SDAA429A June   2026  – October 2026 MSPM0G5187

 

  1.   1
  2.   Abstract
  3.   Trademarks
  4. 1 Introduction
  5. 2 MSPM0G5187 with TinyEngine NPU
  6. 3 Edge AI Toolchains
    1. 3.1 TI Edge AI Studio
    2. 3.2 TI Tiny ML Tensorlab
    3. 3.3 TI Neural Network Compiler
  7. 4 Rapid Prototyping Through TI Edge AI Studio
    1. 4.1 Project Setup
    2. 4.2 Data Capture
      1. 4.2.1 Hardware Setup
      2. 4.2.2 Feature Overview
    3. 4.3 Data Import
      1. 4.3.1 Classification Task
      2. 4.3.2 Regression Task
      3. 4.3.3 Forecasting Task
      4. 4.3.4 Annotation List
    4. 4.4 Data Annotation
    5. 4.5 Model Training
      1. 4.5.1 Training Parameter
      2. 4.5.2 Toolchain Dependency
    6. 4.6 Performance Reports
    7. 4.7 Model Export
  8. 5 Advanced Development Through TI Tiny ML Tensorlab
    1. 5.1 Environment Setup
    2. 5.2 Data Acquisition
      1. 5.2.1 Data Retrieval
      2. 5.2.2 Data Validation
    3. 5.3 Model Architecture Iterative Refactoring
      1. 5.3.1 Baseline Implementation
      2. 5.3.2 Refactoring With PyTorch Built-in Modules
      3. 5.3.3 Data Pipeline Optimization
      4. 5.3.4 Transition to CNN Architecture
    4. 5.4 Model Export
    5. 5.5 Quantization-Aware Training
    6. 5.6 Model Compilation
  9. 6 Edge AI Application: Digit Recognition
    1. 6.1 LeNet-5 Variant CNN Model
    2. 6.2 NPU/CPU Performance Comparison
  10. 7 Edge AI Application: Waveform Classifier
    1. 7.1 Feature Extraction
    2. 7.2 Time-Series Classification Model
    3. 7.3 Model Memory Considerations
    4. 7.4 NPU/CPU Performance Comparison
  11. 8 Summary
  12. 9 References
  13. 10Revision History

3.2 TI Tiny ML Tensorlab

Tiny ML Tensorlab is Texas Instruments’ comprehensive AI toolchain for developing, training, optimizing, and deploying machine learning models on resource-constrained microcontrollers (MCUs), which enables users to:
  • Train machine learning models for time series and image classification tasks
  • Optimize models using quantization (2-bit, 4-bit, 8-bit) for embedded deployment
  • Compile models to run efficiently on TI MCUs, with optional NPU acceleration
  • Deploy models using Code Composer Studio (CCS)

The toolchain provides an end-to-end workflow that takes you from raw data to a compiled model running on a TI MCU. The toolchain handles:

  • Data Preparation & Feature Extraction: Automated formatting, preprocessing, and transformation of raw signals into high-dimensional features.
  • Model Training: Training of neural networks specifically architected for embedded resource constraints.
  • Model Optimization: Implementation of quantization-aware training (QAT) or post-training quantization (PTQ) to support 2-bit, 4-bit, and 8-bit weight precision.
  • Compilation: Generation of highly optimized, device-specific code via the TI Neural Network Compiler.
  • Performance Analysis: Comprehensive evaluation of model accuracy and inference metrics prior to hardware deployment.

TI Tiny ML Tensorlab supports the following Machine Learning (ML) task types:

Table 3-1 Tensorlab-Supported Task Types
Task TypeDescription
Time Series ClassificationCategorize time-series data into discrete classes (for example, fault detection, activity recognition)
Time Series RegressionPredict continuous values from time-series inputs (for example, torque estimation)
Time Series ForecastingPredict future values based on historical patterns (for example, temperature prediction)
Anomaly DetectionIdentify abnormal patterns using autoencoder-based models (for example, equipment monitoring)
Image ClassificationCategorize images into classes (for example, visual inspection, digit recognition)
Tensorlab supports a wide range of TI microcontrollers across several specialized families, including C2000 DSP, MSPM0, MSPM33, AM13x/AM26x, and Connectivity. For latency-critical and low-power applications, select devices (such as F28P55, AM13E2, and MSPM0G5187) feature TI’s integrated Neural Processing Unit (NPU) for hardware-accelerated inference.
Note: The list of supported devices is subject to change as new hardware is integrated. For the most up-to-date and comprehensive list of supported part numbers, please refer to the Tiny ML Tensorlab User's Guide: Supported Devices.