1. Introduction

This section introduces Tiny ML ModelZoo, Texas Instruments’ toolchain for developing machine learning models on microcontrollers.

Contents

• 1.1. What is Tiny ML ModelZoo?
  • 1.1.1. Overview
  • 1.1.2. Target Applications
  • 1.1.3. Key Capabilities
  • 1.1.4. What’s New in 1.5.0
  • 1.1.5. Repository Structure
  • 1.1.6. Workflow Summary
  • 1.1.7. Next Steps
• 1.2. System Architecture
  • 1.2.1. High-Level Architecture
  • 1.2.2. Packages and How They Are Delivered
  • 1.2.3. Component Details
  • 1.2.4. Which Install Do I Need?
  • 1.2.5. Data Flow
  • 1.2.6. Configuration System
  • 1.2.7. Integration Points
• 1.3. Terminology
  • 1.3.1. General ML Terms
  • 1.3.2. Tiny ML ModelZoo Terms
  • 1.3.3. Device and Hardware Terms
  • 1.3.4. Configuration Terms
  • 1.3.5. Model Size Conventions
  • 1.3.6. Abbreviations

1.4. Overview

Tiny ML ModelZoo enables end-to-end machine learning workflows for embedded systems:

1. Data Preparation: format and preprocess your datasets

2. Model Training: train neural networks sized for MCUs

3. Model Optimization: quantize models for efficient deployment

4. Compilation: generate device-ready code with TI’s Neural Network Compiler

5. Deployment: run inference on TI microcontrollers

Note

Starting with 1.5.0, tinyml-modelzoo is the standalone, pip-installable entry point. It replaces cloning the full tinyml-tensorlab set of repositories used up to 1.4.0. See Installation.