Deploying and visualizing models

Goals

• Easily re-train and re-deploy models
• Analyze models performance both over historical test set and new test data.

Deploying models

• Dockerize model (this should be handled automatically in flow). Dockerfile should contain necessary packages.
• Model weights are automatically uploaded to GCS into a bucket called ts-model-prod
• Dockerfile should take as input path to the weight file. So that all that requires changing to updated model.

(Re)-Deployment Architecture

• Historical data gathers over the next few weeks and then Air
• Model preforms better on the previous historical dataset
• Model preforms newly acquired test set (i.e. .