Hannu Töyrylä

Also, you need to make sure you are in the main directory when you run the **download script**. If you run it from the models/ directory, it will place the...

Nice find @xlvector . I am now training with ``` -arch c9s1-16,d32,d64,R64,R64,R64,R64,R64,U2,U2,c9s1-3 ``` and it looks good so far.

Thanks for the tip! Even if I didn't have any problems with it. BTW in the udnie test today I used this architecture.

IHMO, updating torch is in general one of the first things to try when having any problem with torch.

I would think it is connected to the practice back then of using 0..255 pixel range directly in models. Eg. the original neural-style used a VGG model like that. This...

> That way you can directly feed the output of the transformer net into the perceptual net (VGG). That's about what I was thinking too. But also that 150 may...

Seems to me that he's not been active here for a long time. The logical place to start is to consult the paper https://cs.stanford.edu/people/jcjohns/papers/eccv16/JohnsonECCV16.pdf . From section 3.1 "All nonresidual...

Yes, the style image is scaled but not to 256x256 but keeping the aspect ratio so that the smaller side is 256 pixels. This among many other things is explained...

@austingg, I don't think the question was related to the FC layers only working with 256x256 but to the parameter style_image_size, which does indeed scale the longer side of the...

The idea is very simple, preserve the colors of the original image by copying the chrominance from the content image into the result. I have written a script to do...