Autoscaling TensorFlow Model Deployments with TF Serving and Kubernetes

AutoML Vision helps developers with limited ML expertise train high quality image recognition models. In this hands-on lab, you will learn how to train a custom model to recognize different types of clouds (cumulus, cumulonimbus, etc.).

• GSP777
• Overview
• Setup and requirements
• Lab tasks
• Task 1. Getting lab files
• Task 2. Creating a GKE cluster
• Task 3. Deploying ResNet101
• Task 4. Creating ConfigMap
• Task 5. Creating TensorFlow Serving deployment
• Task 6. Exposing the deployment
• Task 7. Configuring horizontal pod autoscaler
• Task 8. Testing the model
• Task 9. Installing Locust
• Task 10. Starting a load test
• Task 11. Monitoring the load test
• Task 12. Stopping the load test
• Congratulations