main_deepclusterv2.py [129:175]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
    )
    sampler = torch.utils.data.distributed.DistributedSampler(train_dataset)
    train_loader = torch.utils.data.DataLoader(
        train_dataset,
        sampler=sampler,
        batch_size=args.batch_size,
        num_workers=args.workers,
        pin_memory=True,
        drop_last=True
    )
    logger.info("Building data done with {} images loaded.".format(len(train_dataset)))

    # build model
    model = resnet_models.__dict__[args.arch](
        normalize=True,
        hidden_mlp=args.hidden_mlp,
        output_dim=args.feat_dim,
        nmb_prototypes=args.nmb_prototypes,
    )
    # synchronize batch norm layers
    if args.sync_bn == "pytorch":
        model = nn.SyncBatchNorm.convert_sync_batchnorm(model)
    elif args.sync_bn == "apex":
        # with apex syncbn we sync bn per group because it speeds up computation
        # compared to global syncbn
        process_group = apex.parallel.create_syncbn_process_group(args.syncbn_process_group_size)
        model = apex.parallel.convert_syncbn_model(model, process_group=process_group)
    # copy model to GPU
    model = model.cuda()
    if args.rank == 0:
        logger.info(model)
    logger.info("Building model done.")

    # build optimizer
    optimizer = torch.optim.SGD(
        model.parameters(),
        lr=args.base_lr,
        momentum=0.9,
        weight_decay=args.wd,
    )
    optimizer = LARC(optimizer=optimizer, trust_coefficient=0.001, clip=False)
    warmup_lr_schedule = np.linspace(args.start_warmup, args.base_lr, len(train_loader) * args.warmup_epochs)
    iters = np.arange(len(train_loader) * (args.epochs - args.warmup_epochs))
    cosine_lr_schedule = np.array([args.final_lr + 0.5 * (args.base_lr - args.final_lr) * (1 + \
                         math.cos(math.pi * t / (len(train_loader) * (args.epochs - args.warmup_epochs)))) for t in iters])
    lr_schedule = np.concatenate((warmup_lr_schedule, cosine_lr_schedule))
    logger.info("Building optimizer done.")
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -



main_swav.py [137:183]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
    )
    sampler = torch.utils.data.distributed.DistributedSampler(train_dataset)
    train_loader = torch.utils.data.DataLoader(
        train_dataset,
        sampler=sampler,
        batch_size=args.batch_size,
        num_workers=args.workers,
        pin_memory=True,
        drop_last=True
    )
    logger.info("Building data done with {} images loaded.".format(len(train_dataset)))

    # build model
    model = resnet_models.__dict__[args.arch](
        normalize=True,
        hidden_mlp=args.hidden_mlp,
        output_dim=args.feat_dim,
        nmb_prototypes=args.nmb_prototypes,
    )
    # synchronize batch norm layers
    if args.sync_bn == "pytorch":
        model = nn.SyncBatchNorm.convert_sync_batchnorm(model)
    elif args.sync_bn == "apex":
        # with apex syncbn we sync bn per group because it speeds up computation
        # compared to global syncbn
        process_group = apex.parallel.create_syncbn_process_group(args.syncbn_process_group_size)
        model = apex.parallel.convert_syncbn_model(model, process_group=process_group)
    # copy model to GPU
    model = model.cuda()
    if args.rank == 0:
        logger.info(model)
    logger.info("Building model done.")

    # build optimizer
    optimizer = torch.optim.SGD(
        model.parameters(),
        lr=args.base_lr,
        momentum=0.9,
        weight_decay=args.wd,
    )
    optimizer = LARC(optimizer=optimizer, trust_coefficient=0.001, clip=False)
    warmup_lr_schedule = np.linspace(args.start_warmup, args.base_lr, len(train_loader) * args.warmup_epochs)
    iters = np.arange(len(train_loader) * (args.epochs - args.warmup_epochs))
    cosine_lr_schedule = np.array([args.final_lr + 0.5 * (args.base_lr - args.final_lr) * (1 + \
                         math.cos(math.pi * t / (len(train_loader) * (args.epochs - args.warmup_epochs)))) for t in iters])
    lr_schedule = np.concatenate((warmup_lr_schedule, cosine_lr_schedule))
    logger.info("Building optimizer done.")
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -