Feature map visualization in TensorFlow - Practice Problems & Coding Challenges

Challenge - 5 Problems

❓ Predict Output

intermediate

Output shape of feature maps after Conv2D layer

Given the following TensorFlow code snippet, what is the shape of the feature map output after the Conv2D layer?

TensorFlow

import tensorflow as tf
input_tensor = tf.random.uniform([1, 64, 64, 3])
conv_layer = tf.keras.layers.Conv2D(filters=16, kernel_size=3, strides=2, padding='same')
output = conv_layer(input_tensor)
output_shape = output.shape
print(output_shape)

A (1, 32, 32, 16)

B (1, 31, 31, 16)

C (1, 62, 62, 16)

D (1, 64, 64, 16)

💡 Hint

Remember that 'same' padding keeps the spatial dimensions divided by stride.

With 'same' padding and stride 2, the height and width are halved (rounded up), so 64/2 = 32. The number of filters defines the last dimension.

🧠 Conceptual

intermediate

Purpose of feature map visualization in CNNs

What is the main purpose of visualizing feature maps in convolutional neural networks (CNNs)?

A To increase the number of parameters in the model for better accuracy.

B To reduce the size of the dataset before training the model.

C To understand which parts of the input image activate certain filters and how the network processes features.

D To convert the CNN into a fully connected network.

💡 Hint

Think about what feature maps represent in CNN layers.

Feature maps show how filters respond to different parts of the input, helping us understand what the network learns.

❓ Metrics

advanced

Interpreting activation values in feature maps

In feature map visualization, what does a higher activation value in a specific spatial location generally indicate?

A The model is overfitting to the training data.

B The filter strongly detects a feature at that location in the input.

C The input image has low contrast in that region.

D The filter is not learning any useful features.

💡 Hint

Activation values represent how much a filter responds to input features.

Higher activation means the filter found a pattern it was designed to detect at that location.

🔧 Debug

advanced

Identifying error in feature map extraction code

What error will occur when running this TensorFlow code to extract feature maps from a model?

TensorFlow

import tensorflow as tf
model = tf.keras.applications.VGG16(weights=None, include_top=False)
input_image = tf.random.uniform([1, 224, 224, 3])
layer_outputs = [layer.output for layer in model.layers if 'conv' in layer.name]
feature_map_model = tf.keras.Model(inputs=model.input, outputs=layer_outputs)
feature_maps = feature_map_model(input_image)
print(len(feature_maps))

A TypeError because layer.output is not a tensor.

B RuntimeError because the model was created without weights.

C ValueError because model.layers contains layers without 'name' attribute.

D No error; prints the number of convolutional layers.

💡 Hint

Check if all layers have a 'name' attribute and output tensor.

All layers in Keras models have a 'name' and 'output' attribute. Filtering by 'conv' in name works fine. Model created without weights is valid.

❓ Model Choice

expert

Best model type for detailed feature map visualization

Which model architecture is best suited for detailed feature map visualization to understand hierarchical feature extraction?

A A deep convolutional neural network with multiple convolutional and pooling layers.

B A recurrent neural network designed for sequence data.

C A simple logistic regression model with no hidden layers.

D A decision tree classifier with no convolutional layers.

💡 Hint

Consider which model type uses convolutional layers producing feature maps.

Deep CNNs have multiple convolutional layers producing feature maps at different levels, ideal for visualization.