DETR/arguments.py

import argparse

def get_args_parser():
    parser = argparse.ArgumentParser('Set transformer detector', add_help=False)
    parser.add_argument('--lr', default=1e-4, type=float)
    parser.add_argument('--lr_backbone', default=1e-5, type=float)

    # # * Backbone
    parser.add_argument('--backbone', default='resnet50', type=str,
                        help="Name of the convolutional backbone to use")
    parser.add_argument('--dilation', action='store_true',
                        help="If true, we replace stride with dilation in the last convolutional block (DC5)")
    parser.add_argument('--position_embedding', default='sine', type=str, choices=('sine', 'learned'),
                        help="Type of positional embedding to use on top of the image features")

    # * Transformer
    parser.add_argument('--enc_layers', default=6, type=int,
                        help="Number of encoding layers in the transformer")
    parser.add_argument('--dec_layers', default=6, type=int,
                        help="Number of decoding layers in the transformer")
    parser.add_argument('--dim_feedforward', default=2048, type=int,
                        help="Intermediate size of the feedforward layers in the transformer blocks")
    parser.add_argument('--hidden_dim', default=256, type=int,
                        help="Size of the embeddings (dimension of the transformer)")
    parser.add_argument('--dropout', default=0.1, type=float,
                        help="Dropout applied in the transformer")
    parser.add_argument('--nheads', default=8, type=int,
                        help="Number of attention heads inside the transformer's attentions")
    parser.add_argument('--num_queries', default=40, type=int,
                        help="Number of query slots")
    parser.add_argument('--pre_norm', action='store_true')

    # dataset parameters
    parser.add_argument('--dataset_file', default='coco')
    parser.add_argument('--device', default='cuda',
                        help='device to use for training / testing')

    # * Segmentation
    parser.add_argument('--masks', action='store_true',
                        help="Train segmentation head if the flag is provided")

    # Loss
    parser.add_argument('--no_aux_loss', dest='aux_loss', action='store_false',
                        help="Disables auxiliary decoding losses (loss at each layer)")
    # * Matcher
    parser.add_argument('--set_cost_class', default=1, type=float,
                        help="Class coefficient in the matching cost")
    parser.add_argument('--set_cost_bbox', default=5, type=float,
                        help="L1 box coefficient in the matching cost")
    parser.add_argument('--set_cost_giou', default=2, type=float,
                        help="giou box coefficient in the matching cost")
    # # * Loss coefficients
    parser.add_argument('--bbox_loss_coef', default=5, type=float)
    parser.add_argument('--giou_loss_coef', default=2, type=float)
    parser.add_argument('--eos_coef', default=0.1, type=float,
                        help="Relative classification weight of the no-object class")
    
    parser.add_argument('--read_checkpoint', default='./DETR/output/checkpoint.pth', help='checkpoint path')

    #Image_Path
    parser.add_argument('--img_org', type=str)
    parser.add_argument('--img_gen', type=str)

    return parser