Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

Pure PyTorch implementation in a fork #2

Open
14 of 15 tasks
filonenkoa opened this issue Aug 14, 2023 · 0 comments
Open
14 of 15 tasks

Pure PyTorch implementation in a fork #2

filonenkoa opened this issue Aug 14, 2023 · 0 comments

Comments

@filonenkoa
Copy link

filonenkoa commented Aug 14, 2023 •
edited
Loading

Hello everyone.

I've forked this repository and removed the PyTorch Lightning leaving pure PyTorch approach to have a better control of the training process. In case someone also wants to expand Runou Yang's work, feel free to join https://github.com/filonenkoa/FAS-LatentDistributionAdjusting

Improvements to the original repository

  • Transfer from PyTorch Lightning to vanilla PyTorch
  • EfficientFormerV2 support
  • FastViT support
  • Use config files
  • Data augmentations
  • TurboJPEG support for faster image decoding
  • Multiple datasets training
  • Compute FAS-related metrics (ACER, etc.)
  • Telegram reports
  • Compute metrics for each val dataset separately
  • Split validation into miltiple GPUs
  • Balanced sampler suitable for DDP
  • Reparametrization efficiency evaluation for supported models
  • FP16/AMP support
  • Conversion to ONNX
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees
No one assigned
Labels
None yet
Projects
None yet
Milestone
No milestone
Development

No branches or pull requests
1 participant
@filonenkoa