9. Deployment

A Tiny ML ModelZoo run produces a compiled model library (mod.a), the model header (tvmgen_default.h), the feature-extraction configuration (user_input_config.h) and golden vectors (test_vector.c). Deploying means dropping these four files into a ready-made example from the device SDK and confirming on the board that the model gives the same answer as on your PC.

Note

Deployment in 1.5.0 is based on the SDK examples in tinyml-sdk (C2000Ware, F29H85x SDK, MSPM33 SDK, AM13 MCU-SDK, AM26x MCU-PLUS-SDK). The 1.4.0 flow of writing your own main.c around mod_inference() and extract_features() is gone; the SDK examples already contain the application, the feature-extraction library calls and the test harness.

9.1. Start Here

Deploy to an SDK Example

The 4 files, which SDK and example to pick, and the expected “All tests have passed.” output.

Deploying a ModelZoo Run to an SDK Example (Golden-Vector Check)

CCS Integration

Importing, building, flashing and debugging the example in Code Composer Studio.

CCS Integration Guide

NPU Devices

What changes for F28P55, MSPM0G5187 and AM13E2 (NPU initialization, memory, debugging).

NPU Device Deployment

Non-NPU Devices

CPU-only devices: C28x, F29H85, MSPM0G3507, MSPM33C32, AM26x.

Non-NPU Deployment

The deck Deploying to an SDK example summarizes the same steps as slides.

Contents

• 9.1.1. Deploying a ModelZoo Run to an SDK Example (Golden-Vector Check)
  • 9.1.1.1. At a Glance: the 4 Files
  • 9.1.1.2. Step 1: Pick the SDK and the Example
  • 9.1.1.3. Step 2: Import the Example into CCS
  • 9.1.1.4. Step 3: Replace the 4 Files
  • 9.1.1.5. Step 4: Build, Flash, Check
  • 9.1.1.6. Step 5: Try the Other Test Sets
  • 9.1.1.7. Troubleshooting
  • 9.1.1.8. After the Golden Vectors Pass
• 9.1.2. CCS Integration Guide
  • 9.1.2.1. Prerequisites
  • 9.1.2.2. What You Get in the Run Folder
  • 9.1.2.3. Import the Example
  • 9.1.2.4. Build, Flash and Run
  • 9.1.2.5. Check the Result
  • 9.1.2.6. Memory and Linker Problems
  • 9.1.2.7. Common Issues
  • 9.1.2.8. Next Steps
• 9.1.3. NPU Device Deployment
  • 9.1.3.1. NPU-Enabled Devices
  • 9.1.3.2. NPU Compilation
  • 9.1.3.3. What Is Different at Run Time
  • 9.1.3.4. Walkthrough: F28P55x
  • 9.1.3.5. Troubleshooting
  • 9.1.3.6. Next Steps
• 9.1.4. Non-NPU Deployment
  • 9.1.4.1. Non-NPU Devices
  • 9.1.4.2. Importing an Example That Is Not in Resource Explorer
  • 9.1.4.3. CPU Inference Considerations
  • 9.1.4.4. Non-NPU vs NPU
  • 9.1.4.5. Next Steps
• 9.1.5. Project Compilation Guide: Timeseries Classification Examples
  • 9.1.5.1. Overview
  • 9.1.5.2. Table of Contents
  • 9.1.5.3. Required Tools
  • 9.1.5.4. Output From Modelzoo
  • 9.1.5.5. How to run on device
  • 9.1.5.6. Next Steps
• 9.1.6. Deploying Regression Models from ModelMaker to Device
  • 9.1.6.1. Abhijeet Pal, Adithya Thonse, Tushar Sharma, Fasna Sharaf, Jaswanth Kumar
  • 9.1.6.2. Table of Contents
  • 9.1.6.3. Overview
  • 9.1.6.4. Prerequisites
  • 9.1.6.5. Deployment Steps
  • 9.1.6.6. Verify Your Model
• 9.1.7. Deploying Forecasting Models from ModelMaker to Device
  • 9.1.7.1. Fasna Sharaf, Adithya Thonse, Tushar Sharma, Abhijeet Pal, Jaswanth Kumar
  • 9.1.7.2. Table of Contents
  • 9.1.7.3. Overview
  • 9.1.7.4. Prerequisites
  • 9.1.7.5. Deployment Steps
  • 9.1.7.6. Verify Your Model
  • 9.1.7.7. Next Steps
• 9.1.8. Deploying Anomaly Detection Models from ModelZoo to Device
  • 9.1.8.1. Jaswanth Jadda, Adithya Thonse, Tushar Sharma, Abhijeet Pal, Fasna Sharaf
  • 9.1.8.2. Table of Contents
  • 9.1.8.3. Overview
  • 9.1.8.4. Prerequisites
  • 9.1.8.5. Deployment Steps
  • 9.1.8.6. Verify Your Model

9.2. Deployment Workflow

1. Train and compile with a config that has compilation: enable: True (see Quickstart). Check the device-support matrix in Device Overview.

2. Open the run folder data/projects/<project_name>/run/<date-time>/<model_name>/ (see Understanding the Run Output).

3. Pick the SDK and example for your target_device and task_type (tables in Deploying a ModelZoo Run to an SDK Example (Golden-Vector Check)).

4. Import the example in CCS, replace the four files, build, flash.

5. Read the console: Feature extraction mismatches 0, All tests have passed., Golden vectors matched: X not matched: 0.

6. Replace the test vector input with your ADC or sensor data in application_main.c.

Per-task walkthroughs (with screenshots) are the four task readmes in the toctree above.