Codeformer Tensorrt

• This repo provides a minimal TensorRT implementation of Codeformer in Python, enabling fast face restoration on images
• This implementation does not include preprocessing (face detection/alignment/cropping) and postprocessing (pasting the restored face on the original image)
• The model only performs inference on preprocessed images (e.g input.png), which need to be 512 x 512, with a face fully visible.
• You can expect a 2x speedup on the inference

⏱️ Performance

Device	Model Input (WxH)	Inference Time(ms)
A10G	512 x 512	23

Note

Inference was conducted using FP16 precision, with a warm-up period of 10 frames. The reported time corresponds to the last inference.

🛠️ Building Tensorrt Engine

1. Download the codeformer onnx model

2. Run the following command

   trtexec --onnx=codeformer.onnx --saveEngine=codeformer.engine --fp16

⚡ Inference

git clone https://github.com/yuvraj108c/Codeformer-Tensorrt.git
pip install -r requirements.txt
python inference.py --input ./input.png --engine ./codeformer.engine --output ./output.png

🤖 Environment tested

• Ubuntu 22.04 LTS, Cuda 12.3, Tensorrt 8.6.1, Python 3.10, A10G GPU
• Windows (Not tested)

👏 Credits

• sczhou/CodeFormer