Barışcan Bozkurt

I come across with a very similar error while I am implementing an Implicit-GON (Gradient Origin Network) model for implicit learning task. `pkg> add AutoGrad#dy/fix671` seems to fix the problem...

Hi @Kausta. Thank you for your quick reply. I think I understand the problem now. The problem is not about the precompilation since other iterations also takes so much time....

Disregard my previous comment. In my second example code, the hcat function inside `model_forw(theta, z)` concatenates z 784 times. Normally, I would like to take the gradient of the `loss()`...

I found my workaround solution. Instead of using `hcat` function to repeat my `z` matrix over its second dimension 784 times, I used 1x1 convolution operation with convolution weights of...

Hello again, I appreciate your comments, which were helpful for me to understand several issues. When I do not use the batchnorm function, I was able to take the derivative...

> Hello again, > > I appreciate your comments, which were helpful for me to understand several issues. > > When I do not use the batchnorm function, I was...

I strongly believe that the issue is related to the affine implementation of batchnorm function in Knet. Here, I will report all the observations I made as well as my...

I am not expert on this model but I will make my own comment. I think you can calculate it with the following line of code `((g - x)**2).sum() /...

I really appreciate the information. If you or @thesamovar have any other suggestion, I will be able to update the citation that I used. Until then, I use the bibtex...