04-deployment

4. Model Deployment

4.1 Three ways of deploying a model

4.2 Web-services: Deploying models with Flask and Docker

See code here

4.3 Web-services: Getting the models from the model registry (MLflow)

See code here

4.4 (Optional) Streaming: Deploying models with Kinesis and Lambda

See code here

4.5 Batch: Preparing a scoring script

See code here

4.6 MLOps Zoomcamp 4.6 - Batch: Scheduling batch scoring jobs with Prefect

The unit 4.6 consists of multiple videos:

• 4.6.1 - Package Manager
• 4.6.2 - Original FIle walkthrough
• 4.6.3 - Modifying score.py
• 4.6.4 - Showing AWS Console
• 4.6.5 - Running the file
• 4.6.6 - Create the project
• 4.6.7 - Creating deployment
• 4.6.8 - Backfilling update
• 4.6.9 - Running on a functioning work pool
• 4.6.10 - Adding schedule
• 4.6.11 - Overview Wrap up

Old Video (2022 Edition)

4.7 Choosing the right way of deployment

COMING SOON

4.8 Homework

More information here.

Notes

Did you take notes? Add them here:

• Notes on model deployment (+ creating a modeling package) by Ron M.
• Notes on Model Deployment using Google Cloud Platform, by M. Ayoub C.
• Week4: Notes on Model Deployment by Bhagabat
• Week 4: Deployment notes by Ayoub.B
• Week 4: Deployment notes by Waleed
• Send a PR, add your notes above this line