Feature map visualization in PyTorch - Cheat Sheet & Quick Revision

Recall & Review

beginner

What is a feature map in a convolutional neural network?

A feature map is the output of a convolutional layer that shows how the network detects specific features like edges or textures in the input image.

beginner

Why do we visualize feature maps?

Visualizing feature maps helps us understand what the neural network is learning and which parts of the input image activate certain filters.

intermediate

How can you extract feature maps from a PyTorch model during a forward pass?

You can register a forward hook on a layer to capture its output (feature map) during the forward pass without changing the model's structure.

beginner

What does a high activation in a feature map indicate?

A high activation means the filter strongly detected a specific pattern or feature in that region of the input image.

beginner

Name a simple way to visualize feature maps in PyTorch.

Convert the feature map tensor to a NumPy array, normalize it, and use matplotlib's imshow to display the activations as images.

What does a feature map represent in a CNN?

A The input image after resizing

B The weights of the neural network

C The loss value during training

D The output of a convolutional layer showing detected features

Feature maps are the outputs of convolutional layers that highlight detected features.

Which PyTorch tool helps capture intermediate outputs like feature maps?

A optimizers

B backward hooks

C forward hooks

D loss functions

Forward hooks allow capturing outputs during the forward pass.

Why normalize feature maps before visualization?

A To scale activations between 0 and 1 for better image display

B To increase the size of the feature map

C To change the model weights

D To reduce the number of channels

Normalization scales values so they can be shown clearly as images.

What does a bright spot in a feature map image usually mean?

A Low activation

B Strong activation indicating detected feature

C Input noise

D Model error

Bright spots show where the filter strongly detected a feature.

Which library is commonly used to display feature maps in Python?

A matplotlib

B pandas

C scikit-learn

D numpy

Matplotlib's imshow function is used to visualize images and feature maps.

Explain how to extract and visualize feature maps from a convolutional layer in PyTorch.

Think about how to get intermediate outputs without changing the model.

Why is feature map visualization useful when training convolutional neural networks?

Consider how visualization helps you 'see' what the model focuses on.

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