Open LWShowTime opened 7 months ago
n visualize_attention.py: https://github.com/facebookresearch/dino/blob/7c446df5b9f45747937fb0d72314eb9f7b66930a/visualize_attention.py#L108 However, in vision_transformer.py: https://github.com/facebookresearch/dino/blob/7c446df5b9f45747937fb0d72314eb9f7b66930a/vision_transformer.py#L116-L122 Will this cause any performance drop?
I notice in DINO, your team have delete this line from the origin ViT: assert H == self.img_size[0], f"Input image height ({H}) doesn't match model ({self.img_size[0]}).
assert H == self.img_size[0], f"Input image height ({H}) doesn't match model ({self.img_size[0]}).
@piotr-bojanowski @mathildecaron31
n visualize_attention.py: https://github.com/facebookresearch/dino/blob/7c446df5b9f45747937fb0d72314eb9f7b66930a/visualize_attention.py#L108 However, in vision_transformer.py: https://github.com/facebookresearch/dino/blob/7c446df5b9f45747937fb0d72314eb9f7b66930a/vision_transformer.py#L116-L122 Will this cause any performance drop?