awesome-semantic-segmentation-pytorch

awesome-semantic-segmentation-pytorch copied to clipboard

As the title say, I find the jpu paramters not add to optim. That makes the jpu module's paramters not change. But interenting things is: when I add the jpu paramters to optim, the results almost not change in mIoU and pixels acc. I not change other hyper-paramter, What a amazing result.

It is possible, network with different modules may depend on different parameters, this paper maybe helpful for searching th optimal parameter.