Realtek AmebaPro2 AI Video Manual

• Realtek AmebaPro2 NN deployment
  • NN Deployment
    • Using customized NN model
    • SDK configuration for customized NN model
    • NN memory and flash usage evaluation
    • Using the NN MMF example with VIPNN module
    • How to add a pre-process node to customized model (optional)
    • How to load model from SD card instead of flash (optional)
    • How to modify customized model name after conversion (optional)
  • Model Security
    • Model Authentication – Hash and Signature check
    • Model Encryption – Cypher Text Decryption
    • SDK Configuration
    • Secure Deployment Flow
    • Signing and Encryption PC Tool
    • Performance Test
  • Post-process PC Development Tool
  • Appendix A. Acuity Supported Operation Layer
    • ONNX to ACUITY Operation Mapping
    • Darknet to ACUITY Operation Mapping
  • Appendix B. Acuity Supported AI Framework
• Realtek AmebaPro2 Model Conversion Tool
  • Offline AI Model Conversion Toolkit (Acuity Toolkit) Overview
    • Introduction to Offline AI Model Conversion Toolkit
    • Eligibility
    • Brief Comparison between Offline and Online Conversion Toolkit
    • Acuity Supported AI Framework
    • AmebaPro2 SDK AI Model Application Types
    • AmebaPro2 SDK NN MMF examples
  • Acuity Toolkit Manual Installation
    • Download Acuity Toolkit
    • Install Acuity Toolkit
    • Install VivanteIDE
  • Acuity Toolkit Docker Installation
    • Download Acuity Toolkit Docker
    • Docker Entry
  • NN Model Conversion Steps using Acuity Toolkit on Docker
    • Step 1: Pre-import Preparation
    • Step 2: Import Model
    • Step 3: Quantize Model
    • Step 4: Export Model
  • Acuity License
    • COPYRIGHT
    • DISCLAIMER
    • TRADEMARKS
    • USING THIS DOCUMENT
• Realtek AmebaPro2 NN Quantization Discussion
  • Inputmeta File Modification
    • Crucial step before quantization
  • NN Example (Yolov7_tiny)
    • Using customized NN model
  • NN Example (Yolov9_tiny)
    • Using customized NN model
    • SDK configuration for customized NN model
    • Post-process PC Development Tool
    • Hybrid Quantize
    • Troubleshooting
• Realtek AI Train Server Guide
  • AI Training Server Setup
    • 1. Hardware Requirements
    • 2. Nvidia Driver Installation
    • 3. Docker Installation
    • 4. Create Working Directory
    • 5. Install the scripts
    • 6. Login to the System
  • AI Training Server Run
    • 1. Log into the Server
    • 2. Start the Training
    • 3. Download the Model
    • 4. Model Testing