 else torch.zeros(dataset.n)).int() dist.broadcast(indices, 0) if RANK != 0: dataset.indices = indices.cpu().numpy() # Update mosaic border # 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(4, device=device) # mean losses if RANK != -1: dataloader.sampler.set_epoch(epoch) pbar = enumerate(dataloader) logger.info(('\n' + '%10s' * 8) % ('Epoch', 'gpu_mem', 'box', 'obj', 'cls', 'total', 'labels', 'img_size')) if RANK in [-1, 0]: pbar = tqdm(pbar, total=nb) # progress bar optimizer.zero_grad() for i, (imgs, targets, paths, _) in pbar: # batch ------------------------------------------------------------- ni = i + nb * epoch # number integrated batches (since train start) imgs = imgs.to(device, non_blocking=True).float() / 255.0 # uint8 to float32, 0-255 to 0.0-1.0 # Warmup if ni <= nw: xi = [0, nw] # x interp # model.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 == 2 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 = F.interpolate(imgs, size=ns, mode='bilinear', align_corners=False) # Forward with amp.autocast(enabled=cuda): 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 if ni % accumulate == 0: scaler.step(optimizer) # optimizer.step scaler.update() optimizer.zero_grad() if ema: ema.update(model) # Print if RANK in [-1, 0]: mloss = (mloss * i + loss_items) / (i + 1) # update mean losses mem = '%.3gG' % (torch.cuda.memory_reserved() / 1E9 if torch.cuda.is_available() else 0) # (GB) s = ('%10s' * 2 + '%10.4g' * 6) % ( f'{epoch}/{epochs - 1}', mem, *mloss, targets.shape[0], imgs.shape[-1]) pbar.set_description(s) # Plot if plots and ni < 3: f = save_dir / f'train_batch{ni}.jpg' # filename Thread(target=plot_images, args=(imgs, targets, paths, f), daemon=True).start() if loggers['tb'] and ni == 0: # TensorBoard with warnings.catch_warnings(): warnings.simplefilter('ignore') # suppress jit trace warning loggers['tb'].add_graph(torch.jit.trace(de_parallel(model), imgs[0:1], strict=False), []) elif plots and ni == 10 and loggers['wandb']: wandb_logger.log({'Mosaics': [loggers['wandb'].Image(str(x), caption=x.name) for x in save_dir.glob('train*.jpg') if x.exists()]}) # end batch ------------------------------------------------------------------------------------------------ # Scheduler lr = [x['lr'] for x in optimizer.param_groups] # for loggers scheduler.step() # DDP process 0 or single-GPU if RANK in [-1, 0]: # mAP ema.update_attr(model, include=['yaml', 'nc', 'hyp', 'gr', 'names', 'stride', 'class_weights']) final_epoch = epoch + 1 == epochs if not notest or final_epoch: # Calculate mAP wandb_logger.current_epoch = epoch + 1 results, maps, _ = test.run(data_dict, batch_size=batch_size // WORLD_SIZE * 2, imgsz=imgsz_test, model=ema.ema, single_cls=single_cls, dataloader=testloader, save_dir=save_dir, save_json=is_coco and final_epoch, verbose=nc < 50 and final_epoch, plots=plots and final_epoch, wandb_logger=wandb_logger, compute_loss=compute_loss) # Write with open(results_file, 'a') as f: f.write(s + '%10.4g' * 7 % results + '\n') # append metrics, val_loss # Log tags = ['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', 'val/box_loss', 'val/obj_loss', 'val/cls_loss', # val loss 'x/lr0', 'x/lr1', 'x/lr2'] # params for x, tag in zip(list(mloss[:-1]) + list(results) + lr, tags): if loggers['tb']: loggers['tb'].add_scalar(tag, x, epoch) # TensorBoard if loggers['wandb']: wandb_logger.log({tag: x}) # W&B # Update best mAP fi = fitness(np.array(results).reshape(1, -1)) # weighted combination of [P, R, [email protected], [email protected]] if fi > best_fitness: best_fitness = fi wandb_logger.end_epoch(best_result=best_fitness == fi) # Save model if (not nosave) or (final_epoch and not evolve): # if save ckpt = {'epoch': epoch, 'best_fitness': best_fitness, 'training_results': results_file.read_text(), 'model': deepcopy(de_parallel(model)).half(), 'ema': deepcopy(ema.ema).half(), 'updates': ema.updates, 'optimizer': optimizer.state_dict(), 'wandb_id': wandb_logger.wandb_run.id if loggers['wandb'] else None} # Save last, best and delete torch.save(ckpt, last) if best_fitness == fi: torch.save(ckpt, best) if loggers['wandb']: if ((epoch + 1) % opt.save_period == 0 and not final_epoch) and opt.save_period != -1: wandb_logger.log_model(last.parent, opt, epoch, fi, best_model=best_fitness == fi) del ckpt # end epoch ---------------------------------------------------------------------------------------------------- # end training ----------------------------------------------------------------------------------------------------- if RANK in [-1, 0]: logger.info(f'{epoch - start_epoch + 1} epochs completed in {(time.time() - t0) / 3600:.3f} hours.\n') if plots: plot_results(save_dir=save_dir) # save as results.png if loggers['wandb']: files = ['results.png', 'confusion_matrix.png', *[f'{x}_curve.png' for x in ('F1', 'PR', 'P', 'R')]] wandb_logger.log({"Results": [loggers['wandb'].Image(str(save_dir / f), caption=f) for f in files if (save_dir / f).exists()]}) if not evolve: if is_coco: # COCO dataset for m in [last, best] if best.exists() else [last]: # speed, mAP tests results, _, _ = test.run(data_dict, batch_size=batch_size // WORLD_SIZE * 2, imgsz=imgsz_test, conf_thres=0.001, iou_thres=0.7, model=attempt_load(m, device).half(), single_cls=single_cls, dataloader=testloader, save_dir=save_dir, save_json=True, plots=False) # Strip optimizers for f in last, best: if f.exists(): strip_optimizer(f) # strip optimizers if loggers['wandb']: # Log the stripped model loggers['wandb'].log_artifact(str(best if best.exists() else last), type='model', name='run_' + wandb_logger.wandb_run.id + '_model', aliases=['latest', 'best', 'stripped']) wandb_logger.finish_run() torch.cuda.empty_cache() return results