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 fill up this Form with your official company, institution, or educational organization email account. This will help us to verify your application 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)
GitHub → Settings → Developer settings → Personal access tokens → Tokens (classic)
Generate new token (classic)
For permissions: at least select: write:packages, read:packages, delete:packages
For Repository access: please select All repositories
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}
Tip
By default the Docker daemon always runs as the root user, as such, sudo command is necessary when calling docker commands.
You may create a Unix group called docker and add your user there.
$ sudo groupadd docker
$ sudo usermod -aG docker $USER
$ newgrp docker
Kindly refer to the Docker post-installation guide for more details.
Windows
Please refer to https://docs.docker.com/desktop/setup/install/windows-install/ to install docker desktop on Windows
While installing docker desktop, DO NOT 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}