How to implement fixed encoder?

[Heisenberg-Don]

Interesting work!

How did you freeze the encoders? I can't determine which part of your implementation handles this operation.

[Heisenberg-Don]

BTW, could you share the 5-degradation dataset settings?

[toummHus]

Thanks for your interest.
The code "nn.Sequential(*[TransformerBlock ...])" will produce a fixed encoder layer and "HyLevel(...)" produces a dynamical layer. The word "fixed" in the paper means that the weights of this module is fixed during inference.

For the 5-degradation setting, you can refer the code of IDR. And maybe we will upload this in the new version.

[toummHus]

In addition, all the classes with a prefix of "Hy" like "HyConv2d" are dynamical during inference. We will add detailed comments in a future release.