stylegan2-pytorch

stylegan2-pytorch copied to clipboard

Tesla V100 GPU - 2600 Image - Too Slow Training

1

I have p3.2xlarge amazon ec2 instance. And there is 1 tesla v100 gpu. I have about 2600 images. Here is my parameters: `stylegan2_pytorch --name try1 --data /data/Part2/dataset_resized --attn-layers 1 --results_dir...

mertyyanik

Generating faces

27

Hello, I tried to train a model on 70k images of the FFHQ thumbnail dataset. The model should generate 128x128 images of faces, unfortunately, the results are not very convincing....

oliverguhr

Windows: pip install doesn't work

5

Dear lucidrains, thank you very much for sharing this work with us. The following is output from the anaconda prompt when I try to install stylegan2: > ERROR: Command errored...

pocaha

Add --wandb flag just like in rosinality?

1

@lucidrains

ucalyptus2

Dear Phil, what is an architecture of web application thispersondoesnotexist.com ? I want to implement a trained model to show random generated images while reloading. As I understood, creating of...

A-simo

PL reg memory consumption

4

Hello. I have the following setting: batch size 12, grad accumulation 4, image_size 128. At 5024 iterations PL reg comes in, and consumes A LOT of memory. 7 GB utilization...

GLivshits

@lucidrains Thanks for this repository. I'm trying this script for generating Morpho-MNIST digits (MNIST with tweaking morphology like thickness and intensity), image size 32x32, 3 channels. Even after training for...

koriavinash1

The generated samples have very little difference

11

I'm trying to generate some avatars of NBA players. After 5000 iterations, I can barely see the silhouette of the player. But the generated samples look the same. Is this...

FrazierLei

Prediction is always the same

1

Hi, first of all thanks for this great project ! I got issues when rendering a prediction with a custom dataset from specific checkpoint. From CLI or with code, it...

Fqlox

Parameters for generating faces

1

Hi, i want to train a GAN to generate images of faces but i am facing the following problems. I am using a dataset of 200000 images of 128x128 and...

liogl9