Why transfer learning saves time and data in TensorFlow - Test Your Understanding

Practice - 5 Tasks

1fill in blank

easy

Complete the code to load a pre-trained model in TensorFlow.

TensorFlow

base_model = tf.keras.applications.MobileNetV2(weights=[1], include_top=False)

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

ANone

B'random'

C'imagenet'

D'cifar10'

Attempts:

3 left

💡 Hint

Common Mistakes

Using None means no pre-trained weights, so transfer learning benefits are lost.

Using dataset names like 'cifar10' is not valid for this parameter.

Using 'imagenet' loads weights trained on a large dataset, which helps transfer learning.

2fill in blank

medium

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

TensorFlow

base_model.trainable = [1]

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

AFalse

BTrue

CNone

D0

Attempts:

3 left

💡 Hint

Common Mistakes

Setting trainable to True will retrain all layers, losing transfer learning speed benefits.

Setting trainable to False freezes the layers, saving training time and data needs.

3fill in blank

hard

Fix the error in the code to add a new classification head after the base model.

TensorFlow

model = tf.keras.Sequential([
    base_model,
    tf.keras.layers.GlobalAveragePooling2D(),
    tf.keras.layers.Dense([1], activation='softmax')
])

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

A1

B10

C'10'

DNone

Attempts:

3 left

💡 Hint

Common Mistakes

Using a string like '10' causes an error.

Using None or 1 will not match the dataset classes.

The Dense layer needs the number of classes as an integer, here 10 for classification.

4fill in blank

hard

Fill both blanks to compile the model with an optimizer and loss suitable for transfer learning.

TensorFlow

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

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

A'adam'

B'sgd'

C'categorical_crossentropy'

D'mse'

Attempts:

3 left

💡 Hint

Common Mistakes

Using 'mse' loss is for regression, not classification.

Using 'sgd' optimizer works but is slower to converge than 'adam'.

Adam optimizer and categorical crossentropy loss are common choices for classification transfer learning.

5fill in blank

hard

Fill all three blanks to create a data pipeline that resizes images, batches them, and prefetches for performance.

TensorFlow

train_ds = train_ds.map(lambda x, y: (tf.image.resize(x, [1]), y))
train_ds = train_ds.batch([2])
train_ds = train_ds.prefetch(buffer_size=[3])

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

A(224, 224)

B32

Ctf.data.AUTOTUNE

D(128, 128)

Attempts:

3 left

💡 Hint

Common Mistakes

Using wrong image size causes shape errors.

Batch size too large or too small affects training speed.

Not using prefetch or wrong buffer size slows data loading.

Images are resized to 224x224, batch size is 32, and prefetch uses AUTOTUNE for best speed.