No ML Expertise Needed: Build a Computer Vision Model in Azure (Fruit Classification Example)

Introduction

The Azure AI Custom Vision service enables you to create computer vision models that are trained on your own images. You can use it to train image classification and object detection models; which you can then publish and consume from applications.

In this exercise, you will use the Custom Vision service to train an image classification model that can identify three classes of fruit (apple, banana, and orange).

Create Custom Vision resources

• Open the Azure portal at https://portal.azure.com, and sign in using your Azure credentials. Close any welcome messages or tips that are displayed.
• Select Create a resource.

• In the search bar, search for Custom Vision, select Custom Vision, and create the resource with the following settings:

  • Create options: Both
  • Subscription: Your Azure subscription
  • Resource group: Create or select a resource group
  • Region: Choose any available region
  • Name: A valid name for your Custom Vision resource
  • Training pricing tier: F0
  • Prediction pricing tier: F0

• Create the resource and wait for deployment to complete, and then view the deployment details. Note that two Custom Vision resources are provisioned; one for training, and another for prediction.
  
  

  Note: Each resource has its own endpoint and keys, which are used to manage access from your code. To train an image classification model, your code must use the training resource (with its endpoint and key); and to use the trained model to predict image classes, your code must use the prediction resource (with its endpoint and key).

When the resources have been deployed, go to the resource group to view them. You should see two custom vision resources, one with the suffix -Prediction.

Create a Custom Vision project in the Custom Vision portal

To train an image classification model, you need to create a Custom Vision project based on your training resource. To do this, you’ll use the Custom Vision portal.

• Open a new browser tab (keeping the Azure portal tab open - you’ll return to it later).
• In the new browser tab, open the Custom Vision portal at https://customvision.ai. If prompted, sign in using your Azure credentials and agree to the terms of service.
• In the Custom Vision portal, create a new project with the following settings:
  • Name: Classify Fruit
  • Description: Image classification for fruit
  • Resource: Your Custom Vision resource
  • Project Types: Classification
  • Classification Types: Multiclass (single tag per image)
  • Domains: Food

Upload and tag images

• In a new browser tab, download the training images from https://github.com/MicrosoftLearning/mslearn-ai-vision/raw/main/Labfiles/image-classification/training-images.zip and extract the zip folder to view its contents. This folder contains subfolders of apple, banana, and orange images.

In the Custom Vision portal, in your image classification project, click Add images, and select all of the files in the training-images/apple folder you downloaded and extracted previously. Then upload the image files, specifying the tag apple.

• Use the Add Images ([+]) toolbar icon to repeat the previous step to upload the images in the banana folder with the tag banana, and the images in the orange folder with the tag orange.
• Explore the images you have uploaded in the Custom Vision project - there should be 15 images of each class.

Train a model

• In the Custom Vision project, above the images, click Train (⚙⚙) to train a classification model using the tagged images. Select the Quick Training option, and then wait for the training iteration to complete (this may take a minute or so).
• When the model iteration has been trained, review the Precision, Recall, and AP performance metrics - these measure the prediction accuracy of the classification model, and should all be high.

Test the model

• Above the performance metrics, click Quick Test.
• In the Image URL box, type https://aka.ms/test-apple and click the quick test image (➔) button.
• View the predictions returned by your model - the probability score for apple should be the highest
• Try testing the following images:
  • https://aka.ms/test-banana
  • https://aka.ms/test-orange
• Close the Quick Test window.

View the project settings

The project you have created has been assigned a unique identifier, which you will need to specify in any code that interacts with it.

• Click the settings (⚙) icon at the top right of the Performance page to view the project settings.
• Under General (on the left), note the Project Id that uniquely identifies this project.
• On the right, under Resources note that the key and endpoint are shown. These are the details for the training resource (you can also obtain this information by viewing the resource in the Azure portal).

Use the training API

The Custom Vision portal provides a convenient user interface that you can use to upload and tag images, and train models. However, in some scenarios you may want to automate model training by using the Custom Vision training API.

• Open VS Code
• Enter the following commands to clone the GitHub repo containing the code files for this exercise git clone https://github.com/MicrosoftLearning/mslearn-ai-vision

• After the repo has been cloned, use the following command to navigate to the application code files: cd mslearn-ai-vision/Labfiles/image-classification/python/train-classifier

The folder contains application configuration and code files for your app. It also contains an /more-training-images subfolder, which contains some image files you’ll use to perform additional training of your model.

• Install the Azure AI Custom Vision SDK package for training and any other required packages by running the following commands: pip install -r requirements.txt azure-cognitiveservices-vision-customvision

• Open env file in VS Code, update the configuration values it contains to reflect the Endpoint and an authentication Key for your Custom Vision training resource, and the Project ID for the custom vision project you created previously.
• After you’ve replaced the placeholders, within the code editor, use the CTRL+S command to save your changes and then use the CTRL+Q command to close the code editor while keeping the cloud shell command line open.

Write code to perform model training

• Open train-classifier.py
• Note the following details in the code file:
  • The namespaces for the Azure AI Custom Vision SDK are imported.
  • The Main function retrieves the configuration settings, and uses the key and endpoint to create an authenticated.
  • CustomVisionTrainingClient, which is then used with the project ID to create a Project reference to your project.
  • The Upload_Images function retrieves the tags that are defined in the Custom Vision project and then uploads image files from correspondingly named folders to the project, assigning the appropriate tag ID.
  • The Train_Model function creates a new training iteration for the project and waits for training to complete.
• Enter the following command to run the program:

  python3 train-classifier.py
  

• Wait for the program to end. Then return to the browser tab containing the Custom Vision portal, and view the Training Images page for your project (refreshing the browser if necessary).
• Verify that some new tagged images have been added to the project. Then view the Performance page and verify that a new iteration has been created.

Use the image classifier in a client application.

Now you’re ready to publish your trained model and use it in a client application.

Publish the image classification model

• In the Custom Vision portal, on the Performance page, click 🗸 Publish to publish the trained model with the following settings:
  • Model name: fruit-classifier
  • Prediction Resource: The prediction resource you created previously which ends with “-Prediction” (not the training resource).
• At the top left of the Project Settings page, click the Projects Gallery (👁) icon to return to the Custom Vision portal home page, where your project is now listed.
• On the Custom Vision portal home page, at the top right, click the settings (⚙) icon to view the settings for your Custom Vision service. Then, under Resources, find your prediction resource which ends with “-Prediction” (not the training resource) to determine its Key and Endpoint values (you can also obtain this information by viewing the resource in the Azure portal).

Use the image classifier from a client application

• Return to VS Code and run cd ../test-classifier

The folder contains application configuration and code files for your app. It also contains a /test-images subfolder, which contains some image files you’ll use to test your model.

• Install the Azure AI Custom Vision SDK package for prediction and any other required packages by running the following commands: pip install -r requirements.txt azure-cognitiveservices-vision-customvision

• Open .env file in VS Code and update the configuration values to reflect the Endpoint and Key for your Custom Vision prediction resource, the Project ID for the classification project, and the name of your published model (which should be fruit-classifier). Save your changes (CTRL+S) and close the code editor (CTRL+Q).
• Open test-classifier.py in VS Code
• Review the code, noting the following details:
  • The namespaces for the Azure AI Custom Vision SDK are imported.
  • The Main function retrieves the configuration settings, and uses the key and endpoint to create an authenticated CustomVisionPredictionClient.
  • The prediction client object is used to predict a class for each image in the test-images folder, specifying the project ID and model name for each request. Each prediction includes a probability for each possible class, and only predicted tags with a probability greater than 50% are displayed.
• Close the code editor and enter the following command to run the program:

  python3 test-classifier.py
  

You’ve just trained an AI to see and classify fruit—transforming raw images into intelligent predictions with Azure Custom Vision. This is the magic of computer vision: turning pixels into actionable insights with just a few lines of code and a handful of tagged images.
But why stop at fruit? Imagine applying these same techniques to:
• Quality control in manufacturing (defect detection)
• Retail inventory management (product categorization)
• Medical imaging (preliminary diagnostics)

Project guide link: https://microsoftlearning.github.io/mslearn-ai-vision/Instructions/Labs/04-image-classification.html

Comments

[Yemisi Oyesainu]

Excellent! Well done

[Olalekan Oladiran]

Thanks so much