python data_modules/coco_detection2detr.py --sequential

from argparse import ArgumentParser
from alonet.detr import LitDetr

import alonet


def get_arg_parser():
    parser = ArgumentParser(conflict_handler="resolve")
    parser = alonet.common.add_argparse_args(parser)  # Common alonet parser
    parser = LitDetr.add_argparse_args(parser)  # LitDetr training parser
    # parser = pl.Trainer.add_argparse_args(parser) # Pytorch lightning Parser
    return parser


def main():
    """Main"""
    # Build parser
    args = get_arg_parser().parse_args()  # Parse

    # Init the Detr model with the dataset
    detr = LitDetr(args)
    print(detr.model)

if __name__ == "__main__":
    main()

import aloscene
import torch
import alodataset.transforms as T

x=torch.zeros(3,256,256)
frame=aloscene.Frame(x,names=("C","H","W"))
mask=aloscene.Mask(torch.randint(0,2,(1,256,256)),names=("C","H","W"))
frame.append_mask(mask)

newframe=T.SpatialShift((10,10))(frame)

from alonet.deformable_detr.deformable_detr import DeformableDETR
from alonet.deformable_detr.backbone import Joiner


class DeformableDetrCustom(DeformableDETR):
    """Deformable Detr with custom transformer. For testing purposes only"""

    def __init__(self, *args, hidden_dim=256, return_intermediate_dec: bool = True, num_classes=91, **kwargs):
        backbone = self.build_backbone(
            backbone_name="resnet50", train_backbone=True, return_interm_layers=True, dilation=False
        )
        position_embed = self.build_positional_encoding(hidden_dim=256)
        backbone = Joiner(backbone, position_embed)
        transformer = self.build_transformer(
            hidden_dim=hidden_dim,
            dropout=0.1,
            nheads=8,
            dim_feedforward=1024,
            enc_layers=6,
            dec_layers=6,
            num_feature_levels=4,
            dec_n_points=4,
            enc_n_points=4,
            return_intermediate_dec=return_intermediate_dec,
        )

        super().__init__(backbone, transformer, *args, num_classes=num_classes, with_box_refine=False, **kwargs)

if __name__ == "__main__":
    model=DeformableDetrCustom(weights=None)
    print(model.transformer.decoder.layers[0].cross_attn.sampling_offsets) #in_features should be 256

    model2=DeformableDetrCustom(hidden_dim=128,weights=None)
    print(model2.transformer.decoder.layers[0].cross_attn.sampling_offsets) #in_features should be 128