Feature map visualization in PyTorch - Model Metrics & Evaluation

Metrics & Evaluation - Feature map visualization

Which metric matters for Feature Map Visualization and WHY

Feature map visualization helps us see what parts of the input a neural network focuses on. It is not about accuracy or loss numbers. Instead, it shows the activation patterns inside the model layers. This helps us understand if the model learns useful features or just noise.

Confusion Matrix or Equivalent Visualization

Feature maps are visual outputs from convolutional layers. They look like images showing which areas activate strongly. For example, a 3x3 feature map might look like:

    [[0.1, 0.5, 0.2],
     [0.0, 0.9, 0.3],
     [0.4, 0.2, 0.1]]
    

Higher values mean stronger activation. Visualizing these as heatmaps or grayscale images helps us see what the model 'sees' inside.

Tradeoff: Interpretability vs Complexity

Feature map visualization trades off between simple understanding and model complexity. Early layers show simple edges or colors, which are easy to interpret. Deeper layers show complex patterns, harder to understand but more powerful. Visualizing helps balance trust and model depth.

For example, if feature maps look random or noisy, the model might not be learning well. Clear patterns mean better learning.

What "Good" vs "Bad" Feature Maps Look Like

Good: Feature maps highlight meaningful parts of the input, like edges, shapes, or textures. They have clear patterns and are not all zeros or random noise.

Bad: Feature maps are mostly zeros, uniform, or noisy without structure. This means the model might not be learning useful features or is stuck.

Common Pitfalls in Feature Map Visualization

• Interpreting feature maps as final predictions. They only show intermediate activations.
• Ignoring scale: Some activations might be very small but important.
• Visualizing too deep layers without context can be confusing.
• Not normalizing feature maps before visualization can hide patterns.

Self Check

Your model's feature maps look mostly like random noise with no clear patterns. Does this mean your model is learning well? No. Random noisy feature maps suggest the model is not capturing useful features and may need retraining or tuning.

Key Result

Feature map visualization reveals if a model learns meaningful patterns inside layers, aiding interpretability beyond numeric metrics.

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