STYLE GAN Implementation


Hi Developers,

My team is trying to implement STYLE GAN transfer but we are not getting good results. I would request you to please share some working resources for the same.
We are working on the style transfer and we trying to implement the same. Pose with style which uses style GAN as base . But the problem is that we are not getting a good accuracy as we expect. For the test data that authors has provided we are getting better accuracy but when it comes with our own data we are seeing a huge accuracy drop. Please share your thoughts on how to increase the accuracy for style transfer especially for style GAN.

useful links:

github repo: GitHub - BadourAlBahar/pose-with-style: [SIGGRAPH Asia 2021] Pose with Style: Detail-Preserving Pose-Guided Image Synthesis with Conditional StyleGAN
research paper:

A clear and concise description of the bug or issue.


TensorRT Version:
GPU Type:
Nvidia Driver Version:
CUDA Version:
CUDNN Version:
Operating System + Version:
Python Version (if applicable):
TensorFlow Version (if applicable):
PyTorch Version (if applicable):
Baremetal or Container (if container which image + tag):

Relevant Files

Please attach or include links to any models, data, files, or scripts necessary to reproduce your issue. (Github repo, Google Drive, Dropbox, etc.)

Steps To Reproduce

Please include:

  • Exact steps/commands to build your repro
  • Exact steps/commands to run your repro
  • Full traceback of errors encountered



Sorry, we do not have inputs on this.
You can also check out StyleGAN 3 implementation from NVIDIA if you’re interested.

Thank you.