scart97

I have not tried to implement this supervision, so I'm not sure how it will happen. According to the paper, section 3.2 of the appendix: > The ground truth gradient...

That's cool! I also tried to get this working today, extracting patches from the image and using sobel filtering. My model learned the correct gradients and also started to get...

Yeah, I compare the numerical gradient of the network output against the ground truth. The official implementation is out, and they use autograd to calculate the networks gradients.

In the original paper they have comparisons with other activation functions, but it's very focused on the modeling aspect. I tried image classification on [imagenette](https://github.com/fastai/imagenette) (small subset of the full...

Sample of image fitting using the model with batchnorm, notice the strange patterns that are not present in the original model: 

It makes sense, and would be a good addition to the library. Also I just realized that this code is not using pytorch to create random numbers, that is a...

The tests are breaking because of a problem while exporting the code from the notebooks. Please follow the instructions to fix it: * Install nbdev: `pip install nbdev --upgrade` *...

@mogwai Is this necessary now that the notebooks are small ?