#machinelearning #modeldeployment #streamlit

Model training code -    • Transfer Learning - Image Classificat...  

Code repo - https://github.com/srivatsan88/google...

GKE Autopilot is a fully managed Kubernetes service that allows you to focus more on your application workload and less on managing cluster infrastructure.

GKE supports 2 mode of operation

Standard: You manage the cluster's underlying infrastructure, giving us node configuration flexibility.
Autopilot: GKE provisions and manages the cluster's underlying infrastructure, including nodes and node pools, giving you an optimized cluster
Standard you pay for number of nodes and node types. In autopilot you pay based on pods

In this video we will deploy an ML application on GKE autopilot