FaPN
FaPN copied to clipboard
[ICCV 2021] FaPN: Feature-aligned Pyramid Network for Dense Image Prediction
`self.dcpack_L2 = dcn_v2(out_nc, out_nc, 3, stride=1, padding=1, dilation=1, deformable_groups=8, extra_offset_mask=True)` why out_nc is 256, not 216(3 x kernel_size x kernal_size x deformable_groups) ?
Could you share the codes for feature visualization in your paper?
您好,看了您的论文,希望借助一下您论文中的FSM和FAM模块,直接插入到我的网络中,但我没有找到这两个模块的单独实现,请问这两个模块的单独实现在哪里呢,谢谢
In module[ FeatureAlign_v2](https://github.com/EMI-Group/FaPN/blob/main/detectron2/modeling/backbone/fan.py) `offset = self.offset(torch.cat([feat_arm, feat_up * 2], dim=1)) # concat for offset by compute the dif` Why multiple feat_up by 2?
Hi, dear authors, can you release your codes for feature alignment visualization, i.e., codes for Figure 6 ?
已解决
I want to use fapn structure in my code, but " File "/databank/home/DCNv2/dcn_v2.py", line 43, in forward ctx.deformable_groups, RuntimeError: expected scalar type Float but found Half" appears,How can I solve...
Hi, thank you for your contribution. It is a good work. I have a small question. Have you done any ablation studies about other FPN-like modules? i.e. FPN-NAP, PAN, BIFPN,...
没有找到fan.py中的 detectron2.layer文件
Can this method be used in the unit price segment target detection model?