the description of SSAM is inconsistent with the code

mohamedac29 / S2-FPN

Scale-ware Strip Attention Guided Feature Pyramid Network for Real-time Semantic Segmentation

MIT License

21 stars 5 forks source link

the description of SSAM is inconsistent with the code #10

Open jiayu-Zou opened 1 year ago

jiayu-Zou commented 1 year ago

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) attt2 = att[:, 1, :, :].unsqueeze(1) fusion = attt1 avgpool + attt2 mxpool

why？