style-based-gan-pytorch

style-based-gan-pytorch copied to clipboard

How to test the trained model

1

Thank you for your work, I am a newcomer who wants to know about the work. I noticed that you only provide the command to train the model in the...

dphero

n_gpu setting not respected

2

Hi, it looks like n_gpu setting isn't used anywhere.

jeffling

CUDA out of memory in generate, even with 1 image

5

Before I start, Huge thank you for the pre trained models; but generating is problematic. Each time I try to run the code this happens:[output](https://pastebin.com/keRn13KQ) Surprisingly enough, training works perfectly...

jamiejacker

Grayscale input

2

Hi, I try to use your environment to train the generator and discriminator with grayscale inputs, but I don't figure it which are the values that need to be change...

dassima

image size and the differences with official implementation

20

thanks for this work! But i still have two question: 1. the number of styledconvblock is 6, so the output image size is no more than 128, am i right?...

cientgu

what is the important of the below lines?

6

if mixing and random.random() < 0.9: gen_in11, gen_in12, gen_in21, gen_in22 = torch.randn(4, b_size, code_size, device='cuda').chunk(4, 0) gen_in1 = [gen_in11.squeeze(0), gen_in12.squeeze(0)] gen_in2 = [gen_in21.squeeze(0), gen_in22.squeeze(0)] else: gen_in1, gen_in2 = torch.randn(2, b_size,...

nile649