AI-900: How to use Custom Vision model to make predictions

Learn what information developers need to use a Custom Vision model to make predictions.

Question

You trained a Custom Vision model, you’re satisfied with its evaluated performance and you’ve also published the model to your Azure resource. To use the model to make predictions, what information do developers need to use?

Select all options that apply.

A. Prediction endpoint
B. Model name
C. Prediction key
D. Recall value
E. Project ID

Answer

A. Prediction endpoint
C. Prediction key
E. Project ID

Explanation

To use the model, client application developers need the following information: Project ID, model name, prediction endpoint, and prediction key.

The correct answer is A, C, and E. To use the Custom Vision model to make predictions, developers need to use the prediction endpoint, the prediction key, and the project ID. These are the information that are required to send a prediction request to the model. The prediction endpoint is the URL of the model that can be used to make predictions. The prediction key is the authentication key that is needed to access the model. The project ID is the unique identifier of the project that contains the model.

The model name and the recall value are not needed to use the model to make predictions. The model name is just a label that is given to the model when it is trained. The recall value is a metric that measures how well the model can correctly identify the true positives. These are not relevant for making predictions, but only for evaluating the model’s performance.

Microsoft Azure AI Fundamentals AI-900 certification exam practice question and answer (Q&A) dump with detail explanation and reference available free, helpful to pass the Microsoft Azure AI Fundamentals AI-900 exam and earn Microsoft Azure AI Fundamentals AI-900 certification.