Merge pull request #198 from panchul/k8s_depl_notebook

Moving K8s deployment to 'notebooks' section

Research/deploying-model-on-k8s/Readme.md → machine-learning-notebooks/deploying-model-on-k8s/Readme.md

@@ -7,6 +7,9 @@ This section guides you through the steps needed to deploy a model for inferenci
 1. Have a valid Microsoft Azure subscription
 2. Be able to provision GPU-enabled VMs
 3. Have access to VM image repository (DockerHub account, or ACR)
+4. Be able to run `kubectl`, configured to your cluster
+5. If you are using Edge device, you should be able to complete this step on AS Edge https://docs.microsoft.com/en-us/azure/databox-online/azure-stack-edge-j-series-deploy-stateless-application-kubernetes
+
 
 Clone this repository somewhere so you can easily access the different source files:
 
@@ -242,7 +245,7 @@ For more information, please see [Pull an Image from a Private Registry](https:/
 
 In the following steps we denote the image as `1234567dedede1234567ceeeee.azurecr.io/tfgpu:1.0`, you can tag your own image adhering to the naming conventions you like.
 
-## Creating a Deployment
+## Creating a Deployment on an Edge Device or another Kubernetes cluster
 
 We provide the Deployment file, `deploy_infer.yaml`:
 

Research/deploying-model-on-k8s/production-deploy-to-k8s-gpu.ipynb → machine-learning-notebooks/deploying-model-on-k8s/production-deploy-to-k8s-gpu.ipynb

@@ -271,7 +271,7 @@
    "outputs": [],
    "source": [
     "# provide name of azure contaienr image and tag \n",
-    "imagename= \"tfgpu\"\n",
+    "imagename= \"tfgpuk8s\"\n",
     "imagelabel=\"1.0\""
    ]
   },
@@ -341,7 +341,7 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "## Preparing Kubernetes Deployment file\n",
+    "## Preparing Deployment file for AS Edge or another Kubernetes cluster.\n",
     "\n",
     "Below is the template for our Kubernetes deployments. We create it within this notebook for visibility, for more complex deployments you can make it part of source control repository.\n",
     "\n",
@@ -356,7 +356,23 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "## kubectl\n",
+    "## Validating kubectl on AS Edge\n",
+    "\n",
+    "If you created your cluster on Azure Stack Edge using aks-engine, you will have `kubectl`. You can check the version:\n",
+    "\n",
+    "    $ kubectl version --client\n",
+    "    Client Version: version.Info{Major:\"1\", Minor:\"19\", GitVersion:\"v1.19.2\",\n",
+    "    GitCommit:\"f5743093fd1c663cb0cbc89748f730662345d44d\", GitTreeState:\"clean\",\n",
+    "    BuildDate:\"2020-09-16T13:41:02Z\", GoVersion:\"go1.15\", Compiler:\"gc\", Platform:\"linux/amd64\"}\n",
+    "    \n",
+    "For more information, visit https://docs.microsoft.com/en-us/azure/databox-online/azure-stack-edge-j-series-deploy-stateless-application-kubernetes\n"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Validating kubectl on a generic Kubernetes cluster\n",
     "\n",
     "You also need `kubectl`. If the following command fails, see https://kubernetes.io/docs/tasks/tools/install-kubectl/\n",
     "\n",
@@ -615,13 +631,6 @@
     "except KeyError as e:\n",
     "    print(str(e))"
    ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": []
   }
  ],
  "metadata": {