Mario Klingemann

Sorry, I don't know. The only thing I can say is that in my experience lambda seems to balance between global and local structure. So if I remember correctly decreasing...

Thanks, I will try this. Do you know if there is a simple way in torch to remove (or at least disable) this batchnorm from a loaded pre-trained model that...

No I did not look into ways how to fix then anymore since they seem to be only happening when using a BatchSize of 1. At least I have not...

I think you might be able to reuse the display server for this. It seems to have a built-in method to visualize tensors: display.image(tensor, options) > Displays the tensor as...

I made a quick test and it seems to work. If you insert this in the display update condition you will have your screen filled quickly :-): ``` local idx...

I can confirm that I occasionally get the same "Creating MTGP constants failed" error.

Ah - I also have two GPUs on my machine, so there might be a pattern. Since I have resorted to adding CUDA_VISIBLE_DEVICES=0 or CUDA_VISIBLE_DEVICES=1 at the beginning of the...

Thanks! I managed to hack something together now which does the job for what I need, but it's pretty dirty - so a clean approach would be much appreciated.

The model only processes an image in the fineSize dimensions. So if you pass in a bigger image it will get scaled down and potentially cropped. To my knowledge there...

One way to solve it is to use a separate counter and instead of doing a modulo check rather do a secondCounter >= saveFreq check and resetting the counter after...