Building the GstInference plugin

GstInference
Introduction
Getting started
Getting the code Building the plugin Quick Starting Guide
Supported architectures
InceptionV1 InceptionV2 InceptionV3 InceptionV4 TinyYoloV2 TinyYoloV3 YoloV2 ResNetV1 MobileNetV2 MobileNetV2 + SSD AlexNet
Supported backends
TensorFlow Tensorflow-Lite Coral from Google Caffe TensorRT ONNXRT ONNXRT ACL ONNXRT OpenVINO
Metadata and Signals
GstClassificationMeta GstEmbeddingMeta GstDetectionMeta GstInferenceMeta Signals
Overlay Elements
Inference Overlay
Utils Elements
InferenceFilter InferenceCrop InferenceDebug InferenceBin
Legacy pipelines
PC NANO TX2 Xavier IMX8
Example pipelines
Example applications
Classification Detection Hand Pose Recognition
Benchmarks
Model Zoo
Project Status
Releases Roadmap
Contact Us

This page provides a guide to build and install GstInference

Dependencies

System Dependencies

GstInference has the following system dependencies:

• pkg-config
• gtk-doc-tools
• libgstreamer1.0-dev
• libgstreamer-plugins-base1.0-dev
• gstreamer1.0-tools
• gstreamer1.0-plugins-good
• gstreamer1.0-libav
• opencv 3.3.1*

Also, GstInference makes use of the Meson build system.

Note: OpenCV is only needed if you wish to build the overlay elements.

Linux

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

sudo apt-get install -y python3 python3-pip python3-setuptools python3-wheel ninja-build pkg-config gtk-doc-tools libgstreamer1.0-dev libgstreamer-plugins-base1.0-dev  gstreamer1.0-tools gstreamer1.0-plugins-good gstreamer1.0-libav libopencv-dev

Then, use pip3 to install the latest version of Meson directly from its repository.

sudo -H pip3 install git+https://github.com/mesonbuild/meson.git

R2Inference

To build GstInference you need to install R2Inference.

To install R2Inference please check R2Inference Build Instructions

Build Plugin

Linux

Note: If you are using Edge TPU backend with Google Coral the /usr/local/lib directory is not included by default in the linking path, hence we need to include it before building.

export LD_LIBRARY_PATH=$LD_LIBRARY_PATH:/usr/local/lib/

export LD_LIBRARY_PATH=/usr/local/lib/x86_64-linux-gnu:$LD_LIBRARY_PATH

git clone https://github.com/RidgeRun/gst-inference.git
cd gst-inference
meson build --prefix /usr
ninja -C build
ninja -C build test
sudo ninja -C build install

Note: If you are building GstInference in the Coral Dev Kit consider using ninja -C build -j 1 if you have troubles related to memory consumption.

Yocto

GstInference is available at Ridgerun's meta-layer, please check our recipes here. Actually, only i.MX8 platforms are supported with Yocto.

First, create a Yocto environment for i.MX8, this i.MX8 dedicated wiki has more information to setup up a Yocto environment.

i.MX8 Yocto guide here.

In your Yocto sources folder, run the following command

git clone https://github.com/RidgeRun/meta-ridgerun.git

Enable RidgeRun's meta-layer in your conf/bblayers.conf file by adding the following line.

  ${BSPDIR}/sources/meta-ridgerun \

Enable Prebuilt-TensorFlow, R2Inference and GstInference in your conf/local.conf.

  IMAGE_INSTALL_append = "prebuilt-tensorflow r2inference gst-inference"

Finally, build your desired image, the previous steps added GstInference and its requirements into your Yocto image.

Verify Installation

The plugin installation can be verified by running:

gst-inspect-1.0 inference

In case of any error, please contact support@ridgerun.com with the following output, modify path according to your architecture:

gst-inspect-1.0 /usr/lib/x86_64-linux-gnu/gstreamer-1.0/libgstinference.so