Feature extraction approach in TensorFlow - Interactive Code Practice

Practice - 5 Tasks

1fill in blank

easy

Complete the code to load a pre-trained MobileNetV2 model without the top classification layer.

TensorFlow

base_model = tf.keras.applications.MobileNetV2(input_shape=(224, 224, 3), include_top=[1], weights='imagenet')

Drag options to blanks, or click blank then click option'

ANone

BFalse

C'imagenet'

DTrue

Attempts:

3 left

💡 Hint

Common Mistakes

Setting include_top=True loads the full model including classification layers, not suitable for feature extraction.

Setting include_top=False loads the model without the final classification layers, which is essential for feature extraction.

2fill in blank

medium

Complete the code to freeze the base model layers so they are not trainable.

TensorFlow

base_model.trainable = [1]

Drag options to blanks, or click blank then click option'

AFalse

BTrue

CNone

D'frozen'

Attempts:

3 left

💡 Hint

Common Mistakes

Setting trainable=True will allow the base model to be trained, which is not desired in feature extraction.

Setting trainable = False freezes the layers, so their weights do not change during training.

3fill in blank

hard

Fix the error in the code to add a global average pooling layer after the base model.

TensorFlow

global_average_layer = tf.keras.layers.GlobalAveragePooling2D() 
features = global_average_layer([1].output)

Drag options to blanks, or click blank then click option'

Abase_model

Bmodel

Cinputs

Dfeatures

Attempts:

3 left

💡 Hint

Common Mistakes

Passing the wrong variable like 'model' or 'inputs' instead of base_model.output.

The global average pooling layer should be applied to the output of the base model, which is base_model.output.

4fill in blank

hard

Fill both blanks to create a new model that uses the base model input and the pooled features as output.

TensorFlow

model = tf.keras.Model(inputs=[1], outputs=[2])

Drag options to blanks, or click blank then click option'

Abase_model.input

Bfeatures

Cbase_model.output

Dinputs

Attempts:

3 left

💡 Hint

Common Mistakes

Using base_model.output as input or using base_model.output as output instead of pooled features.

The new model takes the base model's input and outputs the pooled features for further processing.

5fill in blank

hard

Fill all three blanks to add a dense classification layer, compile the model, and specify the optimizer.

TensorFlow

prediction_layer = tf.keras.layers.Dense([1], activation='softmax')
outputs = prediction_layer([2])
model = tf.keras.Model(inputs=[3], outputs=outputs)
model.compile(optimizer='adam', loss='sparse_categorical_crossentropy', metrics=['accuracy'])

Drag options to blanks, or click blank then click option'

A10

Bfeatures

Cbase_model.input

D1

Attempts:

3 left

💡 Hint

Common Mistakes

Using wrong number of units in dense layer or wrong input/output tensors.

The dense layer has 10 units for 10 classes, takes the pooled features as input, and the model uses the base model input.

Practice

1. What is the main purpose of using feature extraction with a pre-trained TensorFlow model?

easy

A. To use learned features from a large dataset to help a new task

B. To train a model from scratch with random weights

C. To increase the size of the dataset automatically

D. To reduce the number of layers in the model

Solution

1. Step 1: Understand feature extraction concept

   Feature extraction uses a pre-trained model to get useful features learned from a large dataset.

2. Step 2: Identify the benefit for new tasks

   This helps when you have little data or want faster training by reusing learned features.

3. Final Answer:

   To use learned features from a large dataset to help a new task -> Option A

4. Quick Check:

   Feature extraction = reuse learned features [OK]

Hint: Feature extraction reuses knowledge from big datasets [OK]

Common Mistakes:

• Thinking feature extraction trains from scratch
• Confusing feature extraction with data augmentation
• Believing it reduces model layers automatically

2. Which TensorFlow code snippet correctly freezes the base model layers for feature extraction?

easy

A. base_model.trainable = True

B. base_model.trainable = False

C. base_model.freeze()

D. base_model.layers.freeze = True

Solution

1. Step 1: Recall how to freeze layers in TensorFlow

   Setting trainable = False on the base model freezes its weights.

2. Step 2: Check each option's correctness

   base_model.trainable = False correctly sets base_model.trainable = False. Others are invalid syntax or do not freeze layers.

3. Final Answer:

   base_model.trainable = False -> Option B

4. Quick Check:

   Freeze layers = trainable False [OK]

Hint: Freeze layers by setting trainable to False [OK]

Common Mistakes:

• Using trainable = True to freeze layers
• Calling non-existent freeze() method
• Trying to set freeze attribute on layers directly

3. Given this code, what is the output shape of features?

base_model = tf.keras.applications.MobileNetV2(input_shape=(128,128,3), include_top=False)
base_model.trainable = False
inputs = tf.keras.Input(shape=(128,128,3))
features = base_model(inputs)
print(features.shape)

medium

A. (None, 4, 4, 1280)

B. (None, 7, 7, 512)

C. (None, 1, 1, 1000)

D. (None, 128, 128, 3)

Solution

1. Step 1: Understand MobileNetV2 output with include_top=False

   MobileNetV2 outputs feature maps of size (4,4,1280) for 128x128 input when top layers are excluded.

2. Step 2: Confirm batch dimension is None

   The batch size is None (unspecified), so output shape is (None, 4, 4, 1280).

3. Final Answer:

   (None, 4, 4, 1280) -> Option A

4. Quick Check:

   MobileNetV2 feature shape = (None,4,4,1280) [OK]

Hint: MobileNetV2 outputs 4x4x1280 features for 128x128 input [OK]

Common Mistakes:

• Confusing output with classification layer shape
• Assuming output shape equals input shape
• Ignoring batch dimension None

4. Identify the error in this feature extraction code snippet:

base_model = tf.keras.applications.ResNet50(weights='imagenet', include_top=False)
base_model.trainable = False
inputs = tf.keras.Input(shape=(224,224,3))
x = base_model(inputs)
x = tf.keras.layers.Dense(10)(x)
model = tf.keras.Model(inputs, x)

medium

A. Base model weights not loaded correctly

B. Input shape is incorrect for ResNet50

C. Dense layer applied to 4D tensor without flattening

D. trainable should be True to freeze layers

Solution

1. Step 1: Check tensor shapes before Dense layer

   Base model outputs 4D tensor (batch, height, width, channels). Dense expects 2D input.

2. Step 2: Identify missing flatten or global pooling

   Applying Dense directly to 4D tensor causes error; flatten or global pooling needed first.

3. Final Answer:

   Dense layer applied to 4D tensor without flattening -> Option C

4. Quick Check:

   Dense needs 2D input, flatten first [OK]

Hint: Flatten or pool before Dense layer [OK]

Common Mistakes:

• Applying Dense directly to 4D output
• Confusing input shape requirements
• Misunderstanding trainable flag usage

5. You want to use feature extraction with MobileNetV2 on 64x64 images but get an error when adding a Dense layer after the base model. What is the best way to fix this?

hard

A. Set base_model.trainable = True to allow training

B. Change input shape to 224x224 to match MobileNetV2 default

C. Remove the Dense layer and use base model output directly

D. Add a GlobalAveragePooling2D layer before the Dense layer

Solution

1. Step 1: Understand why Dense layer causes error

   MobileNetV2 outputs 4D feature maps; Dense layers need 2D input.

2. Step 2: Use GlobalAveragePooling2D to convert 4D to 2D

   Adding GlobalAveragePooling2D flattens spatial dimensions, making output suitable for Dense.

3. Step 3: Evaluate other options

   Changing input size is not required; training base model is optional; removing Dense loses classification ability.

4. Final Answer:

   Add a GlobalAveragePooling2D layer before the Dense layer -> Option D

5. Quick Check:

   Pool features before Dense layer [OK]

Hint: Use pooling to flatten features before Dense [OK]

Common Mistakes:

• Changing input size unnecessarily
• Trying to train frozen base model
• Skipping pooling and causing shape errors