yolov5 代码部分-2

def train(hyp,  # path/to/hyp.yaml or hyp dictionary
          opt,
          device,
          callbacks=Callbacks()
          ):
    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
------------------------------------------------------------------------------------------------
							传入参数，callbacks（回调函数，我目前用不到）
------------------------------------------------------------------------------------------------

    # 保存路径
    w = save_dir / 'weights'  # weights dir
    w.mkdir(parents=True, exist_ok=True)  # make dir
    last, best = w / 'last.pt', w / 'best.pt'
------------------------------------------------------------------------------------------------
										save root
------------------------------------------------------------------------------------------------
    # 读预存超参数
    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()))
------------------------------------------------------------------------------------------------
									用某颜色输出超参数
------------------------------------------------------------------------------------------------
    # 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)
    data_dict = None
------------------------------------------------------------------------------------------------
										保存hyp\opt
------------------------------------------------------------------------------------------------
    # Loggers
    if RANK in [-1, 0]:
        loggers = Loggers(save_dir, weights, opt, hyp, LOGGER)  # loggers instance
        if loggers.wandb:
            data_dict = loggers.wandb.data_dict
            if resume:
                weights, epochs, hyp = opt.weights, opt.epochs, opt.hyp

        # Register actions
        for k in methods(loggers):
            callbacks.register_action(k, callback=getattr(loggers, k))
------------------------------------------------------------------------------------------------
											没研究
------------------------------------------------------------------------------------------------
    # Config
    plots = not evolve  # create plots
    cuda = device.type != 'cpu'
    init_seeds(1 + RANK)
    with torch_distributed_zero_first(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 = ['item'] if single_cls and len(data_dict['names']) != 1 else data_dict['names']  # class names
    assert len(names) == nc, f'{len(names)} names found for nc={nc} dataset in {data}'  # check
    is_coco = data.endswith('coco.yaml') and nc == 80  # COCO dataset
------------------------------------------------------------------------------------------------
										多线程check数据
------------------------------------------------------------------------------------------------
    # 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
        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
------------------------------------------------------------------------------------------------
											加载model
------------------------------------------------------------------------------------------------

    # Freeze
    freeze = [f'model.{x}.' for x in range(freeze)]  # layers to freeze
    for k, v in model.named_parameters():
        v.requires_grad = True  # train all layers
        if any(x in k for x in freeze):
            print(f'freezing {k}')
            v.requires_grad = False
------------------------------------------------------------------------------------------------
											freeze
------------------------------------------------------------------------------------------------
    # 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']}")

    g0, g1, g2 = [], [], []  # optimizer parameter groups
    for v in model.modules():
        if hasattr(v, 'bias') and isinstance(v.bias, nn.Parameter):  # bias
            g2.append(v.bias)
        if isinstance(v, nn.BatchNorm2d):  # weight (no decay)
            g0.append(v.weight)
        elif hasattr(v, 'weight') and isinstance(v.weight, nn.Parameter):  # weight (with decay)
            g1.append(v.weight)
    if opt.adam:
        optimizer = Adam(g0, lr=hyp['lr0'], betas=(hyp['momentum'], 0.999))  # adjust beta1 to momentum
    else:
        optimizer = SGD(g0, lr=hyp['lr0'], momentum=hyp['momentum'], nesterov=True)

    optimizer.add_param_group({'params': g1, 'weight_decay': hyp['weight_decay']})  # add g1 with weight_decay
    optimizer.add_param_group({'params': g2})  # add g2 (biases)
    LOGGER.info(f"{colorstr('optimizer:')} {type(optimizer).__name__} with parameter groups "
                f"{len(g0)} weight, {len(g1)} weight (no decay), {len(g2)} bias")
    del g0, g1, g2
------------------------------------------------------------------------------------------------
											Optimizer
------------------------------------------------------------------------------------------------
    # Scheduler
    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)
------------------------------------------------------------------------------------------------
											Scheduler
------------------------------------------------------------------------------------------------
    # EMA
    ema = ModelEMA(model) if RANK in [-1, 0] else None
    # Resume
    start_epoch, best_fitness = 0, 0.0
    if pretrained:
        if opt.change_nc:
        # EMA
            ckpt['new_ema'] = []
            for emaa in ckpt['ema'].state_dict():
                ckpt['new_ema'].append(emaa)
            new_weights = []
            for k,v in ckpt['ema'].float().state_dict().items():
                if k.startswith('model.24.m.0.weight'):
                    new_v = torch.rand([27, 128, 1, 1])
                    new_weights.append(new_v)
                elif k.startswith('model.24.m.1.weight'):
                    new_v = torch.rand([27, 256, 1, 1])
                    new_weights.append(new_v)
                elif k.startswith('model.24.m.2.weight'):
                    new_v = torch.rand([27, 512, 1, 1])
                    new_weights.append(new_v)
                elif k.startswith('model.24.m'):
                    new_v = torch.rand([27])
                    new_weights.append(new_v)
                else:
                    new_weights.append(v)

            ckpt['my_weight'] = dict(zip(ckpt['new_ema'], new_weights))


            if ema and ckpt.get('ema'):
                ema.ema.load_state_dict(ckpt['my_weight'])
                # ema.ema.load_state_dict(ckpt['ema'].float().state_dict())
                ema.updates = ckpt['updates']
                # ema.state_dict().update(ckpt['my_weight'])
------------------------------------------------------------------------------------------------
								读参数，我这里想换一下输出层的维度
------------------------------------------------------------------------------------------------
        else:
            if ckpt['optimizer'] is not None:
                optimizer.load_state_dict(ckpt['optimizer'])
                best_fitness = ckpt['best_fitness']
            if ema and ckpt.get('ema'):
                ema.ema.load_state_dict(ckpt['ema'].float().state_dict())
                ema.updates = ckpt['updates']
------------------------------------------------------------------------------------------------
											原本的
------------------------------------------------------------------------------------------------
        # Epochs
        if opt.restart:
            start_epoch = 0
        else:
            start_epoch = ckpt['epoch'] + 1
        if resume:
            assert start_epoch > 0, f'{weights} training to {epochs} epochs is finished, nothing to resume.'
        if epochs < start_epoch:
            LOGGER.info(f"{weights} has been trained for {ckpt['epoch']} epochs. Fine-tuning for {epochs} more epochs.")
            epochs += ckpt['epoch']  # finetune additional epochs

        del ckpt, csd
------------------------------------------------------------------------------------------------
											Epochs
------------------------------------------------------------------------------------------------
    # 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 = check_img_size(opt.imgsz, gs, floor=gs * 2)  # verify imgsz is gs-multiple

    # 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
    train_loader, dataset = create_dataloader(train_path, imgsz, batch_size // WORLD_SIZE, gs, single_cls,
                                              hyp=hyp, augment=True, cache=opt.cache, rect=opt.rect, rank=RANK,
                                              workers=workers, image_weights=opt.image_weights, quad=opt.quad,
                                              prefix=colorstr('train: '))
    mlc = int(np.concatenate(dataset.labels, 0)[:, 0].max())  # max label class
    nb = len(train_loader)  # number of batches
    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, 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)

            # Anchors
            if not opt.noautoanchor:
                check_anchors(dataset, model=model, thr=hyp['anchor_t'], imgsz=imgsz)
            model.half().float()  # pre-reduce anchor precision

        callbacks.on_pretrain_routine_end()

    # 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.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
    last_opt_step = -1
    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} val\n'
                f'Using {train_loader.num_workers} dataloader workers\n'
                f'Logging results to {save_dir}\n'
                f'Starting training for {epochs} epochs...')
------------------------------------------------------------------------------------------------
							imgsz dataloader workers save_dir epochs
------------------------------------------------------------------------------------------------     

    for epoch in range(start_epoch, epochs):  			------------ start_epoch->epochs
        model.train()									------------ model.train()
        if opt.image_weights:							------------ 是否用加权图片
            if RANK in [-1, 0]:							------------ rank = -1
                cw = model.class_weights.cpu().numpy() * (1 - maps) ** 2 / nc  # class weights
                										------------ 按照class_weight机制得到cw
                iw = labels_to_image_weights(dataset.labels, nc=nc, class_weights=cw)  # image weights
                										------------ 按照class_weight机制得到iw
                dataset.indices = random.choices(range(dataset.n), weights=iw, k=dataset.n)  # rand weighted idx
                										------------ 按照iw来生成indices
                										
*************************************************************************************************
            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						*
        									 用不上												*
*************************************************************************************************
        mloss = torch.zeros(3, device=device) 			------------ 初始化均值
*************************************************************************************************
        if RANK != -1:																			*
            train_loader.sampler.set_epoch(epoch)												*
*************************************************************************************************
        pbar = enumerate(train_loader)					------------ train_loader放进pbar										
        LOGGER.info(('\n' + '%10s' * 7) % ('Epoch', 'gpu_mem', 'box', 'obj', 'cls', 'labels', 'img_size'))
        if RANK in [-1, 0]:								------------ rank = -1								
            pbar = tqdm(pbar, total=nb)  				------------ pbar放进tqdm										
        optimizer.zero_grad()							------------ 初始化optim
        for i, (imgs, targets, paths, _) in pbar:  		------------ batch
            ni = i + nb * epoch  						------------ 当前batchnum
            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
                # 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 == 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 = nn.functional.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 - last_opt_step >= accumulate:
                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(('%10s' * 2 + '%10.4g' * 5) % (
                    f'{epoch}/{epochs - 1}', mem, *mloss, targets.shape[0], imgs.shape[-1]))
                callbacks.on_train_batch_end(ni, model, imgs, targets, paths, plots)
            # end batch ------------------------------------------------------------------------------------------------

        # Scheduler
        lr = [x['lr'] for x in optimizer.param_groups]  # for loggers
        scheduler.step()

        if RANK in [-1, 0]:
            # mAP
            callbacks.on_train_epoch_end(epoch=epoch)
            ema.update_attr(model, include=['yaml', 'nc', 'hyp', 'names', 'stride', 'class_weights'])
            final_epoch = epoch + 1 == epochs
            if not noval or final_epoch:  # Calculate mAP
                results, maps, _ = val.run(data_dict,
                                           batch_size=batch_size // WORLD_SIZE * 2,
                                           imgsz=imgsz,
                                           model=ema.ema,
                                           single_cls=single_cls,
                                           dataloader=val_loader,
                                           save_dir=save_dir,
                                           save_json=is_coco and final_epoch,
                                           verbose=nc < 50 and final_epoch,
                                           plots=plots and final_epoch,
                                           callbacks=callbacks,
                                           compute_loss=compute_loss)

            # 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
            log_vals = list(mloss) + list(results) + lr
            callbacks.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(),
                        'wandb_id': loggers.wandb.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)
                del ckpt
                callbacks.on_model_save(last, epoch, final_epoch, best_fitness, fi)

        # 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.')
        if not evolve:
            if is_coco:  # COCO dataset
                for m in [last, best] if best.exists() else [last]:  # speed, mAP tests
                    results, _, _ = val.run(data_dict,
                                            batch_size=batch_size // WORLD_SIZE * 2,
                                            imgsz=imgsz,
                                            model=attempt_load(m, device).half(),
                                            iou_thres=0.7,  # NMS IoU threshold for best pycocotools results
                                            single_cls=single_cls,
                                            dataloader=val_loader,
                                            save_dir=save_dir,
                                            save_json=True,
                                            plots=False)
            # Strip optimizers
            for f in last, best:
                if f.exists():
                    strip_optimizer(f)  # strip optimizers
        callbacks.on_train_end(last, best, plots, epoch)
        LOGGER.info(f"Results saved to {colorstr('bold', save_dir)}")

    torch.cuda.empty_cache()
    return results