i.MX8 Deep Learning Reference Designs

Welcome to RidgeRun's guide to i.MX8 Deep Learning Reference Designs	i.MX8 Deep Learning Reference Designs Getting Started Environment Setup Evaluating the Project Purchasing a License Project Architecture High Level Design Reference Designs Restricted Zone Detector Customizing the Project Implementing Custom Inference Listener Implementing Custom Policies Implementing Custom Actions Implementing Custom Media Implementing a Custom Application Contact Us
i.MX8 Deep Learning Reference Designs
RidgeRun knows how important documentation is for your project, especially with Deep Learning Reference Designs. Regardless of the complexity of the technology, proper documentation can reduce the learning curve and, more importantly, the time-to-market of your product. This wiki is a user guide for our Deep Learning Reference Designs project. Introduction RidgeRun's I.MX8 Deep Learning Reference Designs is a project that provides a robust and modular design, based on the R2Inference and GstInference frameworks, where the building blocks may be replaced to fit a wide variety of use cases. The main objective is to provide an infrastructure for an application using video analytics to perform informed decisions within the application domain. The system could be divided into the following parts: Framework The framework is the main infrastructure responsible for driving the application state and logic. The framework is composed of 4 main sections: Camera Capture: In charge of controlling the media sources. AI Manager: This module will process the inference performed by GstInference defined by the application and forward the gathered information to the next component. Action Dispatcher: It uses the data coming from the inference carried out by GstInference to perform actions depending on the application policies. Both the actions and the policies are defined by the application. Config Parser: This module is in charge of loading the configuration parameters to set up the application before its execution. Application We focus on bringing a solution where the users only need to think about what are they looking for and not develop everything from scratch. With this project, you can define the camera source, restricted zones, and policies that serve as a filter for inference predictions. According to these policies, different actions may be executed, which are also user-defined. All the logic and mechanisms to execute all the user implementations are provided by the framework. In this wiki, you will find technical documentation, tutorials, examples, and much more! How to Purchase
RidgeRun Support
RidgeRun is an official NXP and NVIDIA Partner and we have created this extensive set of documentation to support our joint customers. If you have any questions on the content, please contact us through our contact us page. RidgeRun provides support for embedded Linux development for NXP and NVIDIA's platforms, specializing in the use of hardware accelerators in multimedia applications. This page contains detailed guides and information on how to get started with the I.MX8 Deep Learning Reference Designs and start using its full capabilities. To get up-to-speed with your I.MX8 Deep Learning Reference Designs, start by clicking below: Error creating thumbnail: Unable to save thumbnail to destination
RidgeRun Resources Quick Start Client Engagement Process RidgeRun Blog Homepage Technical and Sales Support RidgeRun Online Store RidgeRun Videos Contact Us Contact Us Visit our Main Website for the RidgeRun Products and Online Store. RidgeRun Engineering informations are available in RidgeRun Professional Services, RidgeRun Subscription Model and Client Engagement Process wiki pages. Please email to support@ridgerun.com for technical questions and contactus@ridgerun.com for other queries. Contact details for sponsoring the RidgeRun GStreamer projects are available in Sponsor Projects page.