permutation order

[philipsgithub]

dino-vit-features/extractor.py

Line 299 in 1779649

desc = x.permute(0, 2, 3, 1).flatten(start_dim=-2, end_dim=-1).unsqueeze(dim=1) # Bx1xtx(dxh)

I am a bit confused. According to my understanding it should be x.permute(0, 2, 1, 3). same goes for line 239.

do I miss something?

PS:

dino-vit-features/extractor.py

Line 239 in 1779649

bin_x = x.permute(0, 2, 3, 1).flatten(start_dim=-2, end_dim=-1) # Bx(t-1)x(dxh)

[ShirAmir]

As mentioned in the documentation of _extract_features, the outputted features are of shape Bxhxtxd. Hence, in the line you mentioned x.permute(0, 2, 3, 1) reshapes to Bxtxdxh; .flatten(start_dim=-2, end_dim=-1) reshapes to Bxtx(dxh) and .unsqueeze(dim=1) reshapes to Bx1xtx(dxh) as needed.