GstInference inferencecrop

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 element receives all the buffers, read the inference metadata and crop the elements that are enabled to process, it crops the image, creates a new buffer and copy the inference metadata of the element. This element uses GstInferenceMeta.

Detection crop example

GstInference inferencecrop properties

The inferencecrop element exposes the following properties to control the aspect ratio. These properties are documented in the following table:

Property	Value	Description
aspect-ratio	fraction [ 0/1, 2147483647/1]	Aspect ratio to crop the detections, width and height separated by '/'. If set to 0/1 it maintains the aspect ratio of each bounding box.

Example

For example, pipelines using inferencecrop element please check the Legacy pipelines section.