Radxa Dragon Q6A User Guide

This document introduces how to use the Aplus AI toolchain. If you encounter issues with hardware interfaces or the underlying system, please refer to the official Radxa Dragon Q6A documentation.

1. Quick Start

1.1 Environment Preparation

1.1.1 Hardware Preparation

• Mainboard: Radxa Dragon Q6A
• Boot media: MicroSD card
• Power adapter: 12V Type-C power adapter (PD protocol compatible)
• USB serial cable (optional): for serial debugging and system login
• HDMI cable and monitor (optional): for displaying the system interface and GUI operations

1.2 System Installation and Usage

Refer to the system installation section in the official Radxa Dragon Q6A documentation to download, install, and use the system. Documentation link: Radxa Dragon Q6A

2. Using the Aplus AI Toolchain

2.1 Installing the Toolchain

• Configure the Aplus apt source

sudo wget -qO- https://archive.aidlux.com/ubuntu24/public.key | sudo gpg --dearmor -o /etc/apt/trusted.gpg.d/private-aidlux.gpg

echo 'deb [arch=arm64 signed-by=/etc/apt/trusted.gpg.d/private-aidlux.gpg] https://archive.aidlux.com/ubuntu24 noble main' | sudo tee /etc/apt/sources.list.d/private-aidlux.list

sudo apt update

• Install AidLite and the license

sudo apt install -y aidlite-sdk aidlite-qnn236 aidlite-qnn240 aidlite-qnn248 aid-lms aidlms-sdk

• Install the dependencies required to build the C++ examples

sudo apt install -y build-essential cmake g++ libopencv-dev

2.2 AidLite SDK Usage Examples

• SDK & API documentation

AidLite SDK

2.2.1 aidlite_qnn236

# Enter the project directory:
cd /usr/local/share/aidlite/examples/aidlite_qnn236/cpp

# Build the executable:
sudo mkdir build && cd build
sudo cmake ..
sudo make

# Run the test project script:
sudo ./qnn_yolov5_multi 3
# Note: 1. sudo requires the password: radxa 2. This example only calls the DSP

2.2.2 aidlite_qnn240

# Enter the project directory:
cd /usr/local/share/aidlite/examples/aidlite_qnn240/cpp

# Build the executable:
sudo mkdir build && cd build
sudo cmake ..
sudo make

# Run the test project script:
sudo ./qnn_yolov5_multi 3
# Note: 1. sudo requires the password: radxa 2. This example only calls the DSP

2.2.3 aidlite_qnn248

# Enter the project directory:
cd /usr/local/share/aidlite/examples/aidlite_qnn248/cpp

# Build the executable:
sudo mkdir build && cd build
sudo cmake ..
sudo make

# Run the test project script:
sudo ./qnn_yolov5_multi 3
# Note: 1. sudo requires the password: radxa 2. This example only calls the DSP

3. Licensing

The AI toolchain provides a 30-day trial period. For a full license, contact the Aplus FAE to obtain a license code. The steps are as follows:

• Get the device SN

cat  /sys/devices/soc0/serial_number

• Send the device SN to the Aplus FAE to obtain the license code