You will be running a cancer detector. The application is a machine learning model already written and tuned to provide probabilities of cancer found in the cell image slides that you provide to the service.

The Tumor Proliferation Assessment Challenge 2016 (TUPAC16) was created to develop state-of-the-art algorithms for automatic prediction of tumor proliferation scores from whole-slide histopathology images of breast tumors. The IBM CODAIT team trained a mitosis detection model (a modified ResNet-50 model) on the TUPAC16 auxiliary mitosis dataset and then applied it to the whole-slide images for predicting tumor proliferation scores.

Further information about this application is available here: IBM Code Model Asset Exchange: Breast Cancer Mitosis Detector

The application is already packaged in a public container. You will make declarations to Kubernetes to deploy the application and expose it as a service. Once running, you will scale the application up and roll out a new version while it remains running.

In this challenge, you will be asked to:

    ☐ Create a YAML file for the Deployment
    ☐ Expose the deployment as a service
    ☐ Access the service to ensure the application is working
    ☐ Scale and update the application then re-verify that the application still functions

This challenge will self-destruct in 60 minutes.