GstInference/Example Applications

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 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 section provides a series of applications that exemplify how to use GstInference in an application. They also serve as placeholders for extending the prediction with custom logic.

Classification

An example using InceptionV4 to classify the frames from a video file in one of the 1000 possible classes. The example provides a placeholder for external code.

Detection

An example using TinyYoloV2 that receives an input video file and detects objects in each buffer. There are 20 different possible objects to detect.

DispTec

A quick and easy guide to get a simple GstInference example running on either a computer running Ubuntu 18.04 or a NVIDIA Jetson TX2.