def parse_args()

in archived/Image_Classification_VIT/scripts/train_images.py [0:0]

• 114 lines of code
• 4 McCabe index (conditional complexity)

def parse_args():

    parser = argparse.ArgumentParser(description="Fine-tune a Transformers model on an image classification dataset")

    
    ##################### SIFTING FLAG #############################
    parser.add_argument(
        "--use_sifting",
        type=int,
        default=None,
        help="Flag for whether to use sifting or not. 0 serves as false",
    )
    #################################################################
    
    parser.add_argument(
        "--dataset_name",
        type=str,
        default="cifar10",
        help=(
            "The name of the Dataset (from the HuggingFace hub) to train on (could be your own, possibly private,"
            " dataset)."
        ),
    )
    parser.add_argument("--train_dir", type=str, default=os.environ["SM_CHANNEL_TRAIN"], help="A folder containing the training data.")
    parser.add_argument("--validation_dir", type=str, default=None, help="A folder containing the validation data.")
    parser.add_argument(
        "--max_train_samples",
        type=int,
        default=None,
        help=(
            "For debugging purposes or quicker training, truncate the number of training examples to this "
            "value if set."
        ),
    )
    parser.add_argument(
        "--max_eval_samples",
        type=int,
        default=None,
        help=(
            "For debugging purposes or quicker training, truncate the number of evaluation examples to this "
            "value if set."
        ),
    )
    parser.add_argument(
        "--train_val_split",
        type=float,
        default=0.15,
        help="Percent to split off of train for validation",
    )
    parser.add_argument(
        "--model_name_or_path",
        type=str,
        help="Path to pretrained model or model identifier from huggingface.co/models.",
        default="google/vit-base-patch16-224-in21k",
    )
    parser.add_argument(
        "--per_device_train_batch_size",
        type=int,
        default=8,
        help="Batch size (per device) for the training dataloader.",
    )
    parser.add_argument(
        "--per_device_eval_batch_size",
        type=int,
        default=8,
        help="Batch size (per device) for the evaluation dataloader.",
    )
    parser.add_argument(
        "--learning_rate",
        type=float,
        default=5e-5,
        help="Initial learning rate (after the potential warmup period) to use.",
    )
    parser.add_argument("--weight_decay", type=float, default=0.0, help="Weight decay to use.")
    parser.add_argument("--num_train_epochs", type=int, default=3, help="Total number of training epochs to perform.")
    parser.add_argument(
        "--max_train_steps",
        type=int,
        default=None,
        help="Total number of training steps to perform. If provided, overrides num_train_epochs.",
    )
    parser.add_argument(
        "--gradient_accumulation_steps",
        type=int,
        default=1,
        help="Number of updates steps to accumulate before performing a backward/update pass.",
    )
    parser.add_argument(
        "--lr_scheduler_type",
        type=SchedulerType,
        default="linear",
        help="The scheduler type to use.",
        choices=["linear", "cosine", "cosine_with_restarts", "polynomial", "constant", "constant_with_warmup"],
    )
    parser.add_argument(
        "--num_warmup_steps", type=int, default=0, help="Number of steps for the warmup in the lr scheduler."
    )
    parser.add_argument("--output_dir", type=str, default=None, help="Where to store the final model.")
    parser.add_argument("--seed", type=int, default=None, help="A seed for reproducible training.")

    parser.add_argument(
        "--checkpointing_steps",
        type=str,
        default=None,
        help="Whether the various states should be saved at the end of every n steps, or 'epoch' for each epoch.",
    )
    parser.add_argument(
        "--resume_from_checkpoint",
        type=str,
        default=None,
        help="If the training should continue from a checkpoint folder.",
    )

    parser.add_argument(
        "--ignore_mismatched_sizes",
        action="store_false",
        help="Whether or not to enable to load a pretrained model whose head dimensions are different.",
    )

    args = parser.parse_args()
    # Sanity checks
    if args.dataset_name is None and args.train_dir is None and args.validation_dir is None:
        raise ValueError("Need either a dataset name or a training/validation folder.")


    return args