changes to keras readme and 04_DeployOnAKS

Keras_Tensorflow/04_DeployOnAKS.ipynb

@@ -889,6 +889,13 @@
     "!kubectl get service azure-dl"
    ]
   },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "Next, we will [test our web application deployed on AKS](05_TestWebApp.ipynb). Once, we are done with all the notebooks of the tutorial, below instructions can be used to delete the cluster and free resources."
+   ]
+  },
   {
    "cell_type": "markdown",
    "metadata": {},
@@ -954,13 +961,6 @@
    "source": [
     "!az group delete --name $resource_group -y"
    ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "Next, we will [test our web application deployed on AKS](05_TestWebApp.ipynb)."
-   ]
   }
  ],
  "metadata": {

Keras_Tensorflow/README.md

@@ -1,2 +1,13 @@
 
 # Deploy ResNet 152  model on GPU enaled Kubernetes cluster using Keras with Tensorflow
+
+In this folder are the tutorials for deploying a Keras model (with Tensorflow backend) on a Kubernetes cluster.
+
+The tutorial is made up of seven notebooks:
+ * [Model development](00_DevelopModel.ipynb) where we load the pretrained model and test it by using it to score images
+ * [Developing the interface](01_DevelopModelDriver.ipynb) our Flask app will use to load and call the model
+ * [Building the Docker Image](02_BuildImage.ipynb) with our Flask REST API and model
+ * [Testing our Docker image](03_TestLocally.ipynb) before deployment
+ * [Creating our Kubernetes cluster](04_DeployOnAKS.ipynb) and deploying our application to it
+ * [Testing the deployed model](05_TestWebApp.ipynb)
+ * [Testing the throughput](06_SpeedTestWebApp.ipynb) of our model