Install AI model convert tool
Preparation
See here for how to get the CV Tool.
The Docker images and containers created for the i-PRO Camera SDK and the AI model conversion tool are not related. The procedures on this page are not related to the SDK, so please perform them in the Ubuntu OS terminal.
Installation target OS in the tutorial
Ubuntu 20.04 LTS
Install docker
Install the packages necessary for building the docker environment and set environment.
Please refer to the docker official website to learn more about installation (ex. installing on other Linux distribution).
$ sudo apt-get update
$ sudo apt-get install ca-certificates curl
$ sudo install -m 0755 -d /etc/apt/keyrings
$ sudo curl -fsSL https://download.docker.com/linux/ubuntu/gpg -o /etc/apt/keyrings/docker.asc
$ sudo chmod a+r /etc/apt/keyrings/docker.asc
$ echo \
"deb [arch=$(dpkg --print-architecture) signed-by=/etc/apt/keyrings/docker.asc] https://download.docker.com/linux/ubuntu \
$(. /etc/os-release && echo "$VERSION_CODENAME") stable" | \
sudo tee /etc/apt/sources.list.d/docker.list > /dev/null
$ sudo apt-get update
$ sudo apt-get install docker-ce docker-ce-cli containerd.io docker-buildx-plugin docker-compose-plugin
Import docker image file (First time only)
It takes several minutes until the import completes.
[image name]
is any
$ cat cvtool_vx.xx.tar.bz2 | sudo docker import - [image name]
Create docker container (First time only)
Option “-v” is needed in sharing files between host and container.
[container name]
is any
$ sudo docker run -d -it --name [container name] [image name] /bin/bash
If you have set a proxy, please refer to the link below to set the proxy for docker.
Reference:https://docs.docker.com/network/proxy/
Run CV Tool
Start the container.
Log in to the container.
If you need a password, please use "cv".
Set the environment (inside the container).
For ambaCV2X camera
For ambaCV5X camera
Conversion
Please refer to the following page for model conversion.
AI model convert tool: Tensorflow
AI model convert: ONNX(PyTorch)