shihuahuang95/fapn-full

[ICCV 2021] FaPN: Feature-aligned Pyramid Network for Dense Image Prediction

fapn-full's Issues

没有找到fan.py中的 detectron2.layer文件

没有找到fan.py中的 detectron2.layer文件

dcn_v2 error RuntimeError: expected scalar type Float but found Half

When running the network, I encountered this problem. Through debugging, I found that the offset in DCN's forword function is a type of float16.So I think this might be the cause of the problem，Do you have a better idea for this problem.

关于可变形卷积的具体实现

您好，您的工作是一份非常有价值的工作。由于我在pytorch1.7.1下,编译不了您提供的可变性卷积的库。所以我尝试用mmd实现您的代码，我遇到了一个问题：
self.dcpack_L2 = dcn_v2(out_nc, out_nc, 3, stride=1, padding=1, dilation=1, deformable_groups=8,
extra_offset_mask=True)
这行代码的mask是根据x算的，还是根据offset算的？您知道具体的计算方法吗？

FSM和FAM

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

Question about the number of "out_channels"

After watching your code, i have a question, about every layer after "FSM" and "FAM" model the output channels are same.Do I understand that right? And i want to know what the number of "out_channels" is set to. Thanks a lot.

Error when train model.

Hi, I follow your instructions to arrange the project. However, this error still occurs. Could you help me with this issue?

KeyError: "No object named 'build_resnet_fan_backbone' found in 'BACKBONE' registry!"