mask2former/modeling/transformer_decoder/mask2former_transformer_decoder.py
mask2former_video/modeling/transformer_decoder/video_mask2former_transformer_decoder.py

mask2former/modeling/criterion.py
mask2former_video/modeling/criterion.py

mask2former/modeling/matcher.py
mask2former_video/modeling/matcher.py

mask2former/modeling/meta_arch/mask_former_head.py
mask2former_video/modeling/transformer_decoder/video_mask2former_transformer_decoder.py

mask2former/modeling/transformer_decoder/maskformer_transformer_decoder.py
mask2former_video/modeling/transformer_decoder/video_mask2former_transformer_decoder.py

mask2former/modeling/meta_arch/per_pixel_baseline.py
mask2former_video/modeling/transformer_decoder/video_mask2former_transformer_decoder.py

mask2former/modeling/transformer_decoder/position_encoding.py
mask2former_video/modeling/transformer_decoder/position_encoding.py

mask2former/modeling/transformer_decoder/transformer.py
mask2former_video/modeling/transformer_decoder/video_mask2former_transformer_decoder.py