Contents Menu Expand Light mode Dark mode Auto light/dark, in light mode Auto light/dark, in dark mode Skip to content
eIQ® Training Materials
Logo
eIQ® Training Materials

Guides

  • Getting Started
    • Releases
  • Deployment
    • PyTorch Models
    • TensorFlow Models
    • Deployment to i.MX 93
    • Deployment to eIQ Neutron NPU
  • Conversion & Quantization
    • PyTorch to ONNX
    • ONNX Quantization
    • ONNX to TF Lite
    • TensorFlow to TF Lite
    • Converting for i.MX 93
    • Converting for eIQ Neutron NPU
  • Profiling
    • On-device Profiling
      • i.MX 8M Plus
      • i.MX 95
    • Simulated Profiling
      • i.MX 9x with eIQ Neutron NPU
      • i.MX 93
    • Microcontrollers

Tools

  • eIQ AI Hub
    • Upload Your Models
    • Upload Your Dataset
    • Optimize the Model
    • Run Simulated Profiling
    • Run MCU Profiling
    • On-Device Profiling
    • Benchmark the Model
    • Device Management
    • User Profile
    • eIQ Watermarking Extension
      • Command-Line Interface (CLI)
      • Walkthrough
  • eIQ AI Toolkit
    • Quickstart
    • Video Tutorials
    • Releases
  • eIQ Neutron SDK
    • Software Tools
      • Neutron Converter
      • Neutron Runner
      • TF Lite Extractor
      • TF Lite Optimizer
      • TF Lite Profiler
      • TF Lite Quantizer
    • User Guide
      • Run-time Update
      • Yocto BSP Compatibility Matrix
      • MCUXpresso SDK Compatibility Matrix
    • Software Stack
      • Model Deployment Flow
      • Runtime Components
        • eIQ Neutron-S
        • eIQ Neutron
      • Inference Execution Flows
        • eIQ Neutron-S
        • eIQ Neutron
  • eIQ Olive
    • Installation
    • Command Line Usage
  • eIQ ONNX2TFLite
    • Installation
    • ONNX Quantization
    • Conversion from ONNX to TF Lite
  • eIQ Vela for i.MX 93
    • Installation
    • Command Line Usage
Back to top
Copyright © 2026 NXP
Made with Sphinx and @pradyunsg's Furo