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.