Acuity Toolkit Docker Installation

Download Acuity Toolkit Docker

By downloading and using the software, you agree to fully comply with the terms and conditions of the Acuity License

  • Users don’t need to download Verisilicon_SW_VIP_Acuity_6.18.8_whl_20250303.tgz and Verisilicon_Tool_VivanteIDE_v5.8.1_CL664938_Linux_Windows_SDK_p6.4.x_dev_6.4.14.tgz since these packages is already install in Docker

  • Acuity_PATH is also written in docker, written in .bashrc

  • We mount acuity_examples_c901149 and Verisilicon_SW_NBInfo_1.2.17_20230412 into docker for flexible operation, so we need to download these software packages

Toolkit Files and Github Access

Note

​To access offline AI model conversion tools, please contact AmebaAIoT@realtek.com with the subject line “Offline AI Model” using official company, institution, or educational organization email account. Please include the organization name, GitHub username, a brief description of your project, this will help us to verify your affiliation and process your inquiry more efficiently.

Once approved, please sign in to your GitHub account to download the files

We store or docker images on GitHub Container Registry (GHCR), please establish Personal Access Token (PAT)

  1. GitHub → Settings → Developer settings → Personal access tokens → Tokens (classic)

  2. Generate new token (classic)

  3. For permissions: at least select: write:packages, read:packages, delete:packages

  4. For Repository access: please select All repositories

Export Script Modification

Please add the following command in ‘pegasus_export_ovx.sh’ to ensure successful export on Docker.

--optimize 'VIP8000NANONI_PID0XAD' \
--pack-nbg-unify \
--viv-sdk '/opt/acuity/Vivante_IDE/VivanteIDE5.8.1.1/cmdtools' \

Docker Entry

Before excuting the “install” and “run” scripts, kindly ensure that you have authenticate to GHCR on Docker, please use the generated PAT as password.

docker login ghcr.io -u <username>

Linux

Please refer to https://docs.docker.com/engine/install/ubuntu/ to install docker engine on Ubuntu

Link: https://github.com/Ameba-AIoT/ameba-ai-offline-toolkit/tree/main/Docker/Linux

cd Docker/Linux
source install.sh (This script will download the docker image from ghcr.io)
source run.sh (docker entry)

The script will mount acuity_examples and Verisilicon_SW_NBInfo into docker, please placed the folders in the same path with run.sh

docker run -it --rm \
   --user $(id -u):$(id -g) \
   -e HOME=/home/user \
   -w /workspace/acuity_examples \
   -v "$(pwd)/acuity_examples_c901149:/workspace/acuity_examples" \
   -v "$(pwd)/Verisilicon_SW_NBInfo_1.2.17_20230412:/workspace/Verisilicon_SW_NBInfo_1.2.17_20230412" \
   ${IMAGE_NAME}:${IMAGE_TAG}

Windows

Please refer to https://docs.docker.com/desktop/setup/install/windows-install/ to install docker desktop on Windows

  • While installing docker desktop, don’t select allow windows container to be used with this installation

Link: https://github.com/Ameba-AIoT/ameba-ai-offline-toolkit/tree/main/Docker/Windows

cd Docker/Windows
source install.bat (This script will download the docker image from ghcr.io)
source run.bat (docker entry)

The script will mount acuity_examples and Verisilicon_SW_NBInfo into docker, please placed the folders in the same path with run.bat

docker run -it --rm \
   --user $(id -u):$(id -g) \
   -e HOME=/home/user \
   -w /workspace/acuity_examples \
   -v "$(pwd)/acuity_examples_c901149:/workspace/acuity_examples" \
   -v "$(pwd)/Verisilicon_SW_NBInfo_1.2.17_20230412:/workspace/Verisilicon_SW_NBInfo_1.2.17_20230412" \
   ${IMAGE_NAME}:${IMAGE_TAG}