ZouJiaYu

Results 1 issues of ZouJiaYu

theoretical code: att = torch.softmax(torch.mul(mxpool, avgpool), 1) fusion = attt * avgpool + attt * mxpool actual code : att = torch.softmax(torch.mul(mxpool, avgpool), 1) attt1 = att[:, 0, :, :].unsqueeze(1)...