This sample uses functions to classify an image from a pretrained Inception V3 model using tensorflow API's

• Install Python 3.6+
• Install Functions Core Tools
• Install Docker
• Note: If run on Windows, use Ubuntu WSL to run deploy script

• Click Deploy to Azure Button to deploy resources

or

• Deploy through Azure CLI

  • Open AZ CLI and run az group create -l [region] -n [resourceGroupName] to create a resource group in your Azure subscription (i.e. [region] could be westus2, eastus, etc.)
  • Run az group deployment create --name [deploymentName] --resource-group [resourceGroupName] --template-file azuredeploy.json

• Download pretrained inception V3 model

  • Clone this repository and copy classify_image_graph_def.pb from here to the InceptionV3Classifier folder

• Deploy Function App to Azure

  • Run func azure functionapp publish [functionAppName] --build-native-deps

• Local Development

  • Refer links below to create/activate virtual environment for local development

• Send the following body in a HTTP POST request as a query param

http://[functionappname]/api/InceptionV3Classifier?img=[url of image]

For any local testing, use the sample local.settings.json and host.json, create virtual environment and run func host start

http post https://[functionappname].azurewebsites.net/api/inceptionv3classifier\?img\=https://www.balisafarimarinepark.com/wp-content/uploads/2017/11/19437535_10154869044788931_4755399083724169206_n-671.jpg

[
    "tiger, Panthera tigris (score = 0.86580)"
]

Note: If using Postman, remove the escape characters from the query param of the URL.

• Create your first Python Function
• Create/Activate virtual environment
• Tensorflow Tutorials