Skip to content

This is the onnxruntime inference code for GFP-GAN: Towards Real-World Blind Face Restoration with Generative Facial Prior (CVPR 2021). Official code: https://github.com/TencentARC/GFPGAN

Notifications You must be signed in to change notification settings

xuanandsix/GFPGAN-onnxruntime-demo

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

4 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

GFPGAN-onnxruntime-demo

This is the onnxruntime inference code for GFP-GAN: Towards Real-World Blind Face Restoration with Generative Facial Prior (CVPR 2021). Official code: https://github.com/TencentARC/GFPGAN

The following issues are addressed:

1、noise = out.new_empty(b, 1, h, w).normal_() in stylegan2_clean_arch.py can‘t be supported in ONNX. I move it out the Model class, like noise = Noise[i], the Noise is a list or others which prestores generated random noise.

2、the forward function of Model is very bad, especially stylegan, so many " if else " and class be reused. Like the StyleConv " in "useself.style_convs.append StyleConv ...". So I rewrite and make it in single forward.

convert torch to onnx.

wget https://github.com/TencentARC/GFPGAN/releases/download/v1.3.0/GFPGANv1.3.pth

python torch2onnx.py  --src_model_path ./GFPGANv1.3.pth --dst_model_path ./GFPGANv1.3.onnx --img_size 512 

run onnx demo.

python demo_onnx.py --model_path GFPGANv1.3.onnx --image_path ./cropped_faces/Adele_crop.png --save_path Adele_v3.jpg
input output

About

This is the onnxruntime inference code for GFP-GAN: Towards Real-World Blind Face Restoration with Generative Facial Prior (CVPR 2021). Official code: https://github.com/TencentARC/GFPGAN

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages