3.1. Quickstart
This guide gets you from zero to a trained model in 5 minutes.
3.1.1. Prerequisites
Python 3.10.x installed
Tiny ML Tensorlab installed (see Installation)
3.1.3. Step 2: Run Hello World Example
./run_tinyml_modelzoo.sh examples/generic_timeseries_classification/config.yaml
run_tinyml_modelzoo.bat examples\generic_timeseries_classification\config.yaml
This example:
Downloads a simple waveform dataset (sine, square, sawtooth waves)
Applies FFT-based feature extraction
Trains a small classification model (~1K parameters)
Quantizes the model for MCU deployment
Compiles for F28P55 (NPU device)
3.1.4. Step 3: View Results
Training outputs are saved to:
../tinyml-modelmaker/data/projects/generic_timeseries_classification/run/<timestamp>/
Directory Contents:
<timestamp>/
├── training/
│ ├── base/ # Float32 training
│ │ ├── best_model.pt # Best model checkpoint
│ │ ├── training_log.csv # Loss/accuracy history
│ │ └── *.png # Visualizations
│ └── quantization/ # Quantized model
│ ├── best_model.onnx # Final ONNX model
│ └── golden_vectors/ # Test data for device
├── testing/ # Test results
└── compilation/
└── artifacts/ # Device-ready files
├── mod.a # Compiled model library
└── tvmgen_default.h # API header
3.1.5. Step 4: Understand the Config
Open examples/generic_timeseries_classification/config.yaml:
common:
task_type: generic_timeseries_classification
target_device: F28P55
dataset:
dataset_name: generic_timeseries_classification
data_processing_feature_extraction:
feature_extraction_name: Generic_1024Input_FFTBIN_64Feature_8Frame
variables: 1
training:
model_name: CLS_1k_NPU
batch_size: 256
training_epochs: 20
testing: {}
compilation: {}
Key parameters:
task_type: What ML task to performtarget_device: Which MCU to compile formodel_name: Which model architecture to usefeature_extraction_name: How to preprocess data
3.1.6. Step 5: Try a Different Example
Run the arc fault detection example:
./run_tinyml_modelzoo.sh examples/dc_arc_fault/config.yaml
run_tinyml_modelzoo.bat examples\dc_arc_fault\config.yaml
3.1.7. Expected Results
For the hello world example, you should see:
Training accuracy: ~98-100%
Quantized accuracy: ~95-100%
Model size: ~1K parameters
Training time: 1-5 minutes (CPU)
3.1.8. Next Steps
First Example - Detailed walkthrough
Understanding Config - Config file reference
Bring Your Own Data - Use your own data
CCS Integration Guide - Deploy to a device