@helm-charts/bitnami-tensorflow-inception v3.3.1-0.1.0

@helm-charts/bitnami-tensorflow-inception

Open-source software library for serving machine learning models

## Global Docker image parameters
## Please, note that this will override the image parameters, including dependencies, configured to use the global value
## Current available global Docker image parameters: imageRegistry and imagePullSecrets
##
# global:
#   imageRegistry: myRegistryName
#   imagePullSecrets:
#     - myRegistryKeySecretName

replicaCount: 1

## TensorFlow Serving server image version
## ref: https://hub.docker.com/r/bitnami/tensorflow-serving/tags/
##
server:
  image:
    registry: docker.io
    repository: bitnami/tensorflow-serving
    tag: 1.13.0
    ## Specify a imagePullPolicy
    ## Defaults to 'Always' if image tag is 'latest', else set to 'IfNotPresent'
    ## ref: http://kubernetes.io/docs/user-guide/images/#pre-pulling-images
    ##
    pullPolicy: IfNotPresent
    ## Optionally specify an array of imagePullSecrets.
    ## Secrets must be manually created in the namespace.
    ## ref: https://kubernetes.io/docs/tasks/configure-pod-container/pull-image-private-registry/
    ##
    # pullSecrets:
    #   - myRegistryKeySecretName
  port: 8500

## TensorFlow Inception image version
## ref: https://hub.docker.com/r/bitnami/tensorflow-inception/tags/
##
client:
  image:
    registry: docker.io
    repository: bitnami/tensorflow-inception
    tag: 1.11.1
    ## Specify a imagePullPolicy
    ## Defaults to 'Always' if image tag is 'latest', else set to 'IfNotPresent'
    ## ref: http://kubernetes.io/docs/user-guide/images/#pre-pulling-images
    ##
    pullPolicy: IfNotPresent
    ## Optionally specify an array of imagePullSecrets.
    ## Secrets must be manually created in the namespace.
    ## ref: https://kubernetes.io/docs/tasks/configure-pod-container/pull-image-private-registry/
    ##
    # pullSecrets:
    #   - myRegistryKeySecretName

## Specify a imagePullPolicy
## Defaults to 'Always' if image tag is 'latest', else set to 'IfNotPresent'
## ref: http://kubernetes.io/docs/user-guide/images/#pre-pulling-images
##
imagePullPolicy: IfNotPresent

## Tensorflow Serving Pod Security Context
## ref: https://kubernetes.io/docs/tasks/configure-pod-container/security-context/
##
securityContext:
  enabled: true
  fsGroup: 1001
  runAsUser: 1001

## Kubernetes configuration
## For minikube, set this to NodePort, elsewhere use LoadBalancer
##
serviceType: LoadBalancer

## Pod annotations
## ref: https://kubernetes.io/docs/concepts/overview/working-with-objects/annotations/
##
podAnnotations: {}

## Prometheus Exporter / Metrics
##
metrics:
  enabled: false
  image:
    registry: docker.io
    repository: ynqa/tensorflow-serving-exporter
    tag: latest
    pullPolicy: IfNotPresent
    ## Optionally specify an array of imagePullSecrets.
    ## Secrets must be manually created in the namespace.
    ## ref: https://kubernetes.io/docs/tasks/configure-pod-container/pull-image-private-registry/
    ##
    # pullSecrets:
    #   - myRegistryKeySecretName
  ## Metrics exporter pod Annotation and Labels
  podAnnotations:
    prometheus.io/scrape: 'true'
    prometheus.io/port: '9118'
    ## Metrics exporter resource requests and limits
    ## ref: http://kubernetes.io/docs/user-guide/compute-resources/
    ##
  # resources: {}

TensorFlow Serving Inception v3

TensorFlow Serving is an open-source software library for serving machine learning models. This chart will specifically serve the Inception v3 model with already trained data.

TL;DR;

$ helm install bitnami/tensorflow-inception

Introduction

This chart bootstraps a TensorFlow Serving Inception v3 pod on a Kubernetes cluster using the Helm package manager.

Bitnami charts can be used with Kubeapps for deployment and management of Helm Charts in clusters. This Helm chart has been tested on top of Bitnami Kubernetes Production Runtime (BKPR). Deploy BKPR to get automated TLS certificates, logging and monitoring for your applications.

Prerequisites

• Kubernetes 1.4+ with Beta APIs enabled
• PV provisioner support in the underlying infrastructure

Get this chart

Download the latest release of the chart from the releases page.

Alternatively, clone the repo if you wish to use the development snapshot:

$ git clone https://github.com/bitnami/charts.git

Installing the Chart

To install the chart with the release name my-release:

$ helm install --name my-release bitnami/tensorflow-inception

The command deploys Tensorflow Serving Inception v3 model on the Kubernetes cluster in the default configuration. The configuration section lists the parameters that can be configured during installation.

Tip: List all releases using helm list

Uninstalling the Chart

To uninstall/delete the my-release deployment:

$ helm delete my-release

You can check your releases with:

$ helm list

The command removes all the Kubernetes components associated with the chart and deletes the release.

Configuration

The following tables lists the configurable parameters of the TensorFlow Inception chart and their default values.

Specify each parameter using the --set key=value[,key=value] argument to helm install. For example,

$ helm install --name my-release bitnami/tensorflow-inception --set imagePullPolicy=Always

Alternatively, a YAML file that specifies the values for the above parameters can be provided while installing the chart. For example,

$ helm install --name my-release -f values.yaml bitnami/tensorflow-inception

Tip: You can use the default values.yaml

Upgrading

To 3.2.0

Tensorflow Serving container was moved to a non-root approach. There shouldn't be any issue when upgrading since the corresponding securityContext is enabled by default. Both container image and chart can be upgraded by running the command below:

$ helm upgrade my-release stable/tensorflow-inception

If you use a previous container image (previous to 1.12.0-r34), disable the securityContext by running the command below:

$ helm upgrade my-release stable/tensorflow-inception --set securityContext.enabled=fase,server.image.tag=XXX

To 1.0.0

Backwards compatibility is not guaranteed unless you modify the labels used on the chart's deployments. Use the workaround below to upgrade from versions previous to 1.0.0. The following example assumes that the release name is tensorflow-inception:

$ kubectl patch deployment tensorflow-inception --type=json -p='[{"op": "remove", "path": "/spec/selector/matchLabels/chart"}]'