GstInference GStreamer example pipelines with hierarchical metadata

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

Sample pipelines

The following section contains a tool for generating simple GStreamer pipelines with one model of a selected architecture using our hierarchical inference metadata. If you are using and older version, you can check the legacy pipelines section. Please make sure to check the documentation to understand the property usage for each element.

The required elements are:

• Backend
• Model
• Model location
• Labels
• Source
• Sink

The optional elements include:

• inferencefilter
• inferencrop
• inferenceoverlay

Error creating thumbnail: Unable to save thumbnail to destination

Detection with new metadata

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

Sample pipelines

The following section contains a tool for generating simple GStreamer pipelines with one model of a selected architecture using our hierarchical inference metadata. If you are using and older version, you can check the legacy pipelines section. Please make sure to check the documentation to understand the property usage for each element.

The required elements are:

• Backend
• Model
• Model location
• Labels
• Source
• Sink

The optional elements include:

• inferencefilter
• inferencrop
• inferenceoverlay

Error creating thumbnail: Unable to save thumbnail to destination

Detection with new metadata

Pipeline Generator

The following tool will provide simple pipelines according to the selected elements.

Platform

Select your platform PC Jetson

Backend

Select your backend EdgeTPU TFLite TensorFlow TensorRT ONNXRT ONNXRT ACL ONNXRT OpenVINO

Model

Select your architecture Inceptionv1 Inceptionv2 Inceptionv3 Inceptionv4 MobileNetv2 FaceNet TinyYolov2

Input layer

Output layer

Model location

Labels

Source

Select your source Image file Video file Camera stream (v4l2)

Sink

Select your sink fakesink xvimagesink

Optional utilites

The following elements are optional yet very useful. Check the documentation for more details on their properties.

Inference Filter

Inference Overlay

Pick a style Classic Dotted Dashed

Inference Crop

Reset Generate!