S2-FPN
S2-FPN copied to clipboard
mohamedac29
Scale-ware Strip Attention Guided Feature Pyramid Network for Real-time Semantic Segmentation
Hi, thanks for your sharing. i am interested in this work. However, i find i cant download the weights ` CamVid | ResNet34M | trainval | 74.76% | 55.5 |...
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)...
When I train with the cityscapes dataset, there is an AttributeError: 'NoneType' object has no attribute 'copy' error. How should I change the dataset path? Is there another error? Datasets...
In paper，Equation 6 is Fscale = A ⊙F2 + A⊙F2, but with the text description, I think it should be Fscale = A⊙F1 + A⊙F2.
In this class, I find `mxpool = F.max_pool2d(x, [h, 1])`, and after this, maxpool will be (B, C, 1, W), but in paper, it's (B, C, H, 1). I have...
In paper, Equation 7 is FSSAM = αFscale + (α-1)F, but in Fig. 4, it shows α and (1-α). And in your code, it's (1 - self.gamma). So I think...
In the SpatialAttention class, both maxpooling and avgpooling functions use F.avg_pool2d, which is inconsistent with the paper, please explain.Thanks
Metadata
Owner
Metadata
Scale-ware Strip Attention Guided Feature Pyramid Network for Real-time Semantic Segmentation