“Enabled by TinyML, ‘artificial intelligence of things’ is a natural evolution, where acting on data locally helps manage data privacy, latency and overall system reliability,” said Infineon v-p IoT Steve Tateosian. “ModusToolbox bridges a gap between machine learning and embedded systems design by providing tools and modular libraries to easily optimise, validate and deploy deep learning models from popular training frameworks on Infineon’s microcontrollers.”
The extension is ‘ModusToolbox ML’, which provides middleware, software libraries and tools for designers to evaluate and deploy deep learning-based machine learning models.
It allows a deep learning framework, such as TensorFlow, to be deployed directly to PSoC MCUs, according to Infineon, and it assists in optimisation for embedded platforms to reduce size and complexity, as well as validate performance against test data.
Includes is an embedded inference engine which supports optimised implementations of neural network operators such as 1D/2D convolutions, a variety of activation functions as well as support for more complex operators for RNN networks such as GRU.
ModusToolbox ML can be found through this page
Credit: Google News