openeuler/onnxruntime repository overview

⁠Quick reference

• The official ONNX Runtime docker image.

• Maintained by: openEuler CloudNative SIG⁠.

• Where to get help: openEuler CloudNative SIG⁠, openEuler⁠.

⁠ONNX Runtime | openEuler

ONNX Runtime is a cross-platform inference and training machine-learning accelerator. ONNX Runtime inference can enable faster customer experiences and lower costs, supporting models from deep learning frameworks such as PyTorch and TensorFlow/Keras as well as classical machine learning libraries such as scikit-learn, LightGBM, XGBoost, etc. ONNX Runtime is compatible with different hardware, drivers, and operating systems, and provides optimal performance by leveraging hardware accelerators where applicable alongside graph optimizations and transforms.

Learn more about on ONNX Runtime Website⁠.

⁠Supported tags and respective Dockerfile links

The tag of each ONNX Runtime docker image is consist of the complete software stack version. The details are as follows

⁠Usage

In this usage, users can select the corresponding {Tag} and container startup options based on their requirements.

• Pull the openeuler/onnxruntime image from docker

  docker pull openeuler/onnxruntime:{Tag}
  

  Copy

• Start a container

  docker run -it --name my-onnxruntime openeuler/onnxruntime:{Tag}
  

  Copy

• Container startup options

  Option	Description
  --name my-onnxruntime	Names the container my-onnxruntime.
  -it	Starts the container in interactive mode with a terminal.
  openeuler/onnxruntime:{Tag}	Specifies the Docker image to run, replace {Tag} with the specific version tag.

• Verify ONNX Runtime installation

  docker run --rm openeuler/onnxruntime:{Tag} python3 -c "import onnxruntime; print(onnxruntime.__version__)"
  

  Copy

• To get an interactive shell

  docker exec -it my-onnxruntime /bin/bash
  

  Copy

⁠Question and answering

If you have any questions or want to use some special features, please submit an issue or a pull request on openeuler-docker-images⁠.