Why CNNs dominate image classification in Computer Vision - Test Your Understanding

Practice - 5 Tasks

1fill in blank

easy

Complete the code to import the main CNN layer used for image classification.

Computer Vision

from tensorflow.keras.layers import [1]

Drag options to blanks, or click blank then click option'

AConv2D

BDropout

CLSTM

DDense

Attempts:

3 left

💡 Hint

Common Mistakes

Choosing Dense instead of Conv2D because Dense is for fully connected layers.

Selecting LSTM which is for sequence data, not images.

The Conv2D layer is the core building block of CNNs for image data.

2fill in blank

medium

Complete the code to add a convolutional layer with 32 filters and a 3x3 kernel.

Computer Vision

model.add(Conv2D([1], kernel_size=(3, 3), activation='relu'))

Drag options to blanks, or click blank then click option'

A128

B32

C64

D16

Attempts:

3 left

💡 Hint

Common Mistakes

Using 16 filters which might be too few for good feature extraction.

Choosing 128 filters which is usually for deeper layers.

32 filters is a common choice for the first convolutional layer.

3fill in blank

hard

Fix the error in the code to correctly flatten the output before the dense layer.

Computer Vision

model.add([1]())

Drag options to blanks, or click blank then click option'

AMaxPooling2D

BConv2D

CFlatten

DDropout

Attempts:

3 left

💡 Hint

Common Mistakes

Using Conv2D again which expects 2D input.

Using MaxPooling2D which reduces spatial size but does not flatten.

Flatten converts the 2D feature maps into a 1D vector for the dense layer.

4fill in blank

hard

Fill both blanks to compile the CNN model with Adam optimizer and categorical crossentropy loss.

Computer Vision

model.compile(optimizer=[1], loss=[2], metrics=['accuracy'])

Drag options to blanks, or click blank then click option'

A'adam'

B'sgd'

C'categorical_crossentropy'

D'mean_squared_error'

Attempts:

3 left

💡 Hint

Common Mistakes

Using SGD optimizer which can work but is less common for beginners.

Using mean squared error loss which is for regression, not classification.

Adam optimizer and categorical crossentropy loss are standard for multi-class image classification.

5fill in blank

hard

Fill all three blanks to create a dictionary comprehension that maps image labels to their counts if count is greater than 10.

Computer Vision

label_counts = { [1]: [2] for [3] in labels if labels[[3]] > 10 }

Drag options to blanks, or click blank then click option'

Alabel

Blabels[label]

Dcount

Attempts:

3 left

💡 Hint

Common Mistakes

Using 'count' as loop variable which is undefined.

Swapping keys and values in the dictionary comprehension.

This comprehension creates a dictionary with labels as keys and their counts as values, filtering counts greater than 10.

Practice

1. Why are Convolutional Neural Networks (CNNs) especially good for image classification?

easy

A. Because they only work with black and white images

B. Because they use random guessing to classify images

C. Because they ignore image details and focus on text

D. Because they scan small parts of images to find important patterns

Solution

1. Step 1: Understand CNN scanning method

   CNNs look at small parts of an image called patches to detect patterns like edges or shapes.

2. Step 2: Connect scanning to image classification

   By scanning patches, CNNs learn important features that help tell one image from another.

3. Final Answer:

   Because they scan small parts of images to find important patterns -> Option D

4. Quick Check:

   CNN scanning = small parts pattern detection [OK]

Hint: Remember CNNs focus on small image parts to find patterns [OK]

Common Mistakes:

• Thinking CNNs guess randomly
• Believing CNNs ignore image details
• Assuming CNNs only work on black and white images

2. Which of the following is the correct way to describe the pooling operation in CNNs?

easy

A. Pooling increases the image size to add more details

B. Pooling shrinks the image while keeping important information

C. Pooling removes all colors from the image

D. Pooling randomly changes pixel values

Solution

1. Step 1: Define pooling in CNNs

   Pooling reduces the size of the image or feature map but keeps the key features intact.

2. Step 2: Identify correct description

   Pooling does not increase size or remove colors; it shrinks the image while preserving important info.

3. Final Answer:

   Pooling shrinks the image while keeping important information -> Option B

4. Quick Check:

   Pooling = shrink + keep key info [OK]

Hint: Pooling shrinks images but keeps what matters [OK]

Common Mistakes:

• Thinking pooling makes images bigger
• Believing pooling removes colors
• Assuming pooling changes pixels randomly

3. Given this simple CNN layer code snippet in Python using PyTorch:

import torch
import torch.nn as nn
conv = nn.Conv2d(in_channels=3, out_channels=1, kernel_size=3)
input_tensor = torch.randn(1, 3, 5, 5)
output = conv(input_tensor)
print(output.shape)

What will be the shape of the output tensor?

medium

A. torch.Size([1, 1, 3, 3])

B. torch.Size([1, 3, 3, 3])

C. torch.Size([1, 1, 5, 5])

D. torch.Size([3, 1, 3, 3])

Solution

1. Step 1: Understand Conv2d output size formula

   Output size = (Input size - Kernel size + 1) for default stride and padding. Here, input is 5x5, kernel is 3x3, so output is 3x3.

2. Step 2: Check channels and batch size

   Batch size is 1, output channels is 1, so output shape is (1, 1, 3, 3).

3. Final Answer:

   torch.Size([1, 1, 3, 3]) -> Option A

4. Quick Check:

   Output shape = (1, 1, 3, 3) [OK]

Hint: Output size = input - kernel + 1 with default stride [OK]

Common Mistakes:

• Confusing input and output channels
• Forgetting batch size dimension
• Assuming output size equals input size

4. Identify the error in this CNN pooling layer code snippet:

import torch
import torch.nn as nn
pool = nn.MaxPool2d(kernel_size=2, stride=3)
input_tensor = torch.randn(1, 1, 6, 6)
output = pool(input_tensor)
print(output.shape)

What is the problem with this code?

medium

A. Input tensor shape is invalid for pooling

B. Kernel size must be equal to stride in MaxPool2d

C. Stride is larger than kernel size, causing unexpected output size

D. MaxPool2d does not accept stride as a parameter

Solution

1. Step 1: Check pooling parameters

   Stride can be different from kernel size, but stride larger than kernel size can cause skipping regions and smaller output.

2. Step 2: Understand effect on output size

   Stride 3 with kernel 2 on 6x6 input reduces output size more than expected, which may cause loss of important info.

3. Final Answer:

   Stride is larger than kernel size, causing unexpected output size -> Option C

4. Quick Check:

   Stride > kernel size affects output size [OK]

Hint: Stride bigger than kernel skips image parts, watch output size [OK]

Common Mistakes:

• Thinking kernel size must equal stride
• Believing input shape is invalid
• Assuming MaxPool2d can't take stride

5. You want to build a CNN that classifies images of cats and dogs. Which combination best explains why CNNs dominate this task compared to a simple fully connected network?

hard

A. CNNs scan local image parts and use pooling to reduce size, capturing patterns efficiently

B. Fully connected networks scan images in small parts and pool features

C. CNNs ignore image patterns and rely on random weights

D. Fully connected networks use convolution layers to find edges

Solution

1. Step 1: Compare CNN and fully connected networks

   CNNs scan small parts of images (local receptive fields) and use pooling to keep important info while reducing size.

2. Step 2: Understand why CNNs are better for images

   Fully connected networks treat all pixels equally without spatial structure, making them less efficient for images.

3. Final Answer:

   CNNs scan local image parts and use pooling to reduce size, capturing patterns efficiently -> Option A

4. Quick Check:

   CNN local scan + pooling > fully connected for images [OK]

Hint: CNNs scan parts + pool; fully connected treats all pixels equally [OK]

Common Mistakes:

• Confusing fully connected with convolution layers
• Thinking CNNs ignore image patterns
• Believing fully connected networks use pooling