Skip to content
Branch: master
Find file Copy path
Find file Copy path
Fetching contributors…
Cannot retrieve contributors at this time
40 lines (29 sloc) 1.33 KB


Utilities and demos of tensorflow machine learning running on Kubernetes.


  1. Run inception using tensorflow serving
  1. Run demo UI to submit an image to inception service
  • Build nodejs-inception-demo docker image (or use mine @

    cd nodejs-inception-demo
    docker build -t myimages/image-classifier-ui .
    cd ..
  • Deploy on Kubernetes.

    kubectl apply -f nodejs-inception-demo/inception_ui_k8s.yaml
  • Depending on your Kubernetes environment, optionally expose the UI service or create an ingress for it. Note: the code is written to run on a /inception path prefix to allow use with path based routing in loadbalancers. Path tested with Traefik.

    for example:
    kubectl apply -f nodejs-inception-demo/inception_ui_k8s_ingress.yaml


Created and maintained by Paul Welch


MIT Licensed. See LICENSE for full details.

You can’t perform that action at this time.