This project provides code for performing inference with BiRefNet using TensorRT. The aim is to accelerate the inference process by leveraging the high-performance capabilities of TensorRT.

Note:

1. Both the PyTorch and ONNX models are from the official BiRefNet GitHub.
2. The TensorRT model was converted using Convert-ONNX-Model-to-TensorRT-Engine.
3. All tests were conducted on a Win10 system with an RTX 4080 Super.
4. Refer to model_compare.py for the conversion code.

• Efficient inference with BiRefNet using TensorRT
• foreground estimate
• colab example
• Performance comparison between PyTorch, ONNX, and TensorRT inference
• Inference using Docker for an isolated and reproducible environment

• NVIDIA GPU with CUDA(>=11.X) and Cudnn(>=8.X)
• Python 3.9

pip install -r requirements.txt

First, download onnx model from Google Drive

second, convert your ONNX model to a TensorRT engine using the provided conversion script:

from utils import convert_onnx_to_engine
onnx_file_path = "birefnet.onnx"
engine_file_path = "engine.trt"
convert_onnx_to_engine(onnx_file_path, engine_file_path)

Now, you can run inference using the TensorRT engine with the following command:

 python .\infer.py --image-path image_path --output-path result.png --output-alpha-path result_alpha.png --engine-path .\engine.trt

python .\infer.py --image-path image_dir --output-path output_dir --output-alpha-path alpha_dir --engine-path .\engine.trt --mode m

Contributions are welcome! Please feel free to submit a Pull Request or open an Issue if you have any suggestions or find bugs.

1. Birefnet
2. fast-foreground-estimation