You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Also, I found another issue, in Attention.py , transposed conv. is used to reconstruct the feature map, as shown in this line: feature_map = F.conv_transpose2d(attention_scores, conv_kernels, stride = 1, padding = self.patch_size//2)
where conv_kernels has been normalized in previous steps (conv_kernels = conv_kernels/norm_factor).
However, I think the conv_kernels here should be the original one (without normalization), could you please help me check this out, thanks! @jingyuanli001
First of all, thanks for your great work!
I got a question when looking through your code in
Attention.py
, where line 39 is as follows:conv_result = F.avg_pool2d(conv_result, 3, 1, padding = 1)*9
this corresponds to the equation (5) in your paper:
My question is, the 3*3 average pooling itself is capable of getting the averaged results, why
multiplied by 9
is needed?Hope to hear your reply : )
The text was updated successfully, but these errors were encountered: