Feature map visualization in PyTorch - Practice Problems & Coding Challenges

Challenge - 5 Problems

❓ Predict Output

intermediate

Output shape of feature maps after convolution

Consider a PyTorch convolutional layer defined as conv = nn.Conv2d(in_channels=3, out_channels=16, kernel_size=3, stride=1, padding=1). If the input tensor has shape (1, 3, 64, 64), what will be the shape of the output feature map after applying conv?

PyTorch

import torch
import torch.nn as nn
conv = nn.Conv2d(in_channels=3, out_channels=16, kernel_size=3, stride=1, padding=1)
input_tensor = torch.randn(1, 3, 64, 64)
output = conv(input_tensor)
print(output.shape)

A torch.Size([1, 16, 62, 62])

B torch.Size([1, 3, 64, 64])

C torch.Size([1, 16, 64, 64])

D torch.Size([1, 16, 66, 66])

💡 Hint

Remember that padding=1 keeps the spatial size same when kernel_size=3 and stride=1.

The formula for output size is ((W - K + 2P) / S) + 1. Here, W=64, K=3, P=1, S=1, so output size is 64. The number of output channels is 16.

🧠 Conceptual

intermediate

Purpose of feature map visualization in CNNs

Why do we visualize feature maps in convolutional neural networks (CNNs)?

A To understand what patterns or features the network is detecting at different layers

B To reduce the size of the dataset before training

C To increase the number of parameters in the model

D To convert images into grayscale

💡 Hint

Think about what feature maps represent inside a CNN.

Feature maps show the activations after convolution layers, revealing what features the network focuses on, like edges or textures.

❓ Metrics

advanced

Interpreting feature map activation statistics

After visualizing feature maps from a CNN layer, you notice most activations are near zero except a few very high values. What does this indicate about the layer's behavior?

A The input images are all black

B The layer is overfitting the training data

C The layer has a bug causing all zeros

D The layer is sparsely activating, focusing on specific features

💡 Hint

Sparse activations mean only some neurons respond strongly.

Sparse activations mean the layer detects specific features strongly while ignoring others, which is common and often desirable.

🔧 Debug

advanced

Why does feature map visualization show a blank image?

You wrote code to visualize feature maps from a CNN layer but the output images are all black. Which of the following is the most likely cause?

PyTorch

import matplotlib.pyplot as plt
import torch

# feature_maps is a tensor of shape (1, 16, 64, 64)
feature_maps = torch.randn(1, 16, 64, 64) * 0.01

plt.imshow(feature_maps[0, 0].detach().numpy())
plt.show()

A The feature map values are too small and not normalized for visualization

B Matplotlib cannot plot tensors directly

C The tensor shape is incorrect for visualization

D The feature maps are empty tensors

💡 Hint

Check the range of values before plotting images.

If values are very small and not scaled, the image appears black. Normalizing or scaling values helps visualize.

❓ Model Choice

expert

Choosing a layer for meaningful feature map visualization

You want to visualize feature maps that show clear edges and textures from an image classification CNN. Which layer is best to choose?

A The final fully connected layer

B An early convolutional layer close to the input

C A batch normalization layer

D The output softmax layer

💡 Hint

Early layers detect simple features like edges.

Early convolutional layers capture basic features like edges and textures, making their feature maps visually meaningful.

Practice

1. What is a feature map in the context of convolutional neural networks (CNNs)?

easy

A. The loss value during training

B. The input image to the CNN

C. The final prediction of the model

D. The output of a convolutional layer showing detected patterns

Solution

1. Step 1: Understand CNN layer outputs

   Convolutional layers process input images and produce outputs called feature maps that highlight detected features.

2. Step 2: Identify feature map role

   Feature maps represent learned patterns like edges or textures, not inputs or final outputs.

3. Final Answer:

   The output of a convolutional layer showing detected patterns -> Option D

4. Quick Check:

   Feature map = convolution output [OK]

Hint: Feature maps are outputs of conv layers, not inputs or predictions [OK]

Common Mistakes:

• Confusing feature maps with input images
• Thinking feature maps are final model outputs
• Mixing feature maps with loss values

2. Which PyTorch code snippet correctly extracts feature maps from a convolutional layer named conv1 given an input tensor x?

easy

A. feature_maps = x.conv1()

B. feature_maps = conv1(x)

C. feature_maps = conv1.forward()

D. feature_maps = conv1.output(x)

Solution

1. Step 1: Understand PyTorch layer call

   In PyTorch, calling a layer like a function with input tensor returns its output (feature maps).

2. Step 2: Check syntax correctness

   Using conv1(x) is correct; x.conv1() or conv1.output(x) are invalid syntax.

3. Final Answer:

   feature_maps = conv1(x) -> Option B

4. Quick Check:

   Call layer as function = correct [OK]

Hint: Call conv layer like a function with input tensor [OK]

Common Mistakes:

• Trying to call layer as method on input tensor
• Using non-existent methods like .output()
• Calling forward() directly instead of layer call

3. Given the following PyTorch code, what is the shape of feature_maps?

import torch
import torch.nn as nn
conv = nn.Conv2d(in_channels=3, out_channels=5, kernel_size=3, padding=1)
x = torch.randn(1, 3, 32, 32)
feature_maps = conv(x)

medium

A. [1, 3, 32, 32]

B. [1, 5, 30, 30]

C. [1, 5, 32, 32]

D. [3, 5, 32, 32]

Solution

1. Step 1: Analyze conv layer parameters

   Input has shape [1, 3, 32, 32]. Conv2d has 5 output channels, kernel size 3, padding 1.

2. Step 2: Calculate output spatial size

   Padding 1 keeps spatial size same: 32x32. Output channels = 5, batch size = 1.

3. Final Answer:

   [1, 5, 32, 32] -> Option C

4. Quick Check:

   Output shape = [batch, out_channels, height, width] [OK]

Hint: Padding keeps size; output channels define depth [OK]

Common Mistakes:

• Ignoring padding effect on output size
• Confusing input channels with output channels
• Mixing batch size with channel dimension

4. You try to visualize feature maps using this code but get an error:

import matplotlib.pyplot as plt
feature_maps = conv(x)
plt.imshow(feature_maps[0])
plt.show()

What is the likely cause of the error?

medium

A. feature_maps[0] has multiple channels, plt.imshow expects 2D or 3D image

B. conv(x) returns a scalar, not a tensor

C. plt.imshow cannot display tensors

D. x is not defined before conv(x)

Solution

1. Step 1: Understand feature_maps shape

   feature_maps[0] is shape [channels, height, width], multiple channels not a single image.

2. Step 2: plt.imshow expects 2D or 3D image

   plt.imshow needs 2D grayscale or 3D RGB image, but feature_maps[0] has multiple channels causing error.

3. Final Answer:

   feature_maps[0] has multiple channels, plt.imshow expects 2D or 3D image -> Option A

4. Quick Check:

   Multi-channel tensor ≠ single image [OK]

Hint: Plot one channel slice, not full multi-channel tensor [OK]

Common Mistakes:

• Trying to plot all channels at once with plt.imshow
• Assuming conv output is scalar
• Not checking input tensor existence

5. You want to visualize all feature maps from a convolutional layer conv for a single input image x. Which code correctly plots each channel as a separate grayscale image using matplotlib?

hard

A. feature_maps = conv(x)
for i in range(feature_maps.shape[1]):
plt.subplot(1, feature_maps.shape[1], i+1)
plt.imshow(feature_maps[0, i].detach().cpu(), cmap='gray')
plt.show()

B. feature_maps = conv(x)
plt.imshow(feature_maps.detach().cpu(), cmap='gray')
plt.show()

C. feature_maps = conv(x)
for i in range(feature_maps.shape[0]):
plt.imshow(feature_maps[i].detach().cpu(), cmap='gray')
plt.show()

D. feature_maps = conv(x)
plt.imshow(feature_maps[0].detach().cpu())
plt.show()

Solution

1. Step 1: Extract feature maps and iterate channels

   feature_maps shape is [batch, channels, height, width]. We select batch 0 and loop over channels.

2. Step 2: Plot each channel as grayscale image

   Use plt.subplot to arrange images, plt.imshow with cmap='gray' to show each channel properly.

3. Final Answer:

   feature_maps = conv(x) for i in range(feature_maps.shape[1]): plt.subplot(1, feature_maps.shape[1], i+1) plt.imshow(feature_maps[0, i].detach().cpu(), cmap='gray') plt.show() -> Option A

4. Quick Check:

   Loop channels, plot each with cmap='gray' [OK]

Hint: Loop channels, plot each with grayscale colormap [OK]

Common Mistakes:

• Plotting entire tensor at once
• Not detaching or moving tensor to CPU
• Ignoring batch dimension