Hardware & Software Requirement

• OS : Ubuntu 18.04 or latest

• CPU : 4 Core (2 core per stream/cam added)

• Memory : 4GB, 8GB recommended

• GPU : Minimum GTX 960M

Pre-requisites

1. Install ubuntu 18.04 or latest version (link)

2. Install nvidia driver > 450 (link)

3. Install docker runtime (link) and nvidia-docker (link)

1. Install nvidia-driver 4.5.0 (GNOME GUI Nvidia Installation Method)

Open the Software & Updates application window. Select TAB Additional Drivers and choose any proprietary NVIDIA driver. The higher the driver number the latest the version.

2. Install docker-ce runtime

• Update the apt package index and install packages to allow apt to use a repository over HTTPS

sudo apt-get update
sudo apt-get install \
    apt-transport-https \
    ca-certificates \
    curl \
    gnupg-agent \
    software-properties-common

• Add Docker’s official GPG key

curl -fsSL https://download.docker.com/linux/ubuntu/gpg | sudo apt-key add -

• Use the following command to set up the stable repository.

sudo add-apt-repository \
   "deb [arch=amd64] https://download.docker.com/linux/ubuntu \
   $(lsb_release -cs) \
   stable"

• Update the apt package index, and install the latest version of Docker Engine and containerd, or go to the next step to install a specific version:

sudo apt-get update
sudo apt-get install docker-ce docker-ce-cli containerd.io

• Verify that Docker Engine is installed correctly by running the hello-world image.

sudo docker run hello-world

• Post-installation steps for Linux. This allows you to run Docker command without sudo .

  sudo groupadd docker
  sudo usermod -aG docker $USER

• Log-out from Linux, then log in again. You now can run Docker without sudo.

3. Install nvidia-docker

• Setup the stable repository and the GPG key

distribution=$(. /etc/os-release;echo $ID$VERSION_ID) \
   && curl -s -L https://nvidia.github.io/nvidia-docker/gpgkey | sudo apt-key add - \
   && curl -s -L https://nvidia.github.io/nvidia-docker/$distribution/nvidia-docker.list | sudo tee /etc/apt/sources.list.d/nvidia-docker.list

• Install the nvidia-docker2 package (and dependencies) after updating the package listing

sudo apt-get update
sudo apt-get install -y nvidia-docker2

• Restart the Docker daemon to complete the installation after setting the default runtime

sudo systemctl restart docker

• At this point, a working setup can be tested by running a base CUDA container

sudo docker run --rm --gpus all nvidia/cuda:11.0-base nvidia-smi

List of Required Credentials

To run Visionaire Stream, you need to have four credentials listed below:

• Nodeflux Gitlab Registry access token. Ask our sales if you don't have one.

• Visionaire Cloud email account and password. Just register to Visionaire Cloud.

• Visionaire Cloud access key and secret key. You can generate one from Cloud dashboard.

• Visionaire Stream deployment key. You can access on Cloud dashboard 'Partnership' in profile tab. If you don't see, it means that you don't have any deployment key. You can request to our sales.

1. Get Visionaire Cloud Email and Password

• Go to cloud.nodeflux.io.

• "Create new account" or "Sign in with Google".

• Fill the registration form, check Terms of Service and Privacy Policy, then click sign up.

• Click link in email we just sent for verification.

• Login with your credential. Remember your Cloud Email and Password.

2. Get Visionaire Cloud Access Key and Secret Key

• Login to cloud.nodeflux.io.

• Go to tab "Access Key".

• Click "Generate Access Key". You might asked to enter some information needed before generating access key for the first time.

• After the key is generated, click "Download as .csv". You can see your Access Key and Secret Key. Save this for Stream installation.

3. Get Deployment Key

• Create / Sign-in to Nodeflux’s Cloud Account.

• If you sign-in with Google for the first time, don’t forget to change the password from the Profile page. Make sure your password does not contain characters such as ! and \.

• Contact our Sales with Interest for Partnership and request details with the amount of serial number requested.

• Wait for the response, and if approved, the Partnership tab will be available on your cloud account.

• In the Partnership page, you will get a deployment key with a number of seats according to your prior request for the amount of serial number.

• Single deployment key refers to a single running instance of docker visionaire. Which means, only one deployment key can be used at a time. You will be unable to execute another instance of docker visionaire using the same deployment key without deactivating (through the cloud dashboard) the previous instance.

• If multiple instances are using the same deployment key, the Visionaire will be able to detect and terminate the older instance automatically.

• You can always monitor the status of the deployment key and its serial numbers through the cloud dashboard.

• You are not encouraged to deactivate the serial number manually as docker visionaire will manage the seats automatically, unless under extraordinary circumstances.

You now can proceed to Installation Guide by using the link bellow: