C4W2:Autoscaling TensorFlow Model Deployments with TF Serving and Kubernetes: Issue with Task 11


This means each of my requests was a fail

And also i keep getting this error

Also the number of managing pods or default pools don’t increase.
What should i do?

Hello @Claudia_Fernandes
Would you please provide more details on what lead to the error? It might be something with your API Endpoint/data format

I followed all the instructions properly, but i realized even when i ran the curl statement, it showed connection timeout.