eIQ® Auto Machine Learning (ML) Toolkit

eIQ-AUTO-ML-TOOLKIT

Diagram

Choose a diagram:

eIQ Auto Development

eIQ Auto Development

eIQ Auto ML Toolkit

eIQ Auto ML Toolkit

Features

Key Features

  • Seamless deployment of ML algorithms to embedded
  • High-performance inference
  • Automotive qualified machine learning (ML) runtime software stack, including accelerator backends
  • Heterogeneous multi-core processing
  • Portability across S32 MCUs/MPUs
  • User-defined operations capable
  • Model Zoo
  • Auto ML support

Offline Tools

  • Import models trained from PyTorch, TensorFlow/Keras, MATLAB®
  • Hardware target selection and model optimization tools
  • Integrated model compilation support
  • x86 simulation and model evaluation

Runtime API

  • Single API independent of backend
  • Heterogeneous computation

Runtime Backend

  • eIQ Auto automotive quality backend
  • ONNX® runtime
  • TFLite
  • TFLite Micro
  • User-defined backend

Model Zoo Applications

  • Battery management
  • Predictive maintenance
  • Intrusion detection
  • Driver monitoring and Identification
  • Keyword porting
  • Speech classification

Supported Devices

  • S32K3: S32K3 Microcontrollers for Automotive General Purpose
  • S32E2: S32E2 Safe and Secure High-Performance Real-Time Processors with Actuation Support
  • S32G3: S32G3 Processors for Vehicle Networking
  • S32Z2: S32Z2 Safe and Secure High-Performance Real-Time Processors
  • S32G2: S32G2 Processors for Vehicle Networking

System Requirements

Design Resources

Select a section:

Hardware

1-5 of 10 hardware offerings

Show All

Training

1 trainings

Support

What do you need help with?