Deploy in a private cloud with Kubernetes

Node requirements

Deepomatic can run using the following minimum requirements:

  • A processor supporting the x86-64 instruction set.

  • 4GB of free RAM.

  • 10GB of storage.

The recommended requirements are however:

  • A quad core processor supporting the x86-64 instruction set.

  • 8GB of free RAM.

  • 40GB of storage.

Deep learning models require lot of computation and it is recommended to use a specific hardware accelerator to make computation tractable. See below for a list of supported accelerators:

Compatible deep learning accelerators (recommended):

  • NVIDIA GPU accelerators, of the family Tesla, Quadro, RTX or GTX, with CUDA compute capability 3.0 or more.

Kubernetes requirements

Minimal Version

Kubernetes version >= 1.10

Accelerator related requirements

Additionally, you will need to install additional software depending on the deep learning you may have chosen.

NVIDIA GPU

You need to install NVIDIA drivers 410.48+ and NVIDIA Docker.

You need to install NVIDIA Device Plugin.

Set up

To deploy on a private kubernetes cluster, you need to get a manifest for your application using a Deepomatic CLI command.

The manifest you get is specific to Google Kubernetes Engine but it can easily be adapted if needed. Contact your Customer Success Manager if you need to deploy your application on a cluster that is not hosted on GCP.

Was this helpful?