Transfer learning for small datasets 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 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'

ATrue

BFalse

CNone

D0

Attempts:

3 left

💡 Hint

Common Mistakes

Setting include_top=True loads the full model including the classification head, which is not suitable for transfer learning on new tasks.

Setting include_top=False loads the model without the final classification layers, which is useful for transfer learning.

2fill in blank

medium

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

TensorFlow

base_model.[1] = False

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

Afrozen

Btrain

Crequires_grad

Dtrainable

Attempts:

3 left

💡 Hint

Common Mistakes

Using incorrect attribute names like 'frozen' or 'requires_grad' which do not exist in TensorFlow.

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

3fill in blank

hard

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

TensorFlow

x = base_model.output
x = tf.keras.layers.[1]()(x)

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

ADense

BFlatten

CGlobalAveragePooling2D

DDropout

Attempts:

3 left

💡 Hint

Common Mistakes

Using Dense or Flatten layers directly after the convolutional base without pooling can cause shape errors.

The GlobalAveragePooling2D layer reduces the spatial dimensions by averaging, which is common after convolutional base models.

4fill in blank

hard

Fill both blanks to create a new model with the base model and a final dense layer for 5 classes.

TensorFlow

outputs = tf.keras.layers.Dense([1], activation=[2])(x)
model = tf.keras.Model(inputs=base_model.input, outputs=outputs)

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

A5

B'softmax'

C'relu'

D10

Attempts:

3 left

💡 Hint

Common Mistakes

Using 'relu' activation in the output layer or wrong number of units.

The final dense layer should have 5 units for 5 classes and use 'softmax' activation for multi-class classification.

5fill in blank

hard

Fill all three blanks to compile the model with Adam optimizer, categorical crossentropy loss, and accuracy metric.

TensorFlow

model.compile(optimizer=[1], loss=[2], metrics=[[3]])

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

A'adam'

B'categorical_crossentropy'

C'accuracy'

D'mse'

Attempts:

3 left

💡 Hint

Common Mistakes

Using mean squared error loss or wrong metrics for classification.

Adam optimizer is popular for training. Categorical crossentropy is used for multi-class classification. Accuracy measures how often predictions are correct.