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.