SAN
SAN copied to clipboard
hszhao
Exploring Self-attention for Image Recognition, CVPR2020.
Thank you for the repo! I can reproduce the SAN-10 pairwise / patchwise results. However, for the CNN baselines mentioned in this paper (i.e. ResNet-26, ResNet-38, ResNet-50), I wonder how...
  But in the code https://github.com/hszhao/SAN/blob/d88b022fc3ec4920d4596f94983f0e5b1ced62c6/model/san.py#L39-L42 I think the self.conv_w is the mapping function but it is different from paper **code**: BN -> R -> Conv -> BN ->...
`model = san.san(sa_type=1, layers=[3, 2, 3, 5, 2], kernels=[3, 7, 7, 7, 7], num_classes=1000).cuda() model.load_state_dict(torch.load('./san15_patchwise/model/model_best.pth'))` RuntimeError: Error(s) in loading state_dict for SAN: Missing key(s) in state_dict: "conv_in.weight", "bn_in.weight", "bn_in.bias", "bn_in.running_mean",...
enviroment: pytorch 1.5.1 cuda 10.1 test on small input tensor (2,8,5,5) when using the test method in lib/sa/functions to test the speed, I found that the corresponding implementation using pytorch...
Hi!!! Dr Zhao. It is a very interesting work. I have one Question. Have you tried your model with more layers ?
Hi, I am just wondering is there any support for 3DCNN using proposed pairwise and patchwise attention. In my case, I have multiple input image and each of them produce...
Hello Dr. Zhao, I was studying your paper and the code shared on the page but had difficulty understanding the "load_kernel()" and "f(block=...., grid=(...., args=[..., stream=...)" parts in subtraction/subtraction2/aggregate functions....
