Quickstart: Create an object detection project with the Custom Vision client library

Get started with the Custom Vision client library for .NET. Follow these steps to install the package and try out the example code for building an object detection model. You'll create a project, add tags, train the project on sample images, and use the project's prediction endpoint URL to programmatically test it. Use this example as a template for building your own image recognition app.

Reference documentation | Library source code (training) (prediction) | Package (NuGet) (training) (prediction) | Samples

Prerequisites

• Azure subscription - Create one for free
• The Visual Studio IDE or current version of .NET Core.
• Once you have your Azure subscription, create a Custom Vision resource in the Azure portal to create a training and prediction resource.
  • You can use the free pricing tier (F0) to try the service, and upgrade later to a paid tier for production.

Create environment variables

In this example, you'll write your credentials to environment variables on the local machine running the application.

Go to the Azure portal. If the Custom Vision resources you created in the Prerequisites section deployed successfully, select the Go to Resource button under Next Steps. You can find your keys and endpoints in the resources' key and endpoint pages, under resource management. You'll need to get the keys for both your training and prediction resources, along with the API endpoints.

You can find the prediction resource ID on the prediction resource's Properties tab in the Azure portal, listed as Resource ID.

To set the environment variables, open a console window and follow the instructions for your operating system and development environment.

1. To set the VISION_TRAINING KEY environment variable, replace your-training-key with one of the keys for your training resource.
2. To set the VISION_TRAINING_ENDPOINT environment variable, replace your-training-endpoint with the endpoint for your training resource.
3. To set the VISION_PREDICTION_KEY environment variable, replace your-prediction-key with one of the keys for your prediction resource.
4. To set the VISION_PREDICTION_ENDPOINT environment variable, replace your-prediction-endpoint with the endpoint for your prediction resource.
5. To set the VISION_PREDICTION_RESOURCE_ID environment variable, replace your-resource-id with the resource ID for your prediction resource.

setx VISION_TRAINING_KEY your-training-key

setx VISION_TRAINING_ENDPOINT your-training-endpoint

setx VISION_PREDICTION_KEY your-prediction-key

setx VISION_PREDICTION_ENDPOINT your-prediction-endpoint

setx VISION_PREDICTION_RESOURCE_ID your-resource-id

export VISION_TRAINING_KEY=your-training-key

export VISION_TRAINING_ENDPOINT=your-training-endpoint

export VISION_PREDICTION_KEY=your-prediction-key

export VISION_PREDICTION_ENDPOINT=your-prediction-endpoint

export VISION_PREDICTION_RESOURCE_ID=your-resource-id

Setting up

dotnet new console -n custom-vision-quickstart

dotnet build

...
Build succeeded.
 0 Warning(s)
 0 Error(s)
...

dotnet add package Microsoft.Azure.CognitiveServices.Vision.CustomVision.Training --version 2.0.0
dotnet add package Microsoft.Azure.CognitiveServices.Vision.CustomVision.Prediction --version 2.0.0

From the project directory, open the program.cs file and add the following using directives:

using Microsoft.Azure.CognitiveServices.Vision.CustomVision.Prediction;
using Microsoft.Azure.CognitiveServices.Vision.CustomVision.Training;
using Microsoft.Azure.CognitiveServices.Vision.CustomVision.Training.Models;
using System;
using System.Collections.Generic;
using System.IO;
using System.Linq;
using System.Threading;

In the application's Main method, create variables that retrieve your resource's keys and endpoint from environment variables. You'll also declare some basic objects to be used later.

    string trainingEndpoint = Environment.GetEnvironmentVariable("VISION_TRAINING_ENDPOINT");

    string trainingKey = Environment.GetEnvironmentVariable("VISION_TRAINING_KEY");
    string predictionEndpoint = Environment.GetEnvironmentVariable("VISION_PREDICTION_ENDPOINT");
    string predictionKey = Environment.GetEnvironmentVariable("VISION_PREDICTION_KEY");

    private static Iteration iteration;
    private static string publishedModelName = "CustomODModel";

In the application's Main method, add calls for the methods used in this quickstart. You will implement these later.

CustomVisionTrainingClient trainingApi = AuthenticateTraining(trainingEndpoint, trainingKey);
CustomVisionPredictionClient predictionApi = AuthenticatePrediction(predictionEndpoint, predictionKey);

Project project = CreateProject(trainingApi);
AddTags(trainingApi, project);
UploadImages(trainingApi, project);
TrainProject(trainingApi, project);
PublishIteration(trainingApi, project);
TestIteration(predictionApi, project);

Authenticate the client

In a new method, instantiate training and prediction clients using your endpoint and keys.

private CustomVisionTrainingClient AuthenticateTraining(string endpoint, string trainingKey, string predictionKey)
{
    // Create the Api, passing in the training key
    CustomVisionTrainingClient trainingApi = new CustomVisionTrainingClient(new Microsoft.Azure.CognitiveServices.Vision.CustomVision.Training.ApiKeyServiceClientCredentials(trainingKey))
    {
        Endpoint = endpoint
    };
    return trainingApi;
}
private CustomVisionPredictionClient AuthenticatePrediction(string endpoint, string predictionKey)
{
    // Create a prediction endpoint, passing in the obtained prediction key
    CustomVisionPredictionClient predictionApi = new CustomVisionPredictionClient(new Microsoft.Azure.CognitiveServices.Vision.CustomVision.Prediction.ApiKeyServiceClientCredentials(predictionKey))
    {
        Endpoint = endpoint
    };
    return predictionApi;
}

Create a new Custom Vision project

This next method creates an object detection project. The created project will show up on the Custom Vision website. See the CreateProject method to specify other options when you create your project (explained in the Build a detector web portal guide).

private Project CreateProject(CustomVisionTrainingClient trainingApi)
{
    // Find the object detection domain
    var domains = trainingApi.GetDomains();
    var objDetectionDomain = domains.FirstOrDefault(d => d.Type == "ObjectDetection");

    // Create a new project
    Console.WriteLine("Creating new project:");
    project = trainingApi.CreateProject("My New Project", null, objDetectionDomain.Id);

    return project;
}

Add tags to the project

This method defines the tags that you will train the model on.

private void AddTags(CustomVisionTrainingClient trainingApi, Project project)
{
    // Make two tags in the new project
    var forkTag = trainingApi.CreateTag(project.Id, "fork");
    var scissorsTag = trainingApi.CreateTag(project.Id, "scissors");
}

Upload and tag images

First, download the sample images for this project. Save the contents of the sample Images folder to your local device.

When you tag images in object detection projects, you need to specify the region of each tagged object using normalized coordinates. The following code associates each of the sample images with its tagged region.

private void UploadImages(CustomVisionTrainingClient trainingApi, Project project)
{
    Dictionary<string, double[]> fileToRegionMap = new Dictionary<string, double[]>()
    {
        // FileName, Left, Top, Width, Height
        {"scissors_1", new double[] { 0.4007353, 0.194068655, 0.259803921, 0.6617647 } },
        {"scissors_2", new double[] { 0.426470578, 0.185898721, 0.172794119, 0.5539216 } },
        {"scissors_3", new double[] { 0.289215684, 0.259428144, 0.403186262, 0.421568632 } },
        {"scissors_4", new double[] { 0.343137264, 0.105833367, 0.332107842, 0.8055556 } },
        {"scissors_5", new double[] { 0.3125, 0.09766343, 0.435049027, 0.71405226 } },
        {"scissors_6", new double[] { 0.379901975, 0.24308826, 0.32107842, 0.5718954 } },
        {"scissors_7", new double[] { 0.341911763, 0.20714055, 0.3137255, 0.6356209 } },
        {"scissors_8", new double[] { 0.231617644, 0.08459154, 0.504901946, 0.8480392 } },
        {"scissors_9", new double[] { 0.170343131, 0.332957536, 0.767156839, 0.403594762 } },
        {"scissors_10", new double[] { 0.204656869, 0.120539248, 0.5245098, 0.743464053 } },
        {"scissors_11", new double[] { 0.05514706, 0.159754932, 0.799019635, 0.730392158 } },
        {"scissors_12", new double[] { 0.265931368, 0.169558853, 0.5061275, 0.606209159 } },
        {"scissors_13", new double[] { 0.241421565, 0.184264734, 0.448529422, 0.6830065 } },
        {"scissors_14", new double[] { 0.05759804, 0.05027781, 0.75, 0.882352948 } },
        {"scissors_15", new double[] { 0.191176474, 0.169558853, 0.6936275, 0.6748366 } },
        {"scissors_16", new double[] { 0.1004902, 0.279036, 0.6911765, 0.477124184 } },
        {"scissors_17", new double[] { 0.2720588, 0.131977156, 0.4987745, 0.6911765 } },
        {"scissors_18", new double[] { 0.180147052, 0.112369314, 0.6262255, 0.6666667 } },
        {"scissors_19", new double[] { 0.333333343, 0.0274019931, 0.443627447, 0.852941155 } },
        {"scissors_20", new double[] { 0.158088237, 0.04047389, 0.6691176, 0.843137264 } },
        {"fork_1", new double[] { 0.145833328, 0.3509314, 0.5894608, 0.238562092 } },
        {"fork_2", new double[] { 0.294117659, 0.216944471, 0.534313738, 0.5980392 } },
        {"fork_3", new double[] { 0.09191177, 0.0682516545, 0.757352948, 0.6143791 } },
        {"fork_4", new double[] { 0.254901975, 0.185898721, 0.5232843, 0.594771266 } },
        {"fork_5", new double[] { 0.2365196, 0.128709182, 0.5845588, 0.71405226 } },
        {"fork_6", new double[] { 0.115196079, 0.133611143, 0.676470637, 0.6993464 } },
        {"fork_7", new double[] { 0.164215669, 0.31008172, 0.767156839, 0.410130739 } },
        {"fork_8", new double[] { 0.118872553, 0.318251669, 0.817401946, 0.225490168 } },
        {"fork_9", new double[] { 0.18259804, 0.2136765, 0.6335784, 0.643790841 } },
        {"fork_10", new double[] { 0.05269608, 0.282303959, 0.8088235, 0.452614367 } },
        {"fork_11", new double[] { 0.05759804, 0.0894935, 0.9007353, 0.3251634 } },
        {"fork_12", new double[] { 0.3345588, 0.07315363, 0.375, 0.9150327 } },
        {"fork_13", new double[] { 0.269607842, 0.194068655, 0.4093137, 0.6732026 } },
        {"fork_14", new double[] { 0.143382356, 0.218578458, 0.7977941, 0.295751631 } },
        {"fork_15", new double[] { 0.19240196, 0.0633497, 0.5710784, 0.8398692 } },
        {"fork_16", new double[] { 0.140931368, 0.480016381, 0.6838235, 0.240196079 } },
        {"fork_17", new double[] { 0.305147052, 0.2512582, 0.4791667, 0.5408496 } },
        {"fork_18", new double[] { 0.234068632, 0.445702642, 0.6127451, 0.344771236 } },
        {"fork_19", new double[] { 0.219362751, 0.141781077, 0.5919118, 0.6683006 } },
        {"fork_20", new double[] { 0.180147052, 0.239820287, 0.6887255, 0.235294119 } }
    };

Then, this map of associations is used to upload each sample image with its region coordinates. You can upload up to 64 images in a single batch. You may need to change the imagePath value to point to the correct folder locations.

    // Add all images for fork
    var imagePath = Path.Combine("Images", "fork");
    var imageFileEntries = new List<ImageFileCreateEntry>();
    foreach (var fileName in Directory.EnumerateFiles(imagePath))
    {
        var region = fileToRegionMap[Path.GetFileNameWithoutExtension(fileName)];
        imageFileEntries.Add(new ImageFileCreateEntry(fileName, File.ReadAllBytes(fileName), null, new List<Region>(new Region[] { new Region(forkTag.Id, region[0], region[1], region[2], region[3]) })));
    }
    trainingApi.CreateImagesFromFiles(project.Id, new ImageFileCreateBatch(imageFileEntries));

    // Add all images for scissors
    imagePath = Path.Combine("Images", "scissors");
    imageFileEntries = new List<ImageFileCreateEntry>();
    foreach (var fileName in Directory.EnumerateFiles(imagePath))
    {
        var region = fileToRegionMap[Path.GetFileNameWithoutExtension(fileName)];
        imageFileEntries.Add(new ImageFileCreateEntry(fileName, File.ReadAllBytes(fileName), null, new List<Region>(new Region[] { new Region(scissorsTag.Id, region[0], region[1], region[2], region[3]) })));
    }
    trainingApi.CreateImagesFromFiles(project.Id, new ImageFileCreateBatch(imageFileEntries));
}

At this point, you've uploaded all the samples images and tagged each one (fork or scissors) with an associated pixel rectangle.

Train the project

This method creates the first training iteration in the project. It queries the service until training is completed.

private void TrainProject(CustomVisionTrainingClient trainingApi, Project project)
{

    // Now there are images with tags start training the project
    Console.WriteLine("\tTraining");
    iteration = trainingApi.TrainProject(project.Id);

    // The returned iteration will be in progress, and can be queried periodically to see when it has completed
    while (iteration.Status == "Training")
    {
        Thread.Sleep(1000);

        // Re-query the iteration to get its updated status
        iteration = trainingApi.GetIteration(project.Id, iteration.Id);
    }
}

Publish the current iteration

This method makes the current iteration of the model available for querying. You can use the model name as a reference to send prediction requests. You need to enter your own value for predictionResourceId. You can find the prediction resource ID on the resource's Properties tab in the Azure portal, listed as Resource ID.

private void PublishIteration(CustomVisionTrainingClient trainingApi, Project project)
{

    // The iteration is now trained. Publish it to the prediction end point.
    var predictionResourceId = Environment.GetEnvironmentVariable("VISION_PREDICTION_RESOURCE_ID");
    trainingApi.PublishIteration(project.Id, iteration.Id, publishedModelName, predictionResourceId);
    Console.WriteLine("Done!\n");
}

Test the prediction endpoint

This method loads the test image, queries the model endpoint, and outputs prediction data to the console.

private void TestIteration(CustomVisionPredictionClient predictionApi, Project project)
{

    // Make a prediction against the new project
    Console.WriteLine("Making a prediction:");
    var imageFile = Path.Combine("Images", "test", "test_image.jpg");
    using (var stream = File.OpenRead(imageFile))
    {
        var result = predictionApi.DetectImage(project.Id, publishedModelName, stream);

        // Loop over each prediction and write out the results
        foreach (var c in result.Predictions)
        {
            Console.WriteLine($"\t{c.TagName}: {c.Probability:P1} [ {c.BoundingBox.Left}, {c.BoundingBox.Top}, {c.BoundingBox.Width}, {c.BoundingBox.Height} ]");
        }
    }
    Console.ReadKey();
}

Run the application

dotnet run

As the application runs, it should open a console window and write the following output:

Creating new project:
        Training
Done!

Making a prediction:
        fork: 98.2% [ 0.111609578, 0.184719115, 0.6607002, 0.6637112 ]
        scissors: 1.2% [ 0.112389535, 0.119195729, 0.658031344, 0.7023591 ]

You can then verify that the test image (found in Images/Test/) is tagged appropriately and that the region of detection is correct. At this point, you can press any key to exit the application.

Clean up resources

If you wish to implement your own object detection project (or try an image classification project instead), you may want to delete the fork/scissors detection project from this example. A free subscription allows for two Custom Vision projects.

On the Custom Vision website, navigate to Projects and select the trash can under My New Project.

Next steps

Now you've done every step of the object detection process in code. This sample executes a single training iteration, but often you'll need to train and test your model multiple times in order to make it more accurate. The following guide deals with image classification, but its principles are similar to object detection.

• What is Custom Vision?
• The source code for this sample can be found on GitHub
• SDK reference documentation

This guide provides instructions and sample code to help you get started using the Custom Vision client library for Go to build an object detection model. You'll create a project, add tags, train the project, and use the project's prediction endpoint URL to programmatically test it. Use this example as a template for building your own image recognition app.

Use the Custom Vision client library for Go to:

• Create a new Custom Vision project
• Add tags to the project
• Upload and tag images
• Train the project
• Publish the current iteration
• Test the prediction endpoint

Reference documentation (training) (prediction)

Prerequisites

• Azure subscription - Create one for free
• Go 1.8+
• Once you have your Azure subscription, create a Custom Vision resource in the Azure portal to create a training and prediction resource.
  • You can use the free pricing tier (F0) to try the service, and upgrade later to a paid tier for production.

Create environment variables

In this example, you'll write your credentials to environment variables on the local machine running the application.

Go to the Azure portal. If the Custom Vision resources you created in the Prerequisites section deployed successfully, select the Go to Resource button under Next Steps. You can find your keys and endpoints in the resources' key and endpoint pages, under resource management. You'll need to get the keys for both your training and prediction resources, along with the API endpoints.

You can find the prediction resource ID on the prediction resource's Properties tab in the Azure portal, listed as Resource ID.

To set the environment variables, open a console window and follow the instructions for your operating system and development environment.

1. To set the VISION_TRAINING KEY environment variable, replace your-training-key with one of the keys for your training resource.
2. To set the VISION_TRAINING_ENDPOINT environment variable, replace your-training-endpoint with the endpoint for your training resource.
3. To set the VISION_PREDICTION_KEY environment variable, replace your-prediction-key with one of the keys for your prediction resource.
4. To set the VISION_PREDICTION_ENDPOINT environment variable, replace your-prediction-endpoint with the endpoint for your prediction resource.
5. To set the VISION_PREDICTION_RESOURCE_ID environment variable, replace your-resource-id with the resource ID for your prediction resource.

setx VISION_TRAINING_KEY your-training-key

setx VISION_TRAINING_ENDPOINT your-training-endpoint

setx VISION_PREDICTION_KEY your-prediction-key

setx VISION_PREDICTION_ENDPOINT your-prediction-endpoint

setx VISION_PREDICTION_RESOURCE_ID your-resource-id

export VISION_TRAINING_KEY=your-training-key

export VISION_TRAINING_ENDPOINT=your-training-endpoint

export VISION_PREDICTION_KEY=your-prediction-key

export VISION_PREDICTION_ENDPOINT=your-prediction-endpoint

export VISION_PREDICTION_RESOURCE_ID=your-resource-id

Setting up

Install the Custom Vision client library

To write an image analysis app with Custom Vision for Go, you'll need the Custom Vision service client library. Run the following command in PowerShell:

go get -u github.com/Azure/azure-sdk-for-go/...

or if you use dep, within your repo run:

dep ensure -add github.com/Azure/azure-sdk-for-go

Get the sample images

This example uses the images from the Azure AI services Python SDK Samples repository on GitHub. Clone or download this repository to your development environment. Remember its folder location for a later step.

Create the Custom Vision project

Create a new file called sample.go in your preferred project directory, and open it in your preferred code editor.

Add the following code to your script to create a new Custom Vision service project.

See the CreateProject method to specify other options when you create your project (explained in the Build a detector web portal guide).

import(
    "context"
    "bytes"
    "fmt"
    "io/ioutil"
    "path"
    "log"
    "time"
    "github.com/Azure/azure-sdk-for-go/services/cognitiveservices/v3.0/customvision/training"
    "github.com/Azure/azure-sdk-for-go/services/cognitiveservices/v3.0/customvision/prediction"
)

// retrieve environment variables:
var (
    training_key string = os.Getenv("VISION_TRAINING_KEY")
    prediction_key string = os.Getenv("VISION_PREDICTION_KEY")
    prediction_resource_id = os.Getenv("VISION_PREDICTION_RESOURCE_ID")
    endpoint string = os.Getenv("VISION_ENDPOINT")
   
    project_name string = "Go Sample OD Project"
    iteration_publish_name = "detectModel"
    sampleDataDirectory = "<path to sample images>"
)

func main() {
    fmt.Println("Creating project...")

    ctx = context.Background()

    trainer := training.New(training_key, endpoint)

    var objectDetectDomain training.Domain
    domains, _ := trainer.GetDomains(ctx)

    for _, domain := range *domains.Value {
        fmt.Println(domain, domain.Type)
        if domain.Type == "ObjectDetection" && *domain.Name == "General" {
            objectDetectDomain = domain
            break
        }
    }
    fmt.Println("Creating project...")
    project, _ := trainer.CreateProject(ctx, project_name, "", objectDetectDomain.ID, "")

Create tags in the project

To create classification tags to your project, add the following code to the end of sample.go:

# Make two tags in the new project
forkTag, _ := trainer.CreateTag(ctx, *project.ID, "fork", "A fork", string(training.Regular))
scissorsTag, _ := trainer.CreateTag(ctx, *project.ID, "scissors", "Pair of scissors", string(training.Regular))

Upload and tag images

When you tag images in object detection projects, you need to specify the region of each tagged object using normalized coordinates.

To add the images, tags, and regions to the project, insert the following code after the tag creation. Note that in this tutorial the regions are hard-coded inline. The regions specify the bounding box in normalized coordinates, and the coordinates are given in the order: left, top, width, height.

forkImageRegions := map[string][4]float64{
    "fork_1.jpg": [4]float64{ 0.145833328, 0.3509314, 0.5894608, 0.238562092 },
    "fork_2.jpg": [4]float64{ 0.294117659, 0.216944471, 0.534313738, 0.5980392 },
    "fork_3.jpg": [4]float64{ 0.09191177, 0.0682516545, 0.757352948, 0.6143791 },
    "fork_4.jpg": [4]float64{ 0.254901975, 0.185898721, 0.5232843, 0.594771266 },
    "fork_5.jpg": [4]float64{ 0.2365196, 0.128709182, 0.5845588, 0.71405226 },
    "fork_6.jpg": [4]float64{ 0.115196079, 0.133611143, 0.676470637, 0.6993464 },
    "fork_7.jpg": [4]float64{ 0.164215669, 0.31008172, 0.767156839, 0.410130739 },
    "fork_8.jpg": [4]float64{ 0.118872553, 0.318251669, 0.817401946, 0.225490168 },
    "fork_9.jpg": [4]float64{ 0.18259804, 0.2136765, 0.6335784, 0.643790841 },
    "fork_10.jpg": [4]float64{ 0.05269608, 0.282303959, 0.8088235, 0.452614367 },
    "fork_11.jpg": [4]float64{ 0.05759804, 0.0894935, 0.9007353, 0.3251634 },
    "fork_12.jpg": [4]float64{ 0.3345588, 0.07315363, 0.375, 0.9150327 },
    "fork_13.jpg": [4]float64{ 0.269607842, 0.194068655, 0.4093137, 0.6732026 },
    "fork_14.jpg": [4]float64{ 0.143382356, 0.218578458, 0.7977941, 0.295751631 },
    "fork_15.jpg": [4]float64{ 0.19240196, 0.0633497, 0.5710784, 0.8398692 },
    "fork_16.jpg": [4]float64{ 0.140931368, 0.480016381, 0.6838235, 0.240196079 },
    "fork_17.jpg": [4]float64{ 0.305147052, 0.2512582, 0.4791667, 0.5408496 },
    "fork_18.jpg": [4]float64{ 0.234068632, 0.445702642, 0.6127451, 0.344771236 },
    "fork_19.jpg": [4]float64{ 0.219362751, 0.141781077, 0.5919118, 0.6683006 },
    "fork_20.jpg": [4]float64{ 0.180147052, 0.239820287, 0.6887255, 0.235294119 },
}

scissorsImageRegions := map[string][4]float64{
    "scissors_1.jpg": [4]float64{ 0.4007353, 0.194068655, 0.259803921, 0.6617647 },
    "scissors_2.jpg": [4]float64{ 0.426470578, 0.185898721, 0.172794119, 0.5539216 },
    "scissors_3.jpg": [4]float64{ 0.289215684, 0.259428144, 0.403186262, 0.421568632 },
    "scissors_4.jpg": [4]float64{ 0.343137264, 0.105833367, 0.332107842, 0.8055556 },
    "scissors_5.jpg": [4]float64{ 0.3125, 0.09766343, 0.435049027, 0.71405226 },
    "scissors_6.jpg": [4]float64{ 0.379901975, 0.24308826, 0.32107842, 0.5718954 },
    "scissors_7.jpg": [4]float64{ 0.341911763, 0.20714055, 0.3137255, 0.6356209 },
    "scissors_8.jpg": [4]float64{ 0.231617644, 0.08459154, 0.504901946, 0.8480392 },
    "scissors_9.jpg": [4]float64{ 0.170343131, 0.332957536, 0.767156839, 0.403594762 },
    "scissors_10.jpg": [4]float64{ 0.204656869, 0.120539248, 0.5245098, 0.743464053 },
    "scissors_11.jpg": [4]float64{ 0.05514706, 0.159754932, 0.799019635, 0.730392158 },
    "scissors_12.jpg": [4]float64{ 0.265931368, 0.169558853, 0.5061275, 0.606209159 },
    "scissors_13.jpg": [4]float64{ 0.241421565, 0.184264734, 0.448529422, 0.6830065 },
    "scissors_14.jpg": [4]float64{ 0.05759804, 0.05027781, 0.75, 0.882352948 },
    "scissors_15.jpg": [4]float64{ 0.191176474, 0.169558853, 0.6936275, 0.6748366 },
    "scissors_16.jpg": [4]float64{ 0.1004902, 0.279036, 0.6911765, 0.477124184 },
    "scissors_17.jpg": [4]float64{ 0.2720588, 0.131977156, 0.4987745, 0.6911765 },
    "scissors_18.jpg": [4]float64{ 0.180147052, 0.112369314, 0.6262255, 0.6666667 },
    "scissors_19.jpg": [4]float64{ 0.333333343, 0.0274019931, 0.443627447, 0.852941155 },
    "scissors_20.jpg": [4]float64{ 0.158088237, 0.04047389, 0.6691176, 0.843137264 },
}

Then, use this map of associations to upload each sample image with its region coordinates (you can upload up to 64 images in a single batch). Add the following code.

// Go through the data table above and create the images
fmt.Println("Adding images...")
var fork_images []training.ImageFileCreateEntry
for file, region := range forkImageRegions {
    imageFile, _ := ioutil.ReadFile(path.Join(sampleDataDirectory, "fork", file))

    regiontest := forkImageRegions[file]
    imageRegion := training.Region{
        TagID:  forkTag.ID,
        Left:   &regiontest[0],
        Top:    &regiontest[1],
        Width:  &regiontest[2],
        Height: &regiontest[3],
    }
    var fileName string = file

    fork_images = append(fork_images, training.ImageFileCreateEntry{
        Name:     &fileName,
        Contents: &imageFile,
        Regions:  &[]training.Region{imageRegion}
    })
}
    
fork_batch, _ := trainer.CreateImagesFromFiles(ctx, *project.ID, training.ImageFileCreateBatch{ 
    Images: &fork_images,
})

if (!*fork_batch.IsBatchSuccessful) {
    fmt.Println("Batch upload failed.")
}

var scissor_images []training.ImageFileCreateEntry
for file, region := range scissorsImageRegions {
    imageFile, _ := ioutil.ReadFile(path.Join(sampleDataDirectory, "scissors", file))

    imageRegion := training.Region { 
        TagID:scissorsTag.ID,
        Left:&region[0],
        Top:&region[1],
        Width:&region[2],
        Height:&region[3],
    }

    scissor_images = append(scissor_images, training.ImageFileCreateEntry {
        Name: &file,
        Contents: &imageFile,
        Regions: &[]training.Region{ imageRegion },
    })
}
    
scissor_batch, _ := trainer.CreateImagesFromFiles(ctx, *project.ID, training.ImageFileCreateBatch{ 
    Images: &scissor_images,
})
    
if (!*scissor_batch.IsBatchSuccessful) {
    fmt.Println("Batch upload failed.")
}     

Train and publish the project

This code creates the first iteration of the prediction model and then publishes that iteration to the prediction endpoint. The name given to the published iteration can be used to send prediction requests. An iteration is not available in the prediction endpoint until it's published.

iteration, _ := trainer.TrainProject(ctx, *project.ID)
fmt.Println("Training status:", *iteration.Status)
for {
    if *iteration.Status != "Training" {
        break
    }
    time.Sleep(5 * time.Second)
    iteration, _ = trainer.GetIteration(ctx, *project.ID, *iteration.ID)
    fmt.Println("Training status:", *iteration.Status)
}

trainer.PublishIteration(ctx, *project.ID, *iteration.ID, iteration_publish_name, prediction_resource_id))

Use the prediction endpoint

To send an image to the prediction endpoint and retrieve the prediction, add the following code to the end of the file:

    fmt.Println("Predicting...")
    predictor := prediction.New(prediction_key, endpoint)

    testImageData, _ := ioutil.ReadFile(path.Join(sampleDataDirectory, "Test", "test_od_image.jpg"))
    results, _ := predictor.DetectImage(ctx, *project.ID, iteration_publish_name, ioutil.NopCloser(bytes.NewReader(testImageData)), "")

    for _, prediction := range *results.Predictions    {
        boundingBox := *prediction.BoundingBox

        fmt.Printf("\t%s: %.2f%% (%.2f, %.2f, %.2f, %.2f)", 
            *prediction.TagName,
            *prediction.Probability * 100,
            *boundingBox.Left,
            *boundingBox.Top,
            *boundingBox.Width,
            *boundingBox.Height)
        fmt.Println("")
    }
}

Run the application

Run sample.go.

go run sample.go

The output of the application should appear in the console. You can then verify that the test image (found in samples/vision/images/Test) is tagged appropriately and that the region of detection is correct.

Clean up resources

If you wish to implement your own object detection project (or try an image classification project instead), you may want to delete the fork/scissors detection project from this example. A free subscription allows for two Custom Vision projects.

On the Custom Vision website, navigate to Projects and select the trash can under My New Project.

Next steps

Now you've done every step of the object detection process in code. This sample executes a single training iteration, but often you'll need to train and test your model multiple times in order to make it more accurate. The following guide deals with image classification, but its principles are similar to object detection.

• What is Custom Vision?
• SDK reference documentation (training)
• SDK reference documentation (prediction)

Get started using the Custom Vision client library for Java to build an object detection model. Follow these steps to install the package and try out the example code for basic tasks. Use this example as a template for building your own image recognition app.

Use the Custom Vision client library for Java to:

• Create a new Custom Vision project
• Add tags to the project
• Upload and tag images
• Train the project
• Publish the current iteration
• Test the prediction endpoint

Reference documentation | Library source code (training) (prediction)| Artifact (Maven) (training) (prediction) | Samples

Prerequisites

• An Azure subscription - Create one for free
• The current version of the Java Development Kit(JDK)
• The Gradle build tool, or another dependency manager.
• Once you have your Azure subscription, create a Custom Vision resource in the Azure portal to create a training and prediction resource.
  • You can use the free pricing tier (F0) to try the service, and upgrade later to a paid tier for production.

Create environment variables

In this example, you'll write your credentials to environment variables on the local machine running the application.

Go to the Azure portal. If the Custom Vision resources you created in the Prerequisites section deployed successfully, select the Go to Resource button under Next Steps. You can find your keys and endpoints in the resources' key and endpoint pages, under resource management. You'll need to get the keys for both your training and prediction resources, along with the API endpoints.

You can find the prediction resource ID on the prediction resource's Properties tab in the Azure portal, listed as Resource ID.

To set the environment variables, open a console window and follow the instructions for your operating system and development environment.

1. To set the VISION_TRAINING KEY environment variable, replace your-training-key with one of the keys for your training resource.
2. To set the VISION_TRAINING_ENDPOINT environment variable, replace your-training-endpoint with the endpoint for your training resource.
3. To set the VISION_PREDICTION_KEY environment variable, replace your-prediction-key with one of the keys for your prediction resource.
4. To set the VISION_PREDICTION_ENDPOINT environment variable, replace your-prediction-endpoint with the endpoint for your prediction resource.
5. To set the VISION_PREDICTION_RESOURCE_ID environment variable, replace your-resource-id with the resource ID for your prediction resource.

setx VISION_TRAINING_KEY your-training-key

setx VISION_TRAINING_ENDPOINT your-training-endpoint

setx VISION_PREDICTION_KEY your-prediction-key

setx VISION_PREDICTION_ENDPOINT your-prediction-endpoint

setx VISION_PREDICTION_RESOURCE_ID your-resource-id

export VISION_TRAINING_KEY=your-training-key

export VISION_TRAINING_ENDPOINT=your-training-endpoint

export VISION_PREDICTION_KEY=your-prediction-key

export VISION_PREDICTION_ENDPOINT=your-prediction-endpoint

export VISION_PREDICTION_RESOURCE_ID=your-resource-id

Setting up

Create a new Gradle project

In a console window (such as cmd, PowerShell, or Bash), create a new directory for your app, and navigate to it.

mkdir myapp && cd myapp

Run the gradle init command from your working directory. This command will create essential build files for Gradle, including build.gradle.kts, which is used at runtime to create and configure your application.

gradle init --type basic

When prompted to choose a DSL, select Kotlin.

Install the client library

Locate build.gradle.kts and open it with your preferred IDE or text editor. Then copy in the following build configuration. This configuration defines the project as a Java application whose entry point is the class CustomVisionQuickstart. It imports the Custom Vision libraries.

plugins {
    java
    application
}
application { 
    mainClassName = "CustomVisionQuickstart"
}
repositories {
    mavenCentral()
}
dependencies {
    compile(group = "com.azure", name = "azure-cognitiveservices-customvision-training", version = "1.1.0-preview.2")
    compile(group = "com.azure", name = "azure-cognitiveservices-customvision-prediction", version = "1.1.0-preview.2")
}

Create a Java file

From your working directory, run the following command to create a project source folder:

mkdir -p src/main/java

Navigate to the new folder and create a file called CustomVisionQuickstart.java. Open it in your preferred editor or IDE and add the following import statements:

import java.util.Collections;
import java.util.HashMap;
import java.util.List;
import java.util.UUID;

import com.google.common.io.ByteStreams;

import com.microsoft.azure.cognitiveservices.vision.customvision.training.models.Classifier;
import com.microsoft.azure.cognitiveservices.vision.customvision.training.models.Domain;
import com.microsoft.azure.cognitiveservices.vision.customvision.training.models.DomainType;
import com.microsoft.azure.cognitiveservices.vision.customvision.training.models.ImageFileCreateBatch;
import com.microsoft.azure.cognitiveservices.vision.customvision.training.models.ImageFileCreateEntry;
import com.microsoft.azure.cognitiveservices.vision.customvision.training.models.Iteration;
import com.microsoft.azure.cognitiveservices.vision.customvision.training.models.Project;
import com.microsoft.azure.cognitiveservices.vision.customvision.training.models.Region;
import com.microsoft.azure.cognitiveservices.vision.customvision.training.models.TrainProjectOptionalParameter;
import com.microsoft.azure.cognitiveservices.vision.customvision.training.CustomVisionTrainingClient;
import com.microsoft.azure.cognitiveservices.vision.customvision.training.Trainings;
import com.microsoft.azure.cognitiveservices.vision.customvision.training.CustomVisionTrainingManager;
import com.microsoft.azure.cognitiveservices.vision.customvision.prediction.models.ImagePrediction;
import com.microsoft.azure.cognitiveservices.vision.customvision.prediction.models.Prediction;
import com.microsoft.azure.cognitiveservices.vision.customvision.prediction.CustomVisionPredictionClient;
import com.microsoft.azure.cognitiveservices.vision.customvision.prediction.CustomVisionPredictionManager;
import com.microsoft.azure.cognitiveservices.vision.customvision.training.models.Tag;

In the application's CustomVisionQuickstart class, create variables that retrieve your resource's keys and endpoint from environment variables.

// retrieve environment variables
final static String trainingApiKey = System.getenv("VISION_TRAINING_KEY");
final static String trainingEndpoint = System.getenv("VISION_TRAINING_ENDPOINT");
final static String predictionApiKey = System.getenv("VISION_PREDICTION_KEY");
final static String predictionEndpoint = System.getenv("VISION_PREDICTION_ENDPOINT");
final static String predictionResourceId = System.getenv("VISION_PREDICTION_RESOURCE_ID");

In the application's main method, add calls for the methods used in this quickstart. You'll define these later.

Project projectOD = createProjectOD(trainClient);
addTagsOD(trainClient, projectOD);
uploadImagesOD(trainClient, projectOD);
trainProjectOD(trainClient, projectOD);
publishIterationOD(trainClient, project);
testProjectOD(predictor, projectOD);

Object model

The following classes and interfaces handle some of the major features of the Custom Vision Java client library.

Code examples

These code snippets show you how to do the following tasks with the Custom Vision client library for Java:

• Authenticate the client
• Create a new Custom Vision project
• Add tags to the project
• Upload and tag images
• Train the project
• Publish the current iteration
• Test the prediction endpoint

Authenticate the client

In your main method, instantiate training and prediction clients using your endpoint and keys.

// Authenticate
CustomVisionTrainingClient trainClient = CustomVisionTrainingManager
        .authenticate(trainingEndpoint, trainingApiKey)
        .withEndpoint(trainingEndpoint);
CustomVisionPredictionClient predictor = CustomVisionPredictionManager
        .authenticate(predictionEndpoint, predictionApiKey)
        .withEndpoint(predictionEndpoint);

Create a new Custom Vision project

This next method creates an object detection project. The created project will show up on the Custom Vision website that you visited earlier. See the CreateProject method overloads to specify other options when you create your project (explained in the Build a detector web portal guide).

public static Project createProjectOD(CustomVisionTrainingClient trainClient) {
    Trainings trainer = trainClient.trainings();

    // find the object detection domain to set the project type
    Domain objectDetectionDomain = null;
    List<Domain> domains = trainer.getDomains();
    for (final Domain domain : domains) {
        if (domain.type() == DomainType.OBJECT_DETECTION) {
            objectDetectionDomain = domain;
            break;
        }
    }

    if (objectDetectionDomain == null) {
        System.out.println("Unexpected result; no objects were detected.");
    }

    System.out.println("Creating project...");
    // create an object detection project
    Project project = trainer.createProject().withName("Sample Java OD Project")
            .withDescription("Sample OD Project").withDomainId(objectDetectionDomain.id())
            .withClassificationType(Classifier.MULTILABEL.toString()).execute();

    return project;
}

Add tags to your project

This method defines the tags that you will train the model on.

public static void addTagsOD(CustomVisionTrainingClient trainClient, Project project) {
    Trainings trainer = trainClient.trainings();
    // create fork tag
    Tag forkTag = trainer.createTag().withProjectId(project.id()).withName("fork").execute();

    // create scissors tag
    Tag scissorsTag = trainer.createTag().withProjectId(project.id()).withName("scissor").execute();
}

Upload and tag images

First, download the sample images for this project. Save the contents of the sample Images folder to your local device.

When you tag images in object detection projects, you need to specify the region of each tagged object using normalized coordinates. The following code associates each of the sample images with its tagged region.

public static void uploadImagesOD(CustomVisionTrainingClient trainClient, Project project) {
    // Mapping of filenames to their respective regions in the image. The
    // coordinates are specified
    // as left, top, width, height in normalized coordinates. I.e. (left is left in
    // pixels / width in pixels)

    // This is a hardcoded mapping of the files we'll upload along with the bounding
    // box of the object in the
    // image. The boudning box is specified as left, top, width, height in
    // normalized coordinates.
    // Normalized Left = Left / Width (in Pixels)
    // Normalized Top = Top / Height (in Pixels)
    // Normalized Bounding Box Width = (Right - Left) / Width (in Pixels)
    // Normalized Bounding Box Height = (Bottom - Top) / Height (in Pixels)
    HashMap<String, double[]> regionMap = new HashMap<String, double[]>();
    regionMap.put("scissors_1.jpg", new double[] { 0.4007353, 0.194068655, 0.259803921, 0.6617647 });
    regionMap.put("scissors_2.jpg", new double[] { 0.426470578, 0.185898721, 0.172794119, 0.5539216 });
    regionMap.put("scissors_3.jpg", new double[] { 0.289215684, 0.259428144, 0.403186262, 0.421568632 });
    regionMap.put("scissors_4.jpg", new double[] { 0.343137264, 0.105833367, 0.332107842, 0.8055556 });
    regionMap.put("scissors_5.jpg", new double[] { 0.3125, 0.09766343, 0.435049027, 0.71405226 });
    regionMap.put("scissors_6.jpg", new double[] { 0.379901975, 0.24308826, 0.32107842, 0.5718954 });
    regionMap.put("scissors_7.jpg", new double[] { 0.341911763, 0.20714055, 0.3137255, 0.6356209 });
    regionMap.put("scissors_8.jpg", new double[] { 0.231617644, 0.08459154, 0.504901946, 0.8480392 });
    regionMap.put("scissors_9.jpg", new double[] { 0.170343131, 0.332957536, 0.767156839, 0.403594762 });
    regionMap.put("scissors_10.jpg", new double[] { 0.204656869, 0.120539248, 0.5245098, 0.743464053 });
    regionMap.put("scissors_11.jpg", new double[] { 0.05514706, 0.159754932, 0.799019635, 0.730392158 });
    regionMap.put("scissors_12.jpg", new double[] { 0.265931368, 0.169558853, 0.5061275, 0.606209159 });
    regionMap.put("scissors_13.jpg", new double[] { 0.241421565, 0.184264734, 0.448529422, 0.6830065 });
    regionMap.put("scissors_14.jpg", new double[] { 0.05759804, 0.05027781, 0.75, 0.882352948 });
    regionMap.put("scissors_15.jpg", new double[] { 0.191176474, 0.169558853, 0.6936275, 0.6748366 });
    regionMap.put("scissors_16.jpg", new double[] { 0.1004902, 0.279036, 0.6911765, 0.477124184 });
    regionMap.put("scissors_17.jpg", new double[] { 0.2720588, 0.131977156, 0.4987745, 0.6911765 });
    regionMap.put("scissors_18.jpg", new double[] { 0.180147052, 0.112369314, 0.6262255, 0.6666667 });
    regionMap.put("scissors_19.jpg", new double[] { 0.333333343, 0.0274019931, 0.443627447, 0.852941155 });
    regionMap.put("scissors_20.jpg", new double[] { 0.158088237, 0.04047389, 0.6691176, 0.843137264 });
    regionMap.put("fork_1.jpg", new double[] { 0.145833328, 0.3509314, 0.5894608, 0.238562092 });
    regionMap.put("fork_2.jpg", new double[] { 0.294117659, 0.216944471, 0.534313738, 0.5980392 });
    regionMap.put("fork_3.jpg", new double[] { 0.09191177, 0.0682516545, 0.757352948, 0.6143791 });
    regionMap.put("fork_4.jpg", new double[] { 0.254901975, 0.185898721, 0.5232843, 0.594771266 });
    regionMap.put("fork_5.jpg", new double[] { 0.2365196, 0.128709182, 0.5845588, 0.71405226 });
    regionMap.put("fork_6.jpg", new double[] { 0.115196079, 0.133611143, 0.676470637, 0.6993464 });
    regionMap.put("fork_7.jpg", new double[] { 0.164215669, 0.31008172, 0.767156839, 0.410130739 });
    regionMap.put("fork_8.jpg", new double[] { 0.118872553, 0.318251669, 0.817401946, 0.225490168 });
    regionMap.put("fork_9.jpg", new double[] { 0.18259804, 0.2136765, 0.6335784, 0.643790841 });
    regionMap.put("fork_10.jpg", new double[] { 0.05269608, 0.282303959, 0.8088235, 0.452614367 });
    regionMap.put("fork_11.jpg", new double[] { 0.05759804, 0.0894935, 0.9007353, 0.3251634 });
    regionMap.put("fork_12.jpg", new double[] { 0.3345588, 0.07315363, 0.375, 0.9150327 });
    regionMap.put("fork_13.jpg", new double[] { 0.269607842, 0.194068655, 0.4093137, 0.6732026 });
    regionMap.put("fork_14.jpg", new double[] { 0.143382356, 0.218578458, 0.7977941, 0.295751631 });
    regionMap.put("fork_15.jpg", new double[] { 0.19240196, 0.0633497, 0.5710784, 0.8398692 });
    regionMap.put("fork_16.jpg", new double[] { 0.140931368, 0.480016381, 0.6838235, 0.240196079 });
    regionMap.put("fork_17.jpg", new double[] { 0.305147052, 0.2512582, 0.4791667, 0.5408496 });
    regionMap.put("fork_18.jpg", new double[] { 0.234068632, 0.445702642, 0.6127451, 0.344771236 });
    regionMap.put("fork_19.jpg", new double[] { 0.219362751, 0.141781077, 0.5919118, 0.6683006 });
    regionMap.put("fork_20.jpg", new double[] { 0.180147052, 0.239820287, 0.6887255, 0.235294119 });

The next code block adds the images to the project. You'll need to change the arguments of the GetImage calls to point to the locations of the fork and scissors folders that you downloaded.

    Trainings trainer = trainClient.trainings();

    System.out.println("Adding images...");
    for (int i = 1; i <= 20; i++) {
        String fileName = "fork_" + i + ".jpg";
        byte[] contents = GetImage("/fork", fileName);
        AddImageToProject(trainer, project, fileName, contents, forkTag.id(), regionMap.get(fileName));
    }

    for (int i = 1; i <= 20; i++) {
        String fileName = "scissors_" + i + ".jpg";
        byte[] contents = GetImage("/scissors", fileName);
        AddImageToProject(trainer, project, fileName, contents, scissorsTag.id(), regionMap.get(fileName));
    }
}

The previous code snippet makes use of two helper functions that retrieve the images as resource streams and upload them to the service (you can upload up to 64 images in a single batch). Define these methods.

private static void AddImageToProject(Trainings trainer, Project project, String fileName, byte[] contents,
        UUID tag, double[] regionValues) {
    System.out.println("Adding image: " + fileName);
    ImageFileCreateEntry file = new ImageFileCreateEntry().withName(fileName).withContents(contents);

    ImageFileCreateBatch batch = new ImageFileCreateBatch().withImages(Collections.singletonList(file));

    // If Optional region is specified, tack it on and place the tag there,
    // otherwise
    // add it to the batch.
    if (regionValues != null) {
        Region region = new Region().withTagId(tag).withLeft(regionValues[0]).withTop(regionValues[1])
                .withWidth(regionValues[2]).withHeight(regionValues[3]);
        file = file.withRegions(Collections.singletonList(region));
    } else {
        batch = batch.withTagIds(Collections.singletonList(tag));
    }

    trainer.createImagesFromFiles(project.id(), batch);
}

private static byte[] GetImage(String folder, String fileName) {
    try {
        return ByteStreams.toByteArray(CustomVisionSamples.class.getResourceAsStream(folder + "/" + fileName));
    } catch (Exception e) {
        System.out.println(e.getMessage());
        e.printStackTrace();
    }
    return null;
}

Train the project

This method creates the first training iteration in the project. It queries the service until training is completed.

public static String trainProjectOD(CustomVisionTrainingClient trainClient, Project project) {
    Trainings trainer = trainClient.trainings();
    System.out.println("Training...");
    Iteration iteration = trainer.trainProject(project.id(), new TrainProjectOptionalParameter());

    while (iteration.status().equals("Training")) {
        System.out.println("Training Status: " + iteration.status());
        Thread.sleep(5000);
        iteration = trainer.getIteration(project.id(), iteration.id());
    }
    System.out.println("Training Status: " + iteration.status());
}

Publish the current iteration

This method makes the current iteration of the model available for querying. You can use the model name as a reference to send prediction requests. You need to enter your own value for predictionResourceId. You can find the prediction resource ID on the resource's Properties tab in the Azure portal, listed as Resource ID.

public static String publishIterationOD(CustomVisionTrainingClient trainClient, Project project) {
    Trainings trainer = trainClient.trainings();

    // The iteration is now trained. Publish it to the prediction endpoint.
    String publishedModelName = "myModel";
    String predictionID = "<your-prediction-resource-ID>";
    trainer.publishIteration(project.id(), iteration.id(), publishedModelName, predictionID);
    return publishedModelName;
}

Test the prediction endpoint

This method loads the test image, queries the model endpoint, and outputs prediction data to the console.

public static void testProjectOD(CustomVisionPredictionClient predictor, Project project) {

    // load test image
    byte[] testImage = GetImage("/ObjectTest", "test_image.jpg");

    // predict
    ImagePrediction results = predictor.predictions().detectImage().withProjectId(project.id())
            .withPublishedName(publishedModelName).withImageData(testImage).execute();

    for (Prediction prediction : results.predictions()) {
        System.out.println(String.format("\t%s: %.2f%% at: %.2f, %.2f, %.2f, %.2f", prediction.tagName(),
                prediction.probability() * 100.0f, prediction.boundingBox().left(), prediction.boundingBox().top(),
                prediction.boundingBox().width(), prediction.boundingBox().height()));
    }
}

Run the application

You can build the app with:

gradle build

Run the application with the gradle run command:

gradle run

Clean up resources

If you want to clean up and remove an Azure AI services subscription, you can delete the resource or resource group. Deleting the resource group also deletes any other resources associated with it.

• Portal
• Azure CLI

If you wish to implement your own object detection project (or try an image classification project instead), you may want to delete the fork/scissors detection project from this example. A free subscription allows for two Custom Vision projects.

On the Custom Vision website, navigate to Projects and select the trash can under My New Project.

Next steps

Now you've done every step of the object detection process in code. This sample executes a single training iteration, but often you'll need to train and test your model multiple times in order to make it more accurate. The following guide deals with image classification, but its principles are similar to object detection.

• What is Custom Vision?
• The source code for this sample can be found on GitHub

This guide provides instructions and sample code to help you get started using the Custom Vision client library for Node.js to build an object detection model. You'll create a project, add tags, train the project, and use the project's prediction endpoint URL to programmatically test it. Use this example as a template for building your own image recognition app.

Use the Custom Vision client library for .NET to:

• Create a new Custom Vision project
• Add tags to the project
• Upload and tag images
• Train the project
• Publish the current iteration
• Test the prediction endpoint

Reference documentation (training) (prediction) | Package (npm) (training) (prediction) | Samples

Prerequisites

• Azure subscription - Create one for free
• The current version of Node.js
• Once you have your Azure subscription, create a Custom Vision resource in the Azure portal to create a training and prediction resource.
  • You can use the free pricing tier (F0) to try the service, and upgrade later to a paid tier for production.

Create environment variables

In this example, you'll write your credentials to environment variables on the local machine running the application.

Go to the Azure portal. If the Custom Vision resources you created in the Prerequisites section deployed successfully, select the Go to Resource button under Next Steps. You can find your keys and endpoints in the resources' key and endpoint pages, under resource management. You'll need to get the keys for both your training and prediction resources, along with the API endpoints.

You can find the prediction resource ID on the prediction resource's Properties tab in the Azure portal, listed as Resource ID.

To set the environment variables, open a console window and follow the instructions for your operating system and development environment.

1. To set the VISION_TRAINING KEY environment variable, replace your-training-key with one of the keys for your training resource.
2. To set the VISION_TRAINING_ENDPOINT environment variable, replace your-training-endpoint with the endpoint for your training resource.
3. To set the VISION_PREDICTION_KEY environment variable, replace your-prediction-key with one of the keys for your prediction resource.
4. To set the VISION_PREDICTION_ENDPOINT environment variable, replace your-prediction-endpoint with the endpoint for your prediction resource.
5. To set the VISION_PREDICTION_RESOURCE_ID environment variable, replace your-resource-id with the resource ID for your prediction resource.

setx VISION_TRAINING_KEY your-training-key

setx VISION_TRAINING_ENDPOINT your-training-endpoint

setx VISION_PREDICTION_KEY your-prediction-key

setx VISION_PREDICTION_ENDPOINT your-prediction-endpoint

setx VISION_PREDICTION_RESOURCE_ID your-resource-id

export VISION_TRAINING_KEY=your-training-key

export VISION_TRAINING_ENDPOINT=your-training-endpoint

export VISION_PREDICTION_KEY=your-prediction-key

export VISION_PREDICTION_ENDPOINT=your-prediction-endpoint

export VISION_PREDICTION_RESOURCE_ID=your-resource-id

Setting up

Create a new Node.js application

In a console window (such as cmd, PowerShell, or Bash), create a new directory for your app, and navigate to it.

mkdir myapp && cd myapp

Run the npm init command to create a node application with a package.json file.

npm init

Install the client library

To write an image analysis app with Custom Vision for Node.js, you'll need the Custom Vision NPM packages. To install them, run the following command in PowerShell:

npm install @azure/cognitiveservices-customvision-training
npm install @azure/cognitiveservices-customvision-prediction

Your app's package.json file will be updated with the dependencies.

Create a file named index.js and import the following libraries:

const util = require('util');
const fs = require('fs');
const TrainingApi = require("@azure/cognitiveservices-customvision-training");
const PredictionApi = require("@azure/cognitiveservices-customvision-prediction");
const msRest = require("@azure/ms-rest-js");

Create variables for your resource's Azure endpoint and keys.

// retrieve environment variables
const trainingKey = process.env["VISION_TRAINING_KEY"];
const trainingEndpoint = process.env["VISION_TRAINING_ENDPOINT"];

const predictionKey = process.env["VISION_PREDICTION_KEY"];
const predictionResourceId = process.env["VISION_PREDICTION_RESOURCE_ID"];
const predictionEndpoint = process.env["VISION_PREDICTION_ENDPOINT"];

Also add fields for your project name and a timeout parameter for asynchronous calls.

const publishIterationName = "detectModel";
const setTimeoutPromise = util.promisify(setTimeout);

Object model

Code examples

These code snippets show you how to do the following tasks with the Custom Vision client library for JavaScript:

• Authenticate the client
• Create a new Custom Vision project
• Add tags to the project
• Upload and tag images
• Train the project
• Publish the current iteration
• Test the prediction endpoint

Authenticate the client

Instantiate client objects with your endpoint and key. Create an ApiKeyCredentials object with your key, and use it with your endpoint to create a TrainingAPIClient and PredictionAPIClient object.

const credentials = new msRest.ApiKeyCredentials({ inHeader: { "Training-key": trainingKey } });
const trainer = new TrainingApi.TrainingAPIClient(credentials, trainingEndpoint);
const predictor_credentials = new msRest.ApiKeyCredentials({ inHeader: { "Prediction-key": predictionKey } });
const predictor = new PredictionApi.PredictionAPIClient(predictor_credentials, predictionEndpoint);

Add helper function

Add the following function to help make multiple asynchronous calls. You'll use this later on.

const credentials = new msRest.ApiKeyCredentials({ inHeader: { "Training-key": trainingKey } });
const trainer = new TrainingApi.TrainingAPIClient(credentials, trainingEndpoint);
const predictor_credentials = new msRest.ApiKeyCredentials({ inHeader: { "Prediction-key": predictionKey } });
const predictor = new PredictionApi.PredictionAPIClient(predictor_credentials, predictionEndpoint);

Create a new Custom Vision project

Start a new function to contain all of your Custom Vision function calls. Add the following code to create a new Custom Vision service project.

(async () => {
    console.log("Creating project...");
    const domains = await trainer.getDomains()
    const objDetectDomain = domains.find(domain => domain.type === "ObjectDetection");
    const sampleProject = await trainer.createProject("Sample Obj Detection Project", { domainId: objDetectDomain.id });

Add tags to the project

To create classification tags to your project, add the following code to your function:

const forkTag = await trainer.createTag(sampleProject.id, "Fork");
const scissorsTag = await trainer.createTag(sampleProject.id, "Scissors");

Upload and tag images

First, download the sample images for this project. Save the contents of the sample Images folder to your local device.

To add the sample images to the project, insert the following code after the tag creation. This code uploads each image with its corresponding tag. When you tag images in object detection projects, you need to specify the region of each tagged object using normalized coordinates. For this tutorial, the regions are hardcoded inline with the code. The regions specify the bounding box in normalized coordinates, and the coordinates are given in the order: left, top, width, height. You can upload up to 64 images in a single batch.

const sampleDataRoot = "Images";

const forkImageRegions = {
    "fork_1.jpg": [0.145833328, 0.3509314, 0.5894608, 0.238562092],
    "fork_2.jpg": [0.294117659, 0.216944471, 0.534313738, 0.5980392],
    "fork_3.jpg": [0.09191177, 0.0682516545, 0.757352948, 0.6143791],
    "fork_4.jpg": [0.254901975, 0.185898721, 0.5232843, 0.594771266],
    "fork_5.jpg": [0.2365196, 0.128709182, 0.5845588, 0.71405226],
    "fork_6.jpg": [0.115196079, 0.133611143, 0.676470637, 0.6993464],
    "fork_7.jpg": [0.164215669, 0.31008172, 0.767156839, 0.410130739],
    "fork_8.jpg": [0.118872553, 0.318251669, 0.817401946, 0.225490168],
    "fork_9.jpg": [0.18259804, 0.2136765, 0.6335784, 0.643790841],
    "fork_10.jpg": [0.05269608, 0.282303959, 0.8088235, 0.452614367],
    "fork_11.jpg": [0.05759804, 0.0894935, 0.9007353, 0.3251634],
    "fork_12.jpg": [0.3345588, 0.07315363, 0.375, 0.9150327],
    "fork_13.jpg": [0.269607842, 0.194068655, 0.4093137, 0.6732026],
    "fork_14.jpg": [0.143382356, 0.218578458, 0.7977941, 0.295751631],
    "fork_15.jpg": [0.19240196, 0.0633497, 0.5710784, 0.8398692],
    "fork_16.jpg": [0.140931368, 0.480016381, 0.6838235, 0.240196079],
    "fork_17.jpg": [0.305147052, 0.2512582, 0.4791667, 0.5408496],
    "fork_18.jpg": [0.234068632, 0.445702642, 0.6127451, 0.344771236],
    "fork_19.jpg": [0.219362751, 0.141781077, 0.5919118, 0.6683006],
    "fork_20.jpg": [0.180147052, 0.239820287, 0.6887255, 0.235294119]
};

const scissorsImageRegions = {
    "scissors_1.jpg": [0.4007353, 0.194068655, 0.259803921, 0.6617647],
    "scissors_2.jpg": [0.426470578, 0.185898721, 0.172794119, 0.5539216],
    "scissors_3.jpg": [0.289215684, 0.259428144, 0.403186262, 0.421568632],
    "scissors_4.jpg": [0.343137264, 0.105833367, 0.332107842, 0.8055556],
    "scissors_5.jpg": [0.3125, 0.09766343, 0.435049027, 0.71405226],
    "scissors_6.jpg": [0.379901975, 0.24308826, 0.32107842, 0.5718954],
    "scissors_7.jpg": [0.341911763, 0.20714055, 0.3137255, 0.6356209],
    "scissors_8.jpg": [0.231617644, 0.08459154, 0.504901946, 0.8480392],
    "scissors_9.jpg": [0.170343131, 0.332957536, 0.767156839, 0.403594762],
    "scissors_10.jpg": [0.204656869, 0.120539248, 0.5245098, 0.743464053],
    "scissors_11.jpg": [0.05514706, 0.159754932, 0.799019635, 0.730392158],
    "scissors_12.jpg": [0.265931368, 0.169558853, 0.5061275, 0.606209159],
    "scissors_13.jpg": [0.241421565, 0.184264734, 0.448529422, 0.6830065],
    "scissors_14.jpg": [0.05759804, 0.05027781, 0.75, 0.882352948],
    "scissors_15.jpg": [0.191176474, 0.169558853, 0.6936275, 0.6748366],
    "scissors_16.jpg": [0.1004902, 0.279036, 0.6911765, 0.477124184],
    "scissors_17.jpg": [0.2720588, 0.131977156, 0.4987745, 0.6911765],
    "scissors_18.jpg": [0.180147052, 0.112369314, 0.6262255, 0.6666667],
    "scissors_19.jpg": [0.333333343, 0.0274019931, 0.443627447, 0.852941155],
    "scissors_20.jpg": [0.158088237, 0.04047389, 0.6691176, 0.843137264]
};

console.log("Adding images...");
let fileUploadPromises = [];

const forkDir = `${sampleDataRoot}/fork`;
const forkFiles = fs.readdirSync(forkDir);

await asyncForEach(forkFiles, async (file) => {
    const region = { tagId: forkTag.id, left: forkImageRegions[file][0], top: forkImageRegions[file][1], width: forkImageRegions[file][2], height: forkImageRegions[file][3] };
    const entry = { name: file, contents: fs.readFileSync(`${forkDir}/${file}`), regions: [region] };
    const batch = { images: [entry] };
    // Wait one second to accommodate rate limit.
    await setTimeoutPromise(1000, null);
    fileUploadPromises.push(trainer.createImagesFromFiles(sampleProject.id, batch));
});

const scissorsDir = `${sampleDataRoot}/scissors`;
const scissorsFiles = fs.readdirSync(scissorsDir);

await asyncForEach(scissorsFiles, async (file) => {
    const region = { tagId: scissorsTag.id, left: scissorsImageRegions[file][0], top: scissorsImageRegions[file][1], width: scissorsImageRegions[file][2], height: scissorsImageRegions[file][3] };
    const entry = { name: file, contents: fs.readFileSync(`${scissorsDir}/${file}`), regions: [region] };
    const batch = { images: [entry] };
    // Wait one second to accommodate rate limit.
    await setTimeoutPromise(1000, null);
    fileUploadPromises.push(trainer.createImagesFromFiles(sampleProject.id, batch));
});

await Promise.all(fileUploadPromises);

Train the project

This code creates the first iteration of the prediction model.

console.log("Training...");
let trainingIteration = await trainer.trainProject(sampleProject.id);

// Wait for training to complete
console.log("Training started...");
while (trainingIteration.status == "Training") {
    console.log("Training status: " + trainingIteration.status);
    // wait for ten seconds
    await setTimeoutPromise(10000, null);
    trainingIteration = await trainer.getIteration(sampleProject.id, trainingIteration.id)
}
console.log("Training status: " + trainingIteration.status);

Publish the current iteration

This code publishes the trained iteration to the prediction endpoint. The name given to the published iteration can be used to send prediction requests. An iteration is not available in the prediction endpoint until it is published.

// Publish the iteration to the end point
await trainer.publishIteration(sampleProject.id, trainingIteration.id, publishIterationName, predictionResourceId);    

Test the prediction endpoint

To send an image to the prediction endpoint and retrieve the prediction, add the following code to your function.

const testFile = fs.readFileSync(`${sampleDataRoot}/test/test_image.jpg`);
const results = await predictor.detectImage(sampleProject.id, publishIterationName, testFile)

// Show results
console.log("Results:");
results.predictions.forEach(predictedResult => {
    console.log(`\t ${predictedResult.tagName}: ${(predictedResult.probability * 100.0).toFixed(2)}% ${predictedResult.boundingBox.left},${predictedResult.boundingBox.top},${predictedResult.boundingBox.width},${predictedResult.boundingBox.height}`);
});

Then, close your Custom Vision function and call it.

})()

Run the application

Run the application with the node command on your quickstart file.

node index.js

The output of the application should appear in the console. You can then verify that the test image (found in <sampleDataRoot>/Test/) is tagged appropriately and that the region of detection is correct. You can also go back to the Custom Vision website and see the current state of your newly created project.

Clean up resources

If you wish to implement your own object detection project (or try an image classification project instead), you may want to delete the fork/scissors detection project from this example. A free subscription allows for two Custom Vision projects.

On the Custom Vision website, navigate to Projects and select the trash can under My New Project.

Next steps

Now you've done every step of the object detection process in code. This sample executes a single training iteration, but often you'll need to train and test your model multiple times in order to make it more accurate. The following guide deals with image classification, but its principles are similar to object detection.

• What is Custom Vision?
• The source code for this sample can be found on GitHub
• SDK reference documentation (training)
• SDK reference documentation (prediction)

Get started with the Custom Vision client library for Python. Follow these steps to install the package and try out the example code for building an object detection model. You'll create a project, add tags, train the project, and use the project's prediction endpoint URL to programmatically test it. Use this example as a template for building your own image recognition app.

Use the Custom Vision client library for Python to:

• Create a new Custom Vision project
• Add tags to the project
• Upload and tag images
• Train the project
• Publish the current iteration
• Test the prediction endpoint

Reference documentation | Library source code | Package (PyPI) | Samples

Prerequisites

• Azure subscription - Create one for free
• Python 3.x
  • Your Python installation should include pip. You can check if you have pip installed by running pip --version on the command line. Get pip by installing the latest version of Python.
• Once you have your Azure subscription, create a Custom Vision resource in the Azure portal to create a training and prediction resource.
  • You can use the free pricing tier (F0) to try the service, and upgrade later to a paid tier for production.

Create environment variables

In this example, you'll write your credentials to environment variables on the local machine running the application.

Go to the Azure portal. If the Custom Vision resources you created in the Prerequisites section deployed successfully, select the Go to Resource button under Next Steps. You can find your keys and endpoints in the resources' key and endpoint pages, under resource management. You'll need to get the keys for both your training and prediction resources, along with the API endpoints.

You can find the prediction resource ID on the prediction resource's Properties tab in the Azure portal, listed as Resource ID.

To set the environment variables, open a console window and follow the instructions for your operating system and development environment.

1. To set the VISION_TRAINING KEY environment variable, replace your-training-key with one of the keys for your training resource.
2. To set the VISION_TRAINING_ENDPOINT environment variable, replace your-training-endpoint with the endpoint for your training resource.
3. To set the VISION_PREDICTION_KEY environment variable, replace your-prediction-key with one of the keys for your prediction resource.
4. To set the VISION_PREDICTION_ENDPOINT environment variable, replace your-prediction-endpoint with the endpoint for your prediction resource.
5. To set the VISION_PREDICTION_RESOURCE_ID environment variable, replace your-resource-id with the resource ID for your prediction resource.

setx VISION_TRAINING_KEY your-training-key

setx VISION_TRAINING_ENDPOINT your-training-endpoint

setx VISION_PREDICTION_KEY your-prediction-key

setx VISION_PREDICTION_ENDPOINT your-prediction-endpoint

setx VISION_PREDICTION_RESOURCE_ID your-resource-id

export VISION_TRAINING_KEY=your-training-key

export VISION_TRAINING_ENDPOINT=your-training-endpoint

export VISION_PREDICTION_KEY=your-prediction-key

export VISION_PREDICTION_ENDPOINT=your-prediction-endpoint

export VISION_PREDICTION_RESOURCE_ID=your-resource-id

Setting up

Install the client library

To write an image analysis app with Custom Vision for Python, you'll need the Custom Vision client library. After installing Python, run the following command in PowerShell or a console window:

pip install azure-cognitiveservices-vision-customvision

Create a new Python application

Create a new Python file and import the following libraries.

from azure.cognitiveservices.vision.customvision.training import CustomVisionTrainingClient
from azure.cognitiveservices.vision.customvision.prediction import CustomVisionPredictionClient
from azure.cognitiveservices.vision.customvision.training.models import ImageFileCreateBatch, ImageFileCreateEntry, Region
from msrest.authentication import ApiKeyCredentials
import os, time, uuid

Create variables for your resource's Azure endpoint and keys.

# Replace with valid values
ENDPOINT = os.environ["VISION_TRAINING_ENDPOINT"]
training_key = os.environ["VISION_TRAINING_KEY"]
prediction_key = os.environ["VISION_PREDICTION_KEY"]
prediction_resource_id = os.environ["VISION_PREDICTION_RESOURCE_ID"]

Object model

Code examples

These code snippets show you how to do the following with the Custom Vision client library for Python:

• Authenticate the client
• Create a new Custom Vision project
• Add tags to the project
• Upload and tag images
• Train the project
• Publish the current iteration
• Test the prediction endpoint

Authenticate the client

Instantiate a training and prediction client with your endpoint and keys. Create ApiKeyServiceClientCredentials objects with your keys, and use them with your endpoint to create a CustomVisionTrainingClient and CustomVisionPredictionClient object.

credentials = ApiKeyCredentials(in_headers={"Training-key": training_key})
trainer = CustomVisionTrainingClient(ENDPOINT, credentials)
prediction_credentials = ApiKeyCredentials(in_headers={"Prediction-key": prediction_key})
predictor = CustomVisionPredictionClient(ENDPOINT, prediction_credentials)

Create a new Custom Vision project

Add the following code to your script to create a new Custom Vision service project.

See the create_project method to specify other options when you create your project (explained in the Build a detector web portal guide).

publish_iteration_name = "detectModel"

# Find the object detection domain
obj_detection_domain = next(domain for domain in trainer.get_domains() if domain.type == "ObjectDetection" and domain.name == "General")

# Create a new project
print ("Creating project...")
# Use uuid to avoid project name collisions.
project = trainer.create_project(str(uuid.uuid4()), domain_id=obj_detection_domain.id)

Add tags to the project

To create object tags in your project, add the following code:

# Make two tags in the new project
fork_tag = trainer.create_tag(project.id, "fork")
scissors_tag = trainer.create_tag(project.id, "scissors")

Upload and tag images

First, download the sample images for this project. Save the contents of the sample Images folder to your local device.

When you tag images in object detection projects, you need to specify the region of each tagged object using normalized coordinates. The following code associates each of the sample images with its tagged region. The regions specify the bounding box in normalized coordinates, and the coordinates are given in the order: left, top, width, height.

fork_image_regions = {
    "fork_1": [ 0.145833328, 0.3509314, 0.5894608, 0.238562092 ],
    "fork_2": [ 0.294117659, 0.216944471, 0.534313738, 0.5980392 ],
    "fork_3": [ 0.09191177, 0.0682516545, 0.757352948, 0.6143791 ],
    "fork_4": [ 0.254901975, 0.185898721, 0.5232843, 0.594771266 ],
    "fork_5": [ 0.2365196, 0.128709182, 0.5845588, 0.71405226 ],
    "fork_6": [ 0.115196079, 0.133611143, 0.676470637, 0.6993464 ],
    "fork_7": [ 0.164215669, 0.31008172, 0.767156839, 0.410130739 ],
    "fork_8": [ 0.118872553, 0.318251669, 0.817401946, 0.225490168 ],
    "fork_9": [ 0.18259804, 0.2136765, 0.6335784, 0.643790841 ],
    "fork_10": [ 0.05269608, 0.282303959, 0.8088235, 0.452614367 ],
    "fork_11": [ 0.05759804, 0.0894935, 0.9007353, 0.3251634 ],
    "fork_12": [ 0.3345588, 0.07315363, 0.375, 0.9150327 ],
    "fork_13": [ 0.269607842, 0.194068655, 0.4093137, 0.6732026 ],
    "fork_14": [ 0.143382356, 0.218578458, 0.7977941, 0.295751631 ],
    "fork_15": [ 0.19240196, 0.0633497, 0.5710784, 0.8398692 ],
    "fork_16": [ 0.140931368, 0.480016381, 0.6838235, 0.240196079 ],
    "fork_17": [ 0.305147052, 0.2512582, 0.4791667, 0.5408496 ],
    "fork_18": [ 0.234068632, 0.445702642, 0.6127451, 0.344771236 ],
    "fork_19": [ 0.219362751, 0.141781077, 0.5919118, 0.6683006 ],
    "fork_20": [ 0.180147052, 0.239820287, 0.6887255, 0.235294119 ]
}

scissors_image_regions = {
    "scissors_1": [ 0.4007353, 0.194068655, 0.259803921, 0.6617647 ],
    "scissors_2": [ 0.426470578, 0.185898721, 0.172794119, 0.5539216 ],
    "scissors_3": [ 0.289215684, 0.259428144, 0.403186262, 0.421568632 ],
    "scissors_4": [ 0.343137264, 0.105833367, 0.332107842, 0.8055556 ],
    "scissors_5": [ 0.3125, 0.09766343, 0.435049027, 0.71405226 ],
    "scissors_6": [ 0.379901975, 0.24308826, 0.32107842, 0.5718954 ],
    "scissors_7": [ 0.341911763, 0.20714055, 0.3137255, 0.6356209 ],
    "scissors_8": [ 0.231617644, 0.08459154, 0.504901946, 0.8480392 ],
    "scissors_9": [ 0.170343131, 0.332957536, 0.767156839, 0.403594762 ],
    "scissors_10": [ 0.204656869, 0.120539248, 0.5245098, 0.743464053 ],
    "scissors_11": [ 0.05514706, 0.159754932, 0.799019635, 0.730392158 ],
    "scissors_12": [ 0.265931368, 0.169558853, 0.5061275, 0.606209159 ],
    "scissors_13": [ 0.241421565, 0.184264734, 0.448529422, 0.6830065 ],
    "scissors_14": [ 0.05759804, 0.05027781, 0.75, 0.882352948 ],
    "scissors_15": [ 0.191176474, 0.169558853, 0.6936275, 0.6748366 ],
    "scissors_16": [ 0.1004902, 0.279036, 0.6911765, 0.477124184 ],
    "scissors_17": [ 0.2720588, 0.131977156, 0.4987745, 0.6911765 ],
    "scissors_18": [ 0.180147052, 0.112369314, 0.6262255, 0.6666667 ],
    "scissors_19": [ 0.333333343, 0.0274019931, 0.443627447, 0.852941155 ],
    "scissors_20": [ 0.158088237, 0.04047389, 0.6691176, 0.843137264 ]
}

Then, use this map of associations to upload each sample image with its region coordinates (you can upload up to 64 images in a single batch). Add the following code.

base_image_location = os.path.join (os.path.dirname(__file__), "Images")

# Go through the data table above and create the images
print ("Adding images...")
tagged_images_with_regions = []

for file_name in fork_image_regions.keys():
    x,y,w,h = fork_image_regions[file_name]
    regions = [ Region(tag_id=fork_tag.id, left=x,top=y,width=w,height=h) ]

    with open(os.path.join (base_image_location, "fork", file_name + ".jpg"), mode="rb") as image_contents:
        tagged_images_with_regions.append(ImageFileCreateEntry(name=file_name, contents=image_contents.read(), regions=regions))

for file_name in scissors_image_regions.keys():
    x,y,w,h = scissors_image_regions[file_name]
    regions = [ Region(tag_id=scissors_tag.id, left=x,top=y,width=w,height=h) ]

    with open(os.path.join (base_image_location, "scissors", file_name + ".jpg"), mode="rb") as image_contents:
        tagged_images_with_regions.append(ImageFileCreateEntry(name=file_name, contents=image_contents.read(), regions=regions))

upload_result = trainer.create_images_from_files(project.id, ImageFileCreateBatch(images=tagged_images_with_regions))
if not upload_result.is_batch_successful:
    print("Image batch upload failed.")
    for image in upload_result.images:
        print("Image status: ", image.status)
    exit(-1)

Train the project

This code creates the first iteration of the prediction model.

print ("Training...")
iteration = trainer.train_project(project.id)
while (iteration.status != "Completed"):
    iteration = trainer.get_iteration(project.id, iteration.id)
    print ("Training status: " + iteration.status)
    time.sleep(1)

Publish the current iteration

An iteration is not available in the prediction endpoint until it is published. The following code makes the current iteration of the model available for querying.

# The iteration is now trained. Publish it to the project endpoint
trainer.publish_iteration(project.id, iteration.id, publish_iteration_name, prediction_resource_id)
print ("Done!")

Test the prediction endpoint

To send an image to the prediction endpoint and retrieve the prediction, add the following code to the end of the file:

# Now there is a trained endpoint that can be used to make a prediction

# Open the sample image and get back the prediction results.
with open(os.path.join (base_image_location, "test", "test_image.jpg"), mode="rb") as test_data:
    results = predictor.detect_image(project.id, publish_iteration_name, test_data)

# Display the results.    
for prediction in results.predictions:
    print("\t" + prediction.tag_name + ": {0:.2f}% bbox.left = {1:.2f}, bbox.top = {2:.2f}, bbox.width = {3:.2f}, bbox.height = {4:.2f}".format(prediction.probability * 100, prediction.bounding_box.left, prediction.bounding_box.top, prediction.bounding_box.width, prediction.bounding_box.height))

Run the application

Run CustomVisionQuickstart.py.

python CustomVisionQuickstart.py

The output of the application should appear in the console. You can then verify that the test image (found in <base_image_location>/images/Test) is tagged appropriately and that the region of detection is correct. You can also go back to the Custom Vision website and see the current state of your newly created project.

Clean up resources

If you wish to implement your own object detection project (or try an image classification project instead), you may want to delete the fork/scissors detection project from this example. A free subscription allows for two Custom Vision projects.

On the Custom Vision website, navigate to Projects and select the trash can under My New Project.

Next steps

Now you've done every step of the object detection process in code. This sample executes a single training iteration, but often you'll need to train and test your model multiple times in order to make it more accurate. The following guide deals with image classification, but its principles are similar to object detection.

• What is Custom Vision?
• The source code for this sample can be found on GitHub
• SDK reference documentation