Building ONNX Runtime

2021-01-08 less than 1 minute read

NVIDIA CUDA

单步构建

下载onnxruntime源代码

git clone --recursive https://github.com/microsoft/onnxruntime.git

拉取容器（编译环境）

docker pull nvidia/cuda:11.1-cudnn8-devel-ubuntu20.04

运行容器

docker run -it --name build-onnxruntime-gpu --runtime nvidia \
  -v $(pwd)/onnxruntime:/onnxruntime -w /onnxruntime \
  nvidia/cuda:11.1-cudnn8-devel-ubuntu20.04

更新apt镜像源

sed -i 's/archive.ubuntu.com/mirrors.aliyun.com/g' /etc/apt/sources.list
apt-get update

安装依赖包

apt-get install language-pack-en git cmake python3 python3-pip -y

修改语言环境

locale-gen en_US.UTF-8
update-locale LANG=en_US.UTF-8

更新pip镜像源

pip3 config set global.index-url https://mirrors.aliyun.com/pypi/simple/

安装numpy
```
pip3 install numpy
```

编译

./build.sh --parallel --build_shared_lib --enable_pybind --build_wheel \
  --use_cuda --cudnn_home /usr/include/x86_64-linux-gnu/ \
  --cuda_home /usr/local/cuda/ --config Release

安装

pip3 install /onnxruntime/build/Linux/Release/dist/onnxruntime_gpu-1.6.0-cp38-cp38-linux_x86_64.whl

测试
```
python -c "import onnxruntime"
```

自动化构建

Dockerfile ONNXRuntime GPU

NVIDIA CUDA

单步构建

自动化构建

参考资料