Kaixuan Wei
Kaixuan Wei
Nope, we use the same dataset (PASCAL VOC) to learn policy for all applications. Since the policy network is only responsible to the parameter selection within the PnP algorithm (the...
Hi, yes you need to set `enable_CT = True`, and install torch_radon from `https://github.com/matteo-ronchetti/torch-radon` This package would be somewhat tricky to install. Please let me know if you encounter any...
Yes, not shared, but it would be easy to modify to the shared version
The implementation seems to be correct. However, to my knowledge, this parameter-shared version might lead to performance decline.
Yes you are right
Hi, I just uploaded my testing data into [GoogleDrive](https://drive.google.com/file/d/1Xk8Lq7TkeK0ByYxfqiNlG1QzBrQuE4N7/view?usp=sharing) from the local computer. Could you please check whether you can reproduce our results
Could you please tell me more information about your environment? for example, the PyTorch version, the GPU version, etc..
Note this work was done many years ago, and actually, I tried to reproduce its results several months ago, but I found a very weird issue---the reproduction was successful in...
VGG-based discrimator might achieve better result than patch-based one since reflection components are easier to be recognized globally (rather than locally)
> while actually such operation(large integers are divided by ratio then make float to integers) pls don't convert the float to int in this step