search

theFoxofSky / ddfnet

The official implementation of the CVPR2021 paper: Decoupled Dynamic Filter Networks
MIT License
212 stars 34 forks source link

basic doubt #23

Open nanmehta opened 3 years ago

nanmehta commented 3 years ago

sir, can you please let me know, why have you use backward compatible code also in the implementation. I am talking about the class defined below.. @staticmethod def backward(ctx, grad_output): assert grad_output.is_cuda

    .........
theFoxofSky commented 2 years ago

The forward of DDF is implemented in CUDA, the autograd is not suitable for this case. So, I also implement the backward function.

nanmehta commented 2 years ago

sir, can you please explain the concept of the relation between dynamic filters and attention as shown in Figure 3 of your paper. How can we relate applying dynamic concept (where every filter is applied to each pixel) with attention