デザイン・センター
トレーニング
Develop ML Applications with the Glow Neural Network Compiler and TensorFlow Lite for i.MX RT Crossover MCUs

Develop ML Applications with the Glow Neural Network Compiler and TensorFlow Lite for i.MX RT Crossover MCUs

About This Training

Machine learning is a rapidly growing field, especially as deep learning moves to the edge and more and more engineers build applications that include some form of vision- or voice-based machine learning technology. The number of deep learning frameworks, tools and other capabilities that have become available to allow developers to build and deploy neural network models continues to expand. TensorFlow Lite, as an inference engine, is one such example of a deep learning tool that has gained tremendous popularity in recent years. A relative newcomer to this field is Glow, the open source neural network compiler.

This session explores the trade-offs and features of TensorFlow Lite and the Glow NN compiler, with a focus on how to target these technologies for MCUs to work within the various resource constraints such as memory and power.

Presentation

Develop ML Applications with the Glow Neural Network Compiler and TensorFlow Lite for i.MX RT Crossover MCUs

What You Will Learn

Explore use cases for machine learning on the edge with i.MX RT MCUs
Discover TensorFlow Lite and Glow neural network features and benefits
How to use eIQ^® for TensorFlow Lite for embedded systems
How to use eIQ for Glow neural network compiler tools for embedded systems

Presented by

Markus Levy
Director of AI and Machine Learning Technologies, NXP Semiconductors
Anthony Huereca
Systems Engineer, NXP Semiconductors

続きを表示非表示にする

期間

1 hr 2 min

言語

英語

スキルレベル

初級編

0閲覧数0いいね

We are looking for ways to improve.

アンケートに答える。

Additional Resources

Have a question? Ask the community.

Ask our i.MX RT community and get expert advice.

Stay In the Loop

Subscribe to our newsletter to stay updated with our latest developments and if you need further assistance, we are here to help.

Subscribe Contact Support