train-distillation.py [82:151]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
    parser.add_argument("--eval_only", type=bool_flag, default=False,
                        help="Only run evaluations")

    # debug
    parser.add_argument("--debug_train", type=bool_flag, default=False,
                        help="Use valid sets for train sets (faster loading)")
    parser.add_argument("--debug_slurm", type=bool_flag, default=False,
                        help="Debug from a SLURM job")
    parser.add_argument("--debug", help="Enable all debug flags",
                        action="store_true")


    # multi-gpu / multi-node
    parser.add_argument("--local_rank", type=int, default=-1,
                        help="Multi-GPU - Local rank")
    parser.add_argument("--master_port", type=int, default=-1,
                        help="Master port (for multi-node SLURM jobs)")

    return parser


def main(params):

    # initialize the multi-GPU / multi-node training
    init_distributed_mode(params)

    # initialize the experiment / load data
    logger = initialize_exp(params)

    # Seed
    torch.manual_seed(params.seed)
    torch.cuda.manual_seed_all(params.seed)

    # initialize SLURM signal handler for time limit / pre-emption
    if params.is_slurm_job:
        init_signal_handler()

    # data loaders / samplers
    populate_dataset(params)
    train_data_loader, train_sampler, _ = get_data_loader(
        img_size=params.img_size,
        crop_size=params.crop_size,
        shuffle=True,
        batch_size=params.batch_size,
        num_classes=params.num_classes,
        nb_workers=params.nb_workers,
        distributed_sampler=params.multi_gpu,
        dataset=params.dataset,
        data_path=params.train_path,
        transform=params.train_transform,
        split='valid' if params.debug_train else 'train',
        seed=params.seed
    )

    valid_data_loader, _, _ = get_data_loader(
        img_size=params.img_size,
        crop_size=params.crop_size,
        shuffle=False,
        batch_size=params.batch_size,
        num_classes=params.num_classes,
        nb_workers=params.nb_workers,
        distributed_sampler=False,
        dataset=params.dataset,
        transform='center',
        split='valid',
        seed=params.seed
    )

    # build model / cuda
    logger.info("Building %s model ..." % params.architecture)
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -



train-logistic.py [77:145]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
    parser.add_argument("--eval_only", type=bool_flag, default=False,
                        help="Only run evaluations")

    # debug
    parser.add_argument("--debug_train", type=bool_flag, default=False,
                        help="Use valid sets for train sets (faster loading)")
    parser.add_argument("--debug_slurm", type=bool_flag, default=False,
                        help="Debug from a SLURM job")
    parser.add_argument("--debug", help="Enable all debug flags",
                        action="store_true")

    # multi-gpu / multi-node
    parser.add_argument("--local_rank", type=int, default=-1,
                        help="Multi-GPU - Local rank")
    parser.add_argument("--master_port", type=int, default=-1,
                        help="Master port (for multi-node SLURM jobs)")

    return parser


def main(params):

    # initialize the multi-GPU / multi-node training
    init_distributed_mode(params)

    # initialize the experiment / load data
    logger = initialize_exp(params)

    # Seed
    torch.manual_seed(params.seed)
    torch.cuda.manual_seed_all(params.seed)

    # initialize SLURM signal handler for time limit / pre-emption
    if params.is_slurm_job:
        init_signal_handler()

    # data loaders / samplers
    populate_dataset(params)
    train_data_loader, train_sampler, _ = get_data_loader(
        img_size=params.img_size,
        crop_size=params.crop_size,
        shuffle=True,
        batch_size=params.batch_size,
        num_classes=params.num_classes,
        nb_workers=params.nb_workers,
        distributed_sampler=params.multi_gpu,
        dataset=params.dataset,
        data_path=params.train_path,
        transform=params.train_transform,
        split='valid' if params.debug_train else 'train',
        seed=params.seed
    )

    valid_data_loader, _, _ = get_data_loader(
        img_size=params.img_size,
        crop_size=params.crop_size,
        shuffle=False,
        batch_size=params.batch_size,
        num_classes=params.num_classes,
        nb_workers=params.nb_workers,
        distributed_sampler=False,
        dataset=params.dataset,
        transform='center',
        split='valid',
        seed=params.seed
    )

    # build model / cuda
    logger.info("Building %s model ..." % params.architecture)
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -