VisionPermutator
VisionPermutator copied to clipboard
houqb
MLP-Like Vision Permutator for Visual Recognition (PyTorch)
Hi! Thank you for releasing the code. Could you explain the pre-training done for cifar-10 and cifar-100 in transfer_learning.py? I found no details about this in the paper, too.
I don't know why,but I got a 84.42%@vip_s7，the following is the cmd and log. Note: I train the vip with 6 Ti1080, batch=64. CUDA_VISIBLE_DEVICES=0,1,2,4,6,7 ./distributed_train.sh 6 --data /data/path/to/imagenet --model vip_s7...
Hello ! Thanks for releasing the code ! While "--apex-amp" is included in the training command, "apex" is not mentioned in requirements. So I wonder whether the "apex amp" is...
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...
