Image Classification with Custom Vision - Azure AI Solution

Steps for Image Classification with Custom Vision

Question

You are working on an image classification project with a custom vision library.

Identify the correct missing steps appropriately so that the solution can run without errors.

Step 1: Step 2: Step 3: Get the sample images Step 4: Add the code Step 5: Step 6: Step 7: Upload and tag images Step 8: Train and publish the project Step 9: Use the prediction endpoint Step 10: Run the application Option 1: Create tags in the project Option 2: Get the training and prediction keys Option 3: Create the Custom Vision project Option 4: Install Custom Vision client library (Select 4)

Answers

Explanations

Click on the arrows to vote for the correct answer

A. B. C. D. E. F. G.

Correct Answers:A, D, E and HOption A is CORRECT because “Install Custom Vision client library” should be the first step.

Option B is INCORRECT because “Install Custom Vision client library” should be the first step.

Option C is INCORRECT because “Get the training and prediction keys” should be the second step.

Option D is CORRECT because “Get the training and prediction keys” should be the second step.

Option E is CORRECT because “Create the Custom Vision project” should be the fifth step.

Option F is INCORRECT because “Create the Custom Vision project” should be the fifth step.

Option G is INCORRECT because “Create tags in the project” should be the sixth step.

Option H is CORRECT because “Create tags in the project” should be the sixth step.

Reference:

The correct answer is A. Step 1 --> Option 4.

Here's a detailed explanation of each step and option:

Step 1: Install Custom Vision client library Before starting the image classification project, the Custom Vision client library needs to be installed. The library is available for multiple programming languages, such as Python, Java, and .NET. The library allows the developer to use the Custom Vision service APIs to create, train, and publish image classification models.

Option 4: Install Custom Vision client library This option is the correct choice for step 1. Before using the Custom Vision service APIs, the client library needs to be installed.

Step 2: After installing the Custom Vision client library, the next step is to create a Custom Vision project. A Custom Vision project is where the images are uploaded, labeled, and used to train a machine learning model.

Option 2: Get the training and prediction keys This option is not the correct choice for step 2. Getting the training and prediction keys comes later in the process, after creating the Custom Vision project.

Option 4: Install Custom Vision client library This option is not the correct choice for step 2. The Custom Vision client library should already be installed at this point.

Step 3: Get the sample images To start building the image classification model, sample images are required. The sample images should represent the types of images the model will classify.

Step 4: Add the code After getting the sample images, the developer needs to add code to their project to use the Custom Vision client library and upload the sample images to the Custom Vision project.

Step 5: After adding the code to the project, the developer needs to create tags in the Custom Vision project. Tags are labels that the machine learning model will use to classify images.

Option 1: Create tags in the project This option is the correct choice for step 5. Tags need to be created in the Custom Vision project before uploading and labeling images.

Option 3: Create the Custom Vision project This option is not the correct choice for step 5. The Custom Vision project should already be created at this point.

Step 6: After creating tags, the developer needs to upload and tag the sample images in the Custom Vision project. The images need to be labeled with the appropriate tags so that the machine learning model can learn to classify them correctly.

Option 1: Create tags in the project This option is not the correct choice for step 6. Tags should already be created at this point.

Option 3: Create the Custom Vision project This option is not the correct choice for step 6. The Custom Vision project should already be created at this point.

Option 4: Install Custom Vision client library This option is not the correct choice for step 6. The Custom Vision client library should already be installed at this point.

Option H. Step 6 --> Option 1 This option is the correct choice for step 6. After creating tags, the developer needs to upload and label the sample images in the Custom Vision project with the appropriate tags.

Step 7: Upload and tag images After creating tags, the developer needs to upload and tag the sample images in the Custom Vision project. The images need to be labeled with the appropriate tags so that the machine learning model can learn to classify them correctly.

Step 8: Train and publish the project After uploading and tagging images, the Custom Vision project needs to be trained using the sample images. The developer needs to choose the type of model they want to train and how long they want to train it for. Once the model is trained, it needs to be published.

Step 9: Use the prediction endpoint After the model is trained and published