R2Inference/Getting started/Building the library

R2Inference
Introduction
Getting started
Getting the code Building the library
Supported backends
TensorFlow TensorFlow-Lite Caffe TensorRT Coral from Google ONNXRT ONNXRT ACL ONNXRT OpenVINO
Examples
TensorFlow TensorFlow-Lite TensorRT Coral from Google ONNXRT ONNXRT ACL ONNXRT OpenVINO
Model Zoo
Contact Us

Dependencies

R2Inference has the following dependencies:

• autoreconf
• automake
• pkg-config
• libtool
• gtk-doc-tools

In Ubuntu 16.04 based systems, you may install the dependencies with the following command:

sudo apt-get install -y autoreconf automake pkg-config libtool gtk-doc-tools

Install library

To build and install r2inference you can run the following commands:

Table 1. R2Inference configuration options

Configure Option	Description
--enable-ncsdk	Compile the library with NCSDK backend support
--enable-tensorflow	Compile the library with TensorFlow backend support

git clone -b dev-0.1 git@github.com:RidgeRun/r2inference.git
cd r2inference
./autogen.sh $OPTIONS # CHOOSE THE APPROPRIATE CONFIGURATION FROM THE TABLE ABOVE
make
make check
sudo make install

Verify

You can verify the library with a simple application:

#include <r2i/r2i.h>

int main (int argc, char *argv[]) {
  r2i::RuntimeError error;

  auto factory = r2i::IFrameworkFactory::MakeFactory(r2i::FrameworkCode::NCSDK, error);

  return error;
}

You can also check our examples page to get the examples included with the library running.