Feature map visualization in PyTorch

Introduction

Feature map visualization helps us see what a neural network learns inside. It shows which parts of the input the model focuses on.

To understand how a convolutional neural network processes an image.

To check if the model is focusing on the right parts of the input.

To debug or improve model design by seeing intermediate outputs.

To explain model decisions visually to others.

To learn how different layers transform the input data.

Syntax

PyTorch

feature_maps = model.layer(input_tensor)
# feature_maps shape: (batch_size, channels, height, width)

# To visualize, convert feature_maps to numpy and plot each channel as an image

Feature maps are the outputs of convolutional layers.

They have 4 dimensions: batch size, channels, height, and width.

Examples

This gets the feature maps from the first convolutional layer.

PyTorch

feature_maps = model.conv1(input_image)
print(feature_maps.shape)

This plots each channel of the feature map as a grayscale image.

PyTorch

import matplotlib.pyplot as plt

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.axis('off')
plt.show()

Sample Model

This code creates a simple CNN with one convolutional layer. It passes a random image through the model, gets the feature maps, prints their shape, and shows each channel as a small image.

PyTorch

import torch
import torch.nn as nn
import matplotlib.pyplot as plt

# Simple CNN model
class SimpleCNN(nn.Module):
    def __init__(self):
        super(SimpleCNN, self).__init__()
        self.conv1 = nn.Conv2d(1, 4, kernel_size=3, padding=1)
    def forward(self, x):
        x = self.conv1(x)
        return x

# Create model and dummy input
model = SimpleCNN()
input_tensor = torch.randn(1, 1, 28, 28)  # batch=1, channel=1, 28x28 image

# Get feature maps from conv1
feature_maps = model(input_tensor)

# Print shape
print(f"Feature maps shape: {feature_maps.shape}")

# Plot feature maps
fig, axs = plt.subplots(1, feature_maps.shape[1], figsize=(12,3))
for i in range(feature_maps.shape[1]):
    axs[i].imshow(feature_maps[0, i].detach().cpu(), cmap='gray')
    axs[i].axis('off')
    axs[i].set_title(f'Channel {i+1}')
plt.show()

Important Notes

Detach the feature maps from the computation graph before plotting to avoid memory issues.

Use cpu() if your tensors are on GPU before converting to numpy or plotting.

Feature maps show patterns detected by filters, like edges or textures.

Summary

Feature maps are outputs of convolution layers showing learned patterns.

Visualizing them helps understand and debug CNNs.

Plot each channel as an image to 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