• Arm 32v7
• Build from source (CPU)
• CUDA + CUDNN
• nGraph
• TensorRT
• OpenVINO
• ONNX Runtime Server

1. Build the docker image from the Dockerfile in this repository.

# If you have a Linux machine, preface this command with "sudo"

docker build -t onnxruntime-source -f Dockerfile.source .

2. Run the Docker image

# If you have a Linux machine, preface this command with "sudo"

docker run -it onnxruntime-source

1. Build the docker image from the Dockerfile in this repository.

# If you have a Linux machine, preface this command with "sudo"

docker build -t onnxruntime-cuda -f Dockerfile.cuda .

2. Run the Docker image

# If you have a Linux machine, preface this command with "sudo"

docker run -it onnxruntime-cuda

1. Build the docker image from the Dockerfile in this repository.

# If you have a Linux machine, preface this command with "sudo"

docker build -t onnxruntime-ngraph -f Dockerfile.ngraph .

2. Run the Docker image

# If you have a Linux machine, preface this command with "sudo"

docker run -it onnxruntime-ngraph

1. Build the docker image from the Dockerfile in this repository.

# If you have a Linux machine, preface this command with "sudo"

docker build -t onnxruntime-trt -f Dockerfile.tensorrt .

2. Run the Docker image

# If you have a Linux machine, preface this command with "sudo"

docker run -it onnxruntime-trt

1. Build the onnxruntime image for all the accelerators supported as below

   Retrieve your docker image in one of the following ways.

   • For building the docker image, download OpenVINO online installer version 2019 R1.1 from here and copy the openvino tar file in the same directory and build the image. The online installer size is only 16MB and the components needed for the accelerators are mentioned in the dockerfile. Providing the argument device enables onnxruntime for that particular device. You can also provide arguments ONNXRUNTIME_REPO and ONNXRUNTIME_BRANCH to test that particular repo and branch. Default values are http://github.com/microsoft/onnxruntime and repo is master

     docker build -t onnxruntime --build-arg DEVICE=$DEVICE .
     

   • Pull the official image from DockerHub.

2. DEVICE: Specifies the hardware target for building OpenVINO Execution Provider. Below are the options for different Intel target devices.

   Device Option	Target Device
   CPU_FP32	Intel CPUs
   GPU_FP32	Intel Integrated Graphics
   GPU_FP16	Intel Integrated Graphics
   MYRIAD_FP16	Intel MovidiusTM USB sticks
   VAD-M_FP16	Intel Vision Accelerator Design based on MovidiusTM MyriadX VPUs

1. Retrieve your docker image in one of the following ways.

   • Build the docker image from the DockerFile in this repository.

     docker build -t onnxruntime-cpu --build-arg DEVICE=CPU_FP32 --network host .
     

   • Pull the official image from DockerHub.

     # Will be available with next release
     

2. Run the docker image

    docker run -it onnxruntime-cpu
   

1. Retrieve your docker image in one of the following ways.

   • Build the docker image from the DockerFile in this repository.

      docker build -t onnxruntime-gpu --build-arg DEVICE=GPU_FP32 --network host . 
     

   • Pull the official image from DockerHub.

       # Will be available with next release
     

2. Run the docker image

   docker run -it --device /dev/dri:/dev/dri onnxruntime-gpu:latest
   

1. Retrieve your docker image in one of the following ways.
   • Build the docker image from the DockerFile in this repository.

      docker build -t onnxruntime-myriad --build-arg DEVICE=MYRIAD_FP16 --network host . 
     

   • Pull the official image from DockerHub.

      # Will be available with next release
     

2. Install the Myriad rules drivers on the host machine according to the reference in here
3. Run the docker image by mounting the device drivers

   docker run -it --network host --privileged -v /dev:/dev  onnxruntime-myriad:latest
   
   

1. Retrieve your docker image in one of the following ways.
   • Build the docker image from the DockerFile in this repository.

      docker build -t onnxruntime-vadr --build-arg DEVICE=VAD-M_FP16 --network host . 
     

   • Pull the official image from DockerHub.

      # Will be available with next release
     

2. Install the HDDL drivers on the host machine according to the reference in here
3. Run the docker image by mounting the device drivers

   docker run -it --device --mount type=bind,source=/var/tmp,destination=/var/tmp --device /dev/ion:/dev/ion  onnxruntime-hddl:latest
   
   

1. Build the docker image from the Dockerfile in this repository

docker build -t {docker_image_name} -f Dockerfile.server .

2. Run the ONNXRuntime server with the image created in step 1

docker run -v {localModelAbsoluteFolder}:{dockerModelAbsoluteFolder} -e MODEL_ABSOLUTE_PATH={dockerModelAbsolutePath} -p {your_local_port}:8001 {imageName}

3. Send HTTP requests to the container running ONNX Runtime Server

Send HTTP requests to the docker container through the binding local port. Here is the full usage document.

curl  -X POST -d "@request.json" -H "Content-Type: application/json" http://0.0.0.0:{your_local_port}/v1/models/mymodel/versions/3:predict