ONNX simple sample: Difference between revisions
Maumontero (talk | contribs) No edit summary |
Maumontero (talk | contribs) No edit summary |
||
Line 1: | Line 1: | ||
__TOC__ | __TOC__ | ||
= Introduction = | = Introduction = | ||
On this page, you are going to find the steps to install ONXX and ONXXRuntime and run a simple C/C++ example on Linux. This wiki page | On this page, you are going to find the steps to install ONXX and ONXXRuntime and run a simple C/C++ example on Linux. This wiki page describes the importance of ONNX models and how to use it. The goal is to provide you some examples. | ||
= Installing ONNX = | = Installing ONNX = | ||
You can | You can install ONNX from PyPI with the following command: | ||
<pre> | <pre> | ||
Line 19: | Line 19: | ||
= Installing ONNXRuntime = | = Installing ONNXRuntime = | ||
This guide builds the baseline CPU version of ONNXRuntime form source, to build it | This guide builds the baseline CPU version of ONNXRuntime form source, to build it use the following commands: | ||
<pre> | <pre> | ||
Line 32: | Line 32: | ||
</pre> | </pre> | ||
After install CMake run the following command | After install CMake run the following command to build onnxruntime: | ||
<pre> | <pre> | ||
Line 45: | Line 45: | ||
</pre> | </pre> | ||
Finally, copy the .so file to general lib path: | |||
<pre> | <pre> | ||
cp libonnxruntime.so /usr/lib/x86_64-linux-gnu/ | cp libonnxruntime.so /usr/lib/x86_64-linux-gnu/ | ||
Line 51: | Line 51: | ||
= Example = | = Example = | ||
This guide is for using an ONNXRuntime C/C++ code on Linux, for that reason only the SqueezeNet examples are | This guide is for using an ONNXRuntime C/C++ code on Linux, for that reason only the SqueezeNet examples are built it. | ||
== Build == | == Build == | ||
First go to the path with the C/C++ code examples. | First, go to the path with the C/C++ code examples. | ||
<pre> | <pre> | ||
cd onnxruntime/csharp/test/Microsoft.ML.OnnxRuntime.EndToEndTests.Capi/ | cd onnxruntime/csharp/test/Microsoft.ML.OnnxRuntime.EndToEndTests.Capi/ | ||
</pre> | </pre> | ||
After that build the code: | After that, build the code: | ||
<pre> | <pre> | ||
Line 67: | Line 67: | ||
== Run == | == Run == | ||
Finally just run the code: | Finally, just run the code: | ||
<pre> | <pre> |
Revision as of 16:57, 20 November 2019
Introduction
On this page, you are going to find the steps to install ONXX and ONXXRuntime and run a simple C/C++ example on Linux. This wiki page describes the importance of ONNX models and how to use it. The goal is to provide you some examples.
Installing ONNX
You can install ONNX from PyPI with the following command:
sudo pip install onnx
You can also build and install ONNX locally from source code:
git clone https://github.com/onnx/onnx.git cd onnx git submodule update --init --recursive python setup.py install
Installing ONNXRuntime
This guide builds the baseline CPU version of ONNXRuntime form source, to build it use the following commands:
git clone --recursive https://github.com/Microsoft/onnxruntime -b v1.0.0 cd onnxruntime
Before install onnxruntime you need to install CMake 3.13 or higher.
sudo -H pip3 install cmake
After install CMake run the following command to build onnxruntime:
./build.sh --config RelWithDebInfo --build_shared_lib --parallel
Finally, install it:
cd build/Linux/RelWithDebInfo sudo make install
Finally, copy the .so file to general lib path:
cp libonnxruntime.so /usr/lib/x86_64-linux-gnu/
Example
This guide is for using an ONNXRuntime C/C++ code on Linux, for that reason only the SqueezeNet examples are built it.
Build
First, go to the path with the C/C++ code examples.
cd onnxruntime/csharp/test/Microsoft.ML.OnnxRuntime.EndToEndTests.Capi/
After that, build the code:
g++ -o Capi_sample C_Api_Sample.cpp -I $PATHTOONNXRUNTIMESESSION (#CHOOSE THE APPROPRIATE PATH TO onnxruntime/include/onnxruntime/core/session) -lonnxruntime -std=c++14
Run
Finally, just run the code:
./Capi_sample
Running this example you will get the following output:
Using Onnxruntime C API Number of inputs = 1 Input 0 : name=data_0 Input 0 : type=1 Input 0 : num_dims=4 Input 0 : dim 0=1 Input 0 : dim 1=3 Input 0 : dim 2=224 Input 0 : dim 3=224 Score for class [0] = 0.000045 Score for class [1] = 0.003846 Score for class [2] = 0.000125 Score for class [3] = 0.001180 Score for class [4] = 0.001317 Done!