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

7 Edge AI Application: Waveform Classifier

MSPM0 provides an experimental waveform classifier design capable of performing real-time, continuous detection and classification of input signals, identifying common waveform types such as sine, triangle, and sawtooth waves. The design is built upon a 13K-parameter time-series classification model, offering strong scalability and extensibility.

The waveform classifier system achieves 100% (R square) classification accuracy with an inference latency of only 5.84ms, while consuming just 21.5KB of Flash and 3.3KB of RAM, as shown in Table 7-6.

Table 7-1 Waveform Classifier Edge AI Solution Performance
MetricValue
Accuracy100%
Flash Usage21.5KB
RAM Usage3.3KB
Inference Latency (NPU)5.84ms
Inference Energy(1) (AVG)236.97uJ
(1) The inference energy was measured using EnergyTrace during repeated executions of the tvmgen_default_run().
Note: To maintain accurate inference energy measurements on the LP-MSPM0G5187, remove the J6 jumper. This prevents additional current consumption from the onboard microphone and audio ADC, which can otherwise skew the results.
Table 7-5 shows the model main information.
Table 7-2 Waveform Classifier AI Model Information
PropertyValue
Model ArchitectureCNN
Number of Parameters14,124
Input ShapeTensor [(1, 1, 128, 1)]
Output Classes3 (Sawtooth, Sine, Square)
QuantizationINT8