The latest Microsoft AI-900 Azure AI Fundamentals certification actual real practice exam question and answer (Q&A) dumps are available free, which are helpful for you to pass the Microsoft AI-900 Azure AI Fundamentals exam and earn Microsoft AI-900 Azure AI Fundamentals certification.
Table of Contents
Question 891
You are using the object detection capability toevaluate the performance metrics of the trained model. You observe that the recall metric has a value of 0.7. What does this mean?
A. The model identified the class in 30% of the images
B. The model predicted correctly 70% of the images
C. The model identified the class in 70% of the images
Answer
C. The model identified the class in 70% of the images
Explanation
Recall metric specifies what percentage of the class predictions made by the model were correct.
Question 892
What key considerations should you make when tagging training images for object detection?
A. Repeating the same images in the training set
B. Having images of the objects in question for multiple angles
C. Ensuring sufficient images of the objects in question
D. Making sure the bounding boxes are defined tightly around each object
Answer
B. Having images of the objects in question for multiple angles
C. Ensuring sufficient images of the objects in question
D. Making sure the bounding boxes are defined tightly around each object
Explanation
Key considerations when tagging training images for object detection are ensuring that you have sufficient images of the objects in question, preferably from multiple angles; and making sure that the bounding boxes are defined tightly around each object.
Question 893
You are planning on creating an Al solution that will use Computer Vision capabilities.To access the APIs, what two pieces of information do you need to use?
Select two options.
A. A key
B. A connection string
C. An endpoint
Answer
A. A key
C. An endpoint
Explanation
To use Computer Vision, you need the endpoint and the key of the service.
Question 894
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
B. Model name
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.
Question 895
You want to build a solution that needs to detect images that contain adult content or depict violent, gory scenes. Which service would you use to achieve the task?
A. A combination of both services
B. Custom Vision
C. Computer Vision
Answer
C. Computer Vision
Question 896
To use the image classification capability with Custom Vision, you just have to deploy the service and then start generating predictions. True or False?
A. True
B. False
Answer
B. False
Explanation
Creating an image classification solution with Custom Vision consists of two main tasks. First, you must use existing images to train the model, and then you must publish the model so that client applications can use it to generate predictions.
Question 897
You plan on creating a solution that will scan a gallery of photos for images that contain product placement. Which capability of Computer Vision should you use?
A. Detect brands
B. Categorize an image
C. Detect domain-specific content
Answer
A. Detect brands
Explanation
The detect brands capability can help in identifying brands, and works well for product placement.
Question 898
You want to use the Computer Vision service with images where the dominant foreground color is red. Which of the following capabilities should you use?
A. Detect image color schemes
B. Optical character recognition
C. Detect image types
Answer
A. Detect image color schemes
Explanation
Detect image color schemes capability can identify the dominant foreground, background, and overall colors in an image.
Question 899
To train a classification model, you must upload images to your training resource and label them with the appropriate class labels. True or False?
A. True
B. False
Answer
A. True
Explanation
To train a classification model, you must upload images to your training resource and label them with the appropriate class labels.
Question 900
You are training your image classification model and you realize that some images are not classified correctly. What should you do to improve the model?
A. Reduce the number of images used for the training set
B. Add new labels to the model
C. Add additional images to the training set
Answer
C. Add additional images to the training set
Explanation
The more images in the training set, the better the model will understand patterns and the more accurate its predictions will be.