facebookresearch / dino

PyTorch code for Vision Transformers training with the Self-Supervised learning method DINO
Apache License 2.0
6.38k stars 910 forks source link

dead code in video_generation.py #222

Open eminorhan opened 1 year ago

eminorhan commented 1 year ago

The thresholded attention maps computed in this block of code aren't being used anywhere else as far as I can tell, so this section seems to just waste computation and memory: https://github.com/facebookresearch/dino/blob/main/video_generation.py#L197