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.

Practice

1. What is the main purpose of visualizing feature maps in a convolutional neural network (CNN)?

easy

A. To reduce the size of the input images

B. To understand what patterns or features the CNN layers detect in the input image

C. To increase the training speed of the CNN model

D. To change the activation function of the CNN layers

Solution

1. Step 1: Understand feature maps in CNNs

   Feature maps are outputs of convolutional layers showing detected features like edges or textures.

2. Step 2: Purpose of visualization

   Visualizing feature maps helps us see what the CNN focuses on in the image, improving model interpretability.

3. Final Answer:

   To understand what patterns or features the CNN layers detect in the input image -> Option B

4. Quick Check:

   Feature map visualization = Understand CNN features [OK]

Hint: Feature maps show what CNN 'sees' in images [OK]

Common Mistakes:

• Thinking visualization speeds up training
• Confusing feature maps with input resizing
• Believing visualization changes activation functions

2. Which TensorFlow code snippet correctly creates a model to output feature maps from the first convolutional layer named 'conv1'?

easy

A. feature_map_model = tf.keras.Model(inputs=model.get_layer('conv1').input, outputs=model.input)

B. feature_map_model = tf.keras.Sequential(model.get_layer('conv1'))

C. feature_map_model = tf.keras.Model(inputs=model.input, outputs=model.get_layer('conv1').output)

D. feature_map_model = tf.keras.Model(inputs=model.output, outputs=model.get_layer('conv1').input)

Solution

1. Step 1: Identify correct Model creation syntax

   To get intermediate outputs, create a new Model with original inputs and desired layer outputs.

2. Step 2: Check each option

   feature_map_model = tf.keras.Model(inputs=model.input, outputs=model.get_layer('conv1').output) correctly uses model.input and conv1 output. Others misuse inputs/outputs or use Sequential incorrectly.

3. Final Answer:

   feature_map_model = tf.keras.Model(inputs=model.input, outputs=model.get_layer('conv1').output) -> Option C

4. Quick Check:

   New model inputs = original inputs, outputs = layer output [OK]

Hint: Use original inputs and layer output to create feature map model [OK]

Common Mistakes:

• Using model.output as input
• Passing layer input as output
• Using Sequential instead of Model for intermediate outputs

3. Given the code below, what is the shape of feature_maps if the input image shape is (1, 64, 64, 3) and the 'conv1' layer outputs 32 filters of size 62x62?

feature_map_model = tf.keras.Model(inputs=model.input, outputs=model.get_layer('conv1').output)
feature_maps = feature_map_model.predict(input_image)

medium

A. (62, 62, 32)

B. (32, 62, 62)

C. (1, 64, 64, 3)

D. (1, 62, 62, 32)

Solution

1. Step 1: Understand input and output shapes

   Input batch size is 1, image size 64x64 with 3 channels. conv1 outputs 32 filters of size 62x62.

2. Step 2: Predict output shape

   Output shape includes batch size, height, width, and number of filters: (1, 62, 62, 32).

3. Final Answer:

   (1, 62, 62, 32) -> Option D

4. Quick Check:

   Output shape = (batch, height, width, filters) [OK]

Hint: Feature map shape includes batch and filter count [OK]

Common Mistakes:

• Ignoring batch dimension
• Confusing input shape with output shape
• Mixing filter count with spatial dimensions

4. You wrote this code to visualize feature maps but get an error:

feature_map_model = tf.keras.Model(inputs=model.input, outputs=model.get_layer('conv1').output)
feature_maps = feature_map_model.predict(input_image)
plt.imshow(feature_maps)

What is the likely cause of the error?

medium

A. Trying to plot a 4D tensor directly with plt.imshow

B. Using the wrong layer name in get_layer

C. Input image shape is incompatible with the model

D. Missing import for matplotlib.pyplot

Solution

1. Step 1: Analyze the error cause

   feature_maps is a 4D array (batch, height, width, filters), but plt.imshow expects 2D or 3D image data.

2. Step 2: Correct visualization approach

   You must select one feature map (e.g., feature_maps[0, :, :, 0]) before plotting with plt.imshow.

3. Final Answer:

   Trying to plot a 4D tensor directly with plt.imshow -> Option A

4. Quick Check:

   Plot single 2D feature map slice, not full 4D tensor [OK]

Hint: Plot one 2D feature map slice, not whole 4D tensor [OK]

Common Mistakes:

• Plotting entire feature_maps array directly
• Ignoring batch dimension when plotting
• Assuming get_layer error without checking data shape

5. You want to visualize feature maps from multiple convolutional layers ('conv1', 'conv2', 'conv3') in a TensorFlow model. Which approach correctly creates a model to output all these feature maps at once?

hard

A. feature_map_model = tf.keras.Model(inputs=model.input, outputs=[model.get_layer(name).output for name in ['conv1', 'conv2', 'conv3']])

B. feature_map_model = tf.keras.Sequential([model.get_layer('conv1'), model.get_layer('conv2'), model.get_layer('conv3')])

C. feature_map_model = tf.keras.Model(inputs=model.output, outputs=model.get_layer('conv3').output)

D. feature_map_model = tf.keras.Model(inputs=model.input, outputs=model.get_layer('conv3').input)

Solution

1. Step 1: Understand multi-output model creation

   To get outputs from multiple layers, pass a list of their outputs to the Model constructor.

2. Step 2: Evaluate options

   feature_map_model = tf.keras.Model(inputs=model.input, outputs=[model.get_layer(name).output for name in ['conv1', 'conv2', 'conv3']]) correctly creates a model with inputs as original inputs and outputs as a list of layer outputs. Others misuse Sequential or inputs/outputs.

3. Final Answer:

   feature_map_model = tf.keras.Model(inputs=model.input, outputs=[model.get_layer(name).output for name in ['conv1', 'conv2', 'conv3']]) -> Option A

4. Quick Check:

   Use list of outputs for multiple feature maps [OK]

Hint: Use list of layer outputs in Model to get multiple feature maps [OK]

Common Mistakes:

• Using Sequential instead of Model for intermediate outputs
• Passing model.output as inputs
• Using layer inputs as outputs