#Software Installation

#Development Environment Deployment

#Development Machine Preparation

In the previous section, we introduced the necessary preparations before using Docker containers. To help you quickly use the toolchain, we provide a Docker image containing the complete development environment, which greatly simplifies the deployment process of the development environment. The following will provide a detailed explanation of how to deploy the Docker container.

docker load -i docker_openexplorer_xxx.tar.gz

You can start the Docker container corresponding to the current OE version by running the following script directly from the first level of the OE package(the script will automatically pull the image from the official Docker hub if there is no local image):

bash run_docker.sh data/

Where data is the path to the evaluation dataset folder. Please create the path before running the command, otherwise loading problems may occur.

If you want to use the CPU version of the Docker image, you need to add the cpu parameter:

bash run_docker.sh data/ cpu

The download links for the relevant publicly available evaluation datasets that the OE package samples rely on can be accessed by referring to the introduction in section Dataset Download.

If you want to start the Docker container manually, you can refer to the following command, where {version} is the OE version number you are currently using.

# CPU Docker
docker pull openexplorer/ai_toolchain_ubuntu_22_j6_cpu:{version}
# Start CPU Docker image manually
docker run -it --rm \
  --network host \ # Adjust network mode to host
  -v {OE package path}:/open_explorer \ # Mount OE package
  -v ./dataset:/data/horizon_j6/data \ # Mount dataset
  openexplorer/ai_toolchain_ubuntu_22_j6_cpu:{version}

# GPU Docker
docker pull openexplorer/ai_toolchain_ubuntu_22_j6_gpu:{version}
# Start GPU Docker image manually
docker run -it --rm \
  --network host \ # Adjust network mode to host
  --gpus all \ # Include the flag when you start a container to access GPU resources
  --shm-size=15g \ # Change the shared memory size
  -v {OE package path}:/open_explorer \ # Mount OE package
  -v {dataset path}:/data/horizon_j6/data \ # Mount dataset
  openexplorer/ai_toolchain_ubuntu_22_j6_gpu:{version}

#Local Manual Installation

In the previous section, we introduced the two quantization schemes and the environment dependencies and related instructions for Horizon's open-source efficient model training. This section will introduce you to the method of local manual installation of the environment. We recommend that after completing floating-point model training, you prioritize the simple and easy-to-use PTQ quantization scheme, and only switch to the QAT quantization scheme when accuracy issues cannot be resolved.

To manually install the environment locally, simply run the script below to complete the environment installation in one click.

cd package/host
bash install.sh 

The installation script will automatically check the environment. If there are missing dependencies or configurations, it will interrupt the installation process and give suggestions to fix it, as shown below:

Run the script again after adding the dependencies as suggested.

#Runtime Environment Deployment

In the previous section, we introduced the necessary preparations for the dev board before inference execution. Next, we will explain the board-side tools required for model inference execution and their installation methods.

#Board Side Tool Installation

#Supplementary Tools

Some of the supplementary tools of the toolchain are not included in the system image, but can be copied to the dev board by running the installation script in the OE package in the host environment, as follows:

cd package/board
# Linux environment
bash install_linux.sh ${board_ip}
# QNX environment
bash install_qnx.sh ${board_ip}

#DEB Deployment Package

To simplify the board-side deployment process, the UCP provides a DEB deployment package. After the package is installed, you can directly call the relevant tools through the command line to automatically install the required binaries and related dependencies, quickly set up and run UCP-related applications, greatly improving the convenience and efficiency of system configuration.

For detailed information about the DEB deployment package, please refer to the Overview - DEB Deployment Package in the UCP section.