Fork of ZHKKKe/MODNet

Differences between original repository and fork:

• Compatibility with PyTorch >=2.1. (🔥)
• Original pretrained models and converted ONNX models from GitHub releases page. (🔥)
• Installation with requirements.txt file.
• ONNX Simplifier integration in the export_onnx.py file.
• Minor modifications in the inference.py file.
• The following errors has been fixed:
  • AttributeError: module 'onnx' has no attribute 'load_from_string'.

Installation

pip install -r requirements.txt

Pretrained models

Name	Link
MODNet (Photographic)	PyTorch, ONNX
MODNet (Webcam)	PyTorch, ONNX

Inference

python -m demo.image_matting.colab.inference --ckpt-path pretrained/modnet_photographic_portrait_matting.ckpt --image-path data/images/test.jpg --output-path result.jpg

Export to ONNX format

pip install onnx onnxsim

python -m onnx_model.export_onnx --ckpt-path pretrained/modnet_photographic_portrait_matting.ckpt --output-path pretrained/modnet_photographic_portrait_matting.onnx
python -m onnx_model.export_onnx --ckpt-path pretrained/modnet_webcam_portrait_matting.ckpt --output-path pretrained/modnet_webcam_portrait_matting.onnx

ONNX inference

python -m onnx_model.inference_onnx --model-path pretrained/modnet_photographic_portrait_matting.onnx --image-path data/images/test.jpg --output-path result.jpg