GstInference is a GStreamer plugin that allows easy integration of deep learning models with GStreamer pipelines for inference tasks. RidgeRun has extended the GstInference functionality to support multiple execution providers available in ONNX Runtime. The execution providers enable hardware acceleration into the ONNX Runtime baseline operation. One of those execution providers is based on the Arm Compute Library (ACL), which is an extensive library for optimized functions for the Arm Cortex-A family of CPU processors and the Arm Mali family of GPUs.
Figure 1. Object Detection. Source: Wikipedia Commons.
Check out the following guides from RidgeRun:
Any Questions? : support@ridgerun.com
Contact Us:
Visit our Main Website for the RidgeRun online store and pricing information of the RidgeRun products and Professional Services. Please email support@ridgerun.com for technical questions. Contact details for sponsoring the RidgeRun GStreamer projects are available at Sponsor Projects page.