saymrwulf/onnxruntime
1
0
Fork 0
mirror of https://github.com/saymrwulf/onnxruntime.git synced 2026-07-30 20:18:08 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Updates to CUDA and TensorRT dockerfiles for v0.5.0 (#1731)

Browse source 
* updates to cuda and tensorrt dockerfiles for v0.5.0

* add table of build tags
This commit is contained in:
Vinitra Swamy 2019-09-13 14:16:47 -07:00 committed by GitHub
parent 634f554471
commit 2a21df2309
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
5 changed files with 45 additions and 34 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

11
dockerfiles/Dockerfile.cuda
View file

@ -4,8 +4,8 @@
# --------------------------------------------------------------
# Dockerfile to run ONNXRuntime with CUDA, CUDNN integration
# nVidia cuda 10.0 Base Image
FROM nvidia/cuda:10.0-cudnn7-devel
# nVidia cuda 10.1 Base Image
FROM nvidia/cuda:10.1-cudnn7-devel
MAINTAINER Vinitra Swamy "viswamy@microsoft.com"
ARG ONNXRUNTIME_REPO=https://github.com/Microsoft/onnxruntime
@ -17,10 +17,9 @@ RUN apt-get update &&\
WORKDIR /code
ENV PATH /usr/local/nvidia/bin:/usr/local/cuda/bin:/code/cmake-3.14.3-Linux-x86_64/bin:/opt/miniconda/bin:${PATH}
# Prepare onnxruntime repository & build onnxruntime with TensorRT
ADD scripts /tmp/scripts
RUN /bin/sh /tmp/scripts/install_common_deps.sh && \
git clone --single-branch --branch ${ONNXRUNTIME_SERVER_BRANCH} --recursive ${ONNXRUNTIME_REPO} onnxruntime &&\
# Prepare onnxruntime repository & build onnxruntime with CUDA
RUN git clone --single-branch --branch ${ONNXRUNTIME_SERVER_BRANCH} --recursive ${ONNXRUNTIME_REPO} onnxruntime &&\
/bin/sh onnxruntime/dockerfiles/scripts/install_common_deps.sh &&\
cp onnxruntime/ThirdPartyNotices.txt /code/ThirdPartyNotices.txt &&\
cp onnxruntime/dockerfiles/LICENSE-IMAGE.txt /code/LICENSE-IMAGE.txt &&\
cd onnxruntime &&\

5
dockerfiles/Dockerfile.openvino
View file

@ -56,9 +56,8 @@ ENV LANG en_US.UTF-8
WORKDIR /code
ENV PATH /opt/miniconda/bin:/code/cmake-3.14.3-Linux-x86_64/bin:$PATH
ADD scripts /tmp/scripts
RUN /bin/sh /tmp/scripts/install_common_deps.sh && \
git clone --recursive -b $ONNXRUNTIME_BRANCH $ONNXRUNTIME_REPO /onnxruntime && \
RUN git clone --recursive -b $ONNXRUNTIME_BRANCH $ONNXRUNTIME_REPO /onnxruntime && \
/bin/sh onnxruntime/dockerfiles/scripts/install_common_deps.sh && \
cd /onnxruntime/cmake/external/onnx && python3 setup.py install && \
cp /onnxruntime/dockerfiles/LICENSE-IMAGE.txt /code/LICENSE-IMAGE.txt && \
cp /onnxruntime/ThirdPartyNotices.txt /code/ThirdPartyNotices.txt && \

5
dockerfiles/Dockerfile.source
View file

@ -17,10 +17,9 @@ RUN apt-get update &&\
WORKDIR /code
ENV PATH /opt/miniconda/bin:/code/cmake-3.14.3-Linux-x86_64/bin:${PATH}
ADD scripts /tmp/scripts
# Prepare onnxruntime repository & build onnxruntime
RUN /bin/sh /tmp/scripts/install_common_deps.sh &&\
git clone --single-branch --branch ${ONNXRUNTIME_SERVER_BRANCH} --recursive ${ONNXRUNTIME_REPO} onnxruntime &&\
RUN git clone --single-branch --branch ${ONNXRUNTIME_SERVER_BRANCH} --recursive ${ONNXRUNTIME_REPO} onnxruntime &&\
/bin/sh onnxruntime/dockerfiles/scripts/install_common_deps.sh &&\
cd onnxruntime &&\
/bin/sh ./build.sh --config Release --build_wheel --update --build --cmake_extra_defines ONNXRUNTIME_VERSION=$(cat ./VERSION_NUMBER) &&\
pip install /code/onnxruntime/build/Linux/Release/dist/*.whl &&\

7
dockerfiles/Dockerfile.tensorrt
View file

@ -5,7 +5,7 @@
# Dockerfile to run ONNXRuntime with TensorRT integration
# nVidia TensorRT Base Image
FROM nvcr.io/nvidia/tensorrt:19.02-py3
FROM nvcr.io/nvidia/tensorrt:19.06-py3
MAINTAINER Vinitra Swamy "viswamy@microsoft.com"
ARG ONNXRUNTIME_REPO=https://github.com/Microsoft/onnxruntime
@ -17,10 +17,9 @@ RUN apt-get update &&\
WORKDIR /code
ENV PATH /usr/local/nvidia/bin:/usr/local/cuda/bin:/code/cmake-3.14.3-Linux-x86_64/bin:/opt/miniconda/bin:${PATH}
ADD scripts /tmp/scripts
# Prepare onnxruntime repository & build onnxruntime with TensorRT
RUN /bin/sh /tmp/scripts/install_common_deps.sh && \
git clone --single-branch --branch ${ONNXRUNTIME_SERVER_BRANCH} --recursive ${ONNXRUNTIME_REPO} onnxruntime &&\
RUN git clone --single-branch --branch ${ONNXRUNTIME_SERVER_BRANCH} --recursive ${ONNXRUNTIME_REPO} onnxruntime &&\
/bin/sh onnxruntime/dockerfiles/scripts/install_common_deps.sh &&\
cp onnxruntime/dockerfiles/LICENSE-IMAGE.txt /code/LICENSE-IMAGE.txt &&\
cp onnxruntime/ThirdPartyNotices.txt /code/ThirdPartyNotices.txt &&\
cd onnxruntime &&\

51
dockerfiles/README.md
View file

@ -1,5 +1,7 @@
# Docker containers for ONNX Runtime
#### Build Instructions
- [Arm 32v7](Dockerfile.arm32v7)
- [Build from source (CPU)](Dockerfile.source)
- [CUDA + CUDNN](Dockerfile.cuda)
@ -9,7 +11,20 @@
- [ONNX Runtime Server](Dockerfile.server)
- [Nuphar](Dockerfile.nuphar)
**Preparation step:** download `scripts` to your local folder before running the `docker build` command for any of the options below.
#### Published Microsoft Container Registry (MCR) Images
Use `docker pull` with any of the images and tags below to pull an image and try for yourself. Note that the build from source (CPU), CUDA, and TensorRT images include additional dependencies like miniconda for compatibility with AzureML image deployment.
**Example**: Run `docker pull mcr.microsoft.com/azureml/onnxruntime:latest-cuda` to pull the latest released docker image with ONNX Runtime GPU, CUDA, and CUDNN support.
| Build Flavor | Base Image | ONNX Runtime Docker Image tags | Latest |
|-------------------|---------------------------------------|--------------------------------------------------|------------------|
| Source (CPU) | mcr.microsoft.com/azureml/onnxruntime | :v0.4.0, :v0.5.0 | :latest |
| CUDA (GPU) | mcr.microsoft.com/azureml/onnxruntime | :v0.4.0-cuda10.0-cudnn7, :v0.5.0-cuda10.1-cudnn7 | :latest-cuda |
| TensorRT (x86) | mcr.microsoft.com/azureml/onnxruntime | :v0.4.0-tensorrt19.03, :v0.5.0-tensorrt19.06 | :latest-tensorrt |
| OpenVino (VAD-M) | mcr.microsoft.com/azureml/onnxruntime | TBA | TBA |
| OpenVino (MYRIAD) | mcr.microsoft.com/azureml/onnxruntime | TBA | TBA |
| Server | mcr.microsoft.com/onnxruntime/server | :v0.4.0, :v0.5.0 | :latest |
## Build from Source
#### Linux 16.04, CPU, Python Bindings
@ -86,7 +101,7 @@
## OpenVINO (Public Preview)
#### Linux 16.04, Python Bindings
1. Build the onnxruntime image for all the accelerators supported as below
1. Build the onnxruntime image for all the accelerators supported as below
Retrieve your docker image in one of the following ways.
@ -95,7 +110,7 @@
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.
@ -107,12 +122,12 @@
| <code>MYRIAD_FP16</code> | Intel<sup></sup> Movidius<sup>TM</sup> USB sticks |
| <code>VAD-M_FP16</code> | Intel<sup></sup> Vision Accelerator Design based on Movidius<sup>TM</sup> MyriadX VPUs |
## CPU
## CPU
1. Retrieve your docker image in one of the following ways.
- Build the docker image from the DockerFile in this repository.
- Build the docker image from the DockerFile in this repository.
```
docker build -t onnxruntime-cpu --build-arg DEVICE=CPU_FP32 --network host .
```
@ -127,10 +142,10 @@
## GPU
1. Retrieve your docker image in one of the following ways.
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 .
```
docker build -t onnxruntime-gpu --build-arg DEVICE=GPU_FP32 --network host .
```
- Pull the official image from DockerHub.
```
@ -141,12 +156,12 @@
```
docker run -it --device /dev/dri:/dev/dri onnxruntime-gpu:latest
```
## Myriad VPU Accelerator
## Myriad VPU Accelerator
1. Retrieve your docker image in one of the following ways.
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 .
```
docker build -t onnxruntime-myriad --build-arg DEVICE=MYRIAD_FP16 --network host .
```
- Pull the official image from DockerHub.
```
@ -159,12 +174,12 @@
```
=======
## VAD-M Accelerator Version
## VAD-M Accelerator Version
1. Retrieve your docker image in one of the following ways.
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 .
```
docker build -t onnxruntime-vadr --build-arg DEVICE=VAD-M_FP16 --network host .
```
- Pull the official image from DockerHub.
```
@ -212,4 +227,4 @@
# If you have a Linux machine, preface this command with "sudo"
docker run -it onnxruntime-nuphar
```
```