For best experience this site requires Javascript to be enabled. To enable on your browser, follow our accessibility instructions.

Machine Learning on i.MX Applications Processors

About This Training

This session focuses on guided labs and demos of how to run TensorFlow Lite and DeepView RT inference engines using eIQ^®, and how to profile a quantized ML model on the i.MX 8M Plus.

This session is part of the AI and Machine Learning Training Academy developed to help you get to market faster with the NXP eIQ ML software development environment.

Training Outline and Presentations

eIQ Inference with TensorFlow^™ Lite for MPUs: Overview and Guided Lab

eIQ Inference with DeepViewRT for MPUs: Guided Lab

How to Bring Your Own Quantized Model and Profile on NPU/CPU

What You Will Learn

What TensorFlow Lite is
How to run inference using TensorFlow Lite on target
eIQ inference with DeepView RT
Steps to run an inference on a target (MPU)
Profile the quantized model on various compute engine of i.MX 8M Plus using eIQ Portal GUI interface