FCInter
FCInter
@chengdazhi Sorry limited by environment, I can only use 1.0.0. What if I ignore this error and directly use it in my network? Will this be a problem?
No. Go to the `torch_deform_conv/layers.py`. Have a look at the `forward()` function of the class `ConvOffset2D`. Just print the shapes of every tensor, you'll find the implementation is right. The...
Quite a lot of implementation details were not made clear in the paper. I tried to implement one version, but the result is awful. Looking forward to the code.
According to my test case, I'm afraid it really matters, because when I build the training network and load the test checkpoint, the model does not converge very well. Moreover,...
@AresGao I have updated the issue. I posted the printed logs during training process. The problem is that I cannot get good results when I continue to train from the...
@AresGao What version of mxnet are you using? I was wondering if it's caused by the version, since I got a bug because of the wrong version I was using.
@AresGao Finally I got good results after training for 2 complete epoch!!! I just have one last question. I find that when saving checkpoint at the end of each epoch,...
Same problem I met. Looking forward to a solution here.
In the latest version, you just need to remove all the torch-dependent code from the source files. No influence.