0

We intend to deploy a trained model in production. since we can not keep the same in the code base, we need to upload into the cloud and refer it on runtime.

We are using kubernetes, and I'm relatively new to it. Below is my stepwise understanding on how to solve this.

  1. build a persistent volume with my trained model (size around 30MB)
  2. mount the persistent volume into pod with a single container.
  3. keep this pod running. refer to the model from a python script via pod.

I tried referring documentation pv with no luck. I also tried to move the model to PV via "kubectl cp", with no success.

Any idea on how to resolve this? any helps would be appreciated.

Madhu Venkatesh
  • 21
  • 2
  • Could you share snippets of your yaml files? Also not sure if your application has logic to keep retrying till the model file is available. – leodotcloud Jul 11 '18 at 07:26
  • I'm sure that I got the steps wrong. could you please mention how to use a trained model via the cloud. – Madhu Venkatesh Jul 11 '18 at 18:45
  • I am not sure about how to actually use your training model. Your steps from kubernetes side of things seem ok. Your question is too open ended, need more details. – leodotcloud Jul 11 '18 at 21:24

0 Answers0