houqb VisionPermutator issues - Githubissues

houqb / VisionPermutator

MLP-Like Vision Permutator for Visual Recognition (PyTorch)

MIT License

190 stars 25 forks source link

issues

Newest

Newest Most commented Recently updated Oldest Least commented Least recently updated

In the code class WeightedPermuteMLP, after h = h.permute(0, 3, 2, 1, 4), h becomes (B, segment_dim, W, H, S); after w = w.permute(0, 1, 3, 2, 4), w becomes (B, H, segment_dim, W, S). My question is why can't w also be turned into (B, segment_dim, H, W, S)

#6 lxy51 opened 1 month ago
0
Question about pre-training for cifar10 and cifar-100

#5 sairaamVenkatraman opened 2 years ago
0
A higher result than paper, but i don't know why.

#4 GuideWsp opened 3 years ago
9
questions regarding training loss and parser

#3 chengengliu closed 3 years ago
3
Missing Citation?

#2 digantamisra98 closed 3 years ago
3
Question about apex

#1 ziyuwwang opened 3 years ago
3