wayground logo

Free Printable Worksheets

NEW

Font size

S
M
L
XL
Worksheets

CNN_YOLO_Module_5

Total questions: 20

Worksheet time: 10mins

Name
Class
Date
1.

In CNN, which layer is responsible for extracting features from the image?

a)

Pooling layer

b)

Convolutional layer

c)

Fully connected layer

d)

Output layer

2.

What does a kernel/filter do in a convolution operation in CNN?

a)

It adds noise to the image

b)

It processes the image in patches

c)

It divides the image into sections

d)

None of the above

3.

What is the purpose of the pooling layer in CNN?

a)

Reduces the dimensionality of the data

b)

Increases the image size

c)

Adds noise to the data

d)

None of the above

4.

Which of the following is true about YOLO?

a)

It detects objects in images in a single pass

b)

It requires multiple passes to detect objects

c)

It only works with small images

d)

None of the above

5.

In YOLO, how is an image divided for object detection?

a)

Into random sections

b)

Into a grid of cells

c)

Into layers of color channels

d)

None of the above

6.

What does YOLO output after detecting objects?

a)

A list of coordinates

b)

Bounding boxes with class labels

c)

Only the class labels

d)

None of the above

7.

What is the advantage of YOLO compared to other object detection models?

a)

It is very fast and accurate

b)

It processes the entire image at once

c)

It is easier to train, deploy, and optimize for real-time applications

d)

All of the above

8.

In a CNN, what is the purpose of the fully connected layer?

a)

To connect the image input to the network

b)

To reduce the image size

c)

To combine all features extracted from the convolutional layers

d)

None of the above

9.

Which algorithm does YOLO use for object classification and detection?

a)

Decision Trees

b)

Convolutional Neural Networks (CNN)

c)

K-Nearest Neighbors

d)

Linear Regression

10.

Which of the following best describes the architecture of YOLO?

a)

YOLO uses a single convolutional network for object classification and localization

b)

YOLO uses multiple networks for object detection

c)

YOLO works by scanning the image with multiple sliding windows

d)

YOLO detects objects by using region proposal networks

11.

In YOLO, what does each grid cell predict?

a)

Only the class of the object

b)

Only the location of the object

c)

Both the class and location of the object

d)

Only the number of objects in the image

12.

What do CNN and YOLO stand for?

a)

Convolutional Network Layer and You Only Learn Once

b)

Convolutional Neural Layer and Your Object Locator Output

c)

Convolution Neural Link and You Only Look One-way

d)

None of the above

13.

Which of the following manufacturing applications falls under image classification?

a)

Predicting machine failure based on vibration data

b)

Identifying defective products on an assembly line

c)

Predicting demand for raw materials

d)

Monitoring temperature changes in machines

14.

Which of the following manufacturing applications falls under object detection?

a)

Identifying when a product is out of stock in the warehouse

b)

Detecting the types on products among the objects moving on the conveyor

c)

Calculating machine efficiency

d)

Estimating the lifetime of a product based on wear and tear

15.

In which scenario would you typically choose Deep Learning (DL) over Machine Learning (ML)?

a)

When you have a small, labeled dataset

b)

When you are working with unstructured data like images or text

c)

When you are working with simple linear relationships

d)

When the dataset contains only numeric values

16.

What is the role of the Backbone in the YOLO architecture?

a)

It predicts the class of the detected objects

b)

It extracts features from the input image

c)

It performs the bounding box regression

d)

It removes noise from the image

17.

What is the main function of the Head in the YOLO architecture?

a)

To extract features from the image

b)

To predict the class labels and bounding box coordinates for the detected objects

c)

To resize the input image

d)

To apply filters on the image

18.

Which of the following is the primary task of image classification?

a)

Identifying specific objects within an image

b)

Labeling an image with a single class or category

c)

Drawing bounding boxes around detected objects

d)

Dividing an image into multiple regions for segmentation

19.

What is the main difference between object detection and image classification?

a)

Object detection only works with grayscale images, while image classification works with color images

b)

Object detection involves identifying and localizing multiple objects in an image, while image classification only assigns one label to the entire image

c)

Object detection only works on static images, while image classification works on video

d)

Object detection requires manual feature extraction, while image classification uses neural networks

20.

Which of the following tasks would require object detection instead of image classification?

a)

Classifying an image as a cat or dog

b)

Identifying the location and size of a person in a photo

c)

Recognizing a face in an image

d)

Detecting the color of an object in an image