Tiny ML ModelZoo User Guide
Welcome to the Tiny ML ModelZoo documentation! This guide covers Texas Instruments’ end-to-end AI toolchain for developing, training, optimizing, and deploying machine learning models on resource-constrained microcontrollers.
Note
This documentation is for Tiny ML ModelZoo version 1.5.0. Starting with 1.5.0,
tinyml-modelzoo is the standalone, pip-installable entry point to TI’s MCU AI
flow. It replaces cloning the full tinyml-tensorlab set of repositories.
The 1.4.0 documentation is still available as the
Tiny ML Tensorlab User Guide.
Quick Links
Models, examples, and configurations: your starting point for MCU AI development.
Install with one pip install of the wheel, or clone tinyml-modelzoo to add your own models.
Run the hello world example, understand the config YAML, and read the run output.
Ready-to-run examples: arc fault, motor bearing fault, wake word, radar and more.
Find your target TI MCU and learn about NPU acceleration options.
Copy the compiled model and golden vectors into an SDK example and verify on the board.
What is Tiny ML ModelZoo?
Tiny ML ModelZoo is Texas Instruments’ complete solution for bringing AI to microcontrollers. The toolchain enables you to:
Train machine learning models for time series, audio, image and radar tasks
Optimize models using quantization (2-bit, 4-bit, 8-bit, mixed precision) for embedded deployment
Compile models to run efficiently on TI MCUs, with optional NPU acceleration
Deploy models using Code Composer Studio (CCS) and the device SDK examples
Documentation Structure
- User Guide
Start with the Introduction to understand the toolchain architecture, then follow the Installation guide to set up your environment.
- Task Types
Learn about the different Supported Task Types supported and choose the right one for your application.
- Working with Data
The Bring Your Own Data (Bring Your Own Data) section explains dataset formats and preparation.
- Target Devices
Browse Supported Devices to find specifications and capabilities of the supported TI MCUs.
- Examples & Applications
The Examples & Applications section provides ready-to-run configurations for common applications.
- Advanced Features
Explore Features such as feature extraction, quantization, Neural Architecture Search and on-device training.
- Deployment
The Deployment section covers CCS integration and running models on devices.
- Edge AI Studio
Prefer a GUI? See Edge AI Studio Model Composer for our no-code web platform.
- Extending the Toolchain
The Bring Your Own Model (Bring Your Own Model) section covers adding custom models.