Autoscaling TensorFlow Model Deployments with TF Serving and Kubernetes Reviews

Prathmesh P. · Reviewed about 4 years ago

Eugenio C. · Reviewed about 4 years ago

tingsia d. · Reviewed about 4 years ago

Chad Y. · Reviewed about 4 years ago

Rahul C. · Reviewed about 4 years ago

Eduard A. · Reviewed about 4 years ago

mateo3 S. · Reviewed about 4 years ago

Ilia T. · Reviewed about 4 years ago

got stucked on last load test, it showed the pods are stuck.

Tommy L. · Reviewed about 4 years ago

I have an issue to complete it

Ghada S. · Reviewed about 4 years ago

sara k. · Reviewed about 4 years ago

GANAR Y. · Reviewed about 4 years ago

Станислав М. · Reviewed about 4 years ago

Jason L. · Reviewed about 4 years ago

Pyin M. · Reviewed about 4 years ago

Praveen J. · Reviewed about 4 years ago

Tulay M. · Reviewed about 4 years ago

Mateusz O. · Reviewed about 4 years ago

I couldn't complete the Lab due to some issue in the GKE cluster. I started my GKE service successfully and checked the status in the lab. When I tried to do load testing using Locust, it threw an error on the external ip address. I used the EXTERNAL_IP value returned by the command "kubectl get svc image-classifier" inside the curl command "curl -d @locust/request-body.json -X POST http://${EXTERNAL_IP}:8501/v1/models/image_classifier:predict" but it threw "connection refused" error.

Mahendra R. · Reviewed about 4 years ago

Christoph P. · Reviewed about 4 years ago

Việt N. · Reviewed about 4 years ago

Nicolas K. · Reviewed about 4 years ago

There are some problems...

Philippe B. · Reviewed about 4 years ago

Markus K. · Reviewed about 4 years ago

there is an error in the last assignments: task.py never stresses the cpu to 60% therefore no other pods are created

Gabriele B. · Reviewed about 4 years ago