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.

Practice

1. Why does transfer learning save time when training a model in TensorFlow?

easy

A. Because it requires more data to train

B. Because it uses more layers than a normal model

C. Because it trains all layers from the beginning

D. Because it reuses a pre-trained model's knowledge instead of training from scratch

Solution

1. Step 1: Understand transfer learning basics

   Transfer learning uses a model already trained on a large dataset to start learning a new task.

2. Step 2: Identify how time is saved

   Since the model already knows useful features, it needs less training time than starting fresh.

3. Final Answer:

   Because it reuses a pre-trained model's knowledge instead of training from scratch -> Option D

4. Quick Check:

   Transfer learning saves time by reusing knowledge [OK]

Hint: Transfer learning reuses knowledge, so less training time needed [OK]

Common Mistakes:

• Thinking transfer learning trains all layers from scratch
• Assuming transfer learning needs more data
• Confusing transfer learning with training a bigger model

2. Which TensorFlow code snippet correctly freezes layers in a pre-trained model for transfer learning?

easy

A. for layer in base_model.layers:
layer.trainable = True

B. base_model.trainable = True

C. for layer in base_model.layers:
layer.trainable = False

D. base_model.freeze_layers()

Solution

1. Step 1: Understand freezing layers in TensorFlow

   To freeze layers, set each layer's trainable property to False.

2. Step 2: Check code correctness

   for layer in base_model.layers: layer.trainable = False loops through layers and sets trainable to False, which is correct syntax.

3. Final Answer:

   for layer in base_model.layers: layer.trainable = False -> Option C

4. Quick Check:

   Freeze layers by setting trainable = False [OK]

Hint: Freeze layers by setting layer.trainable = False in a loop [OK]

Common Mistakes:

• Using base_model.freeze_layers() which is not a TensorFlow method
• Setting base_model.trainable = True to freeze layers
• Setting trainable = True instead of False to freeze

3. Given this TensorFlow code using transfer learning, what will be the output shape of the model's predictions?

base_model = tf.keras.applications.MobileNetV2(input_shape=(128,128,3), include_top=False, pooling='avg')
base_model.trainable = False
model = tf.keras.Sequential([
    base_model,
    tf.keras.layers.Dense(10, activation='softmax')
])
output = model(tf.random.uniform([1,128,128,3]))
print(output.shape)

medium

A. (1, 10)

B. (128, 10)

C. (1, 128, 128, 10)

D. (10,)

Solution

1. Step 1: Analyze model architecture

   The base MobileNetV2 outputs a pooled vector per input image, shape (batch_size, features). Then Dense(10) outputs 10 class scores.

2. Step 2: Determine output shape

   Input batch size is 1, so output shape is (1, 10) representing 10 class probabilities for one image.

3. Final Answer:

   (1, 10) -> Option A

4. Quick Check:

   Output shape = (batch_size, number_of_classes) = (1, 10) [OK]

Hint: Output shape matches batch size and final Dense units [OK]

Common Mistakes:

• Confusing spatial input shape with output shape
• Ignoring pooling layer effect on output shape
• Assuming output shape includes input image dimensions

4. You tried transfer learning but your model overfits quickly. Which fix below correctly addresses this issue in TensorFlow?

medium

A. Freeze more layers and add dropout layers to reduce overfitting

B. Unfreeze all layers and train with a very high learning rate

C. Remove the pre-trained base model and train from scratch

D. Use fewer training examples to speed up training

Solution

1. Step 1: Identify overfitting causes

   Overfitting happens when model learns noise; freezing layers and dropout help reduce it.

2. Step 2: Evaluate options

   Freeze more layers and add dropout layers to reduce overfitting freezes more layers and adds dropout, both good to reduce overfitting.

3. Final Answer:

   Freeze more layers and add dropout layers to reduce overfitting -> Option A

4. Quick Check:

   Freeze layers + dropout reduces overfitting [OK]

Hint: Freeze layers and add dropout to fight overfitting [OK]

Common Mistakes:

• Unfreezing all layers with high learning rate causes more overfitting
• Removing pre-trained model loses transfer learning benefits
• Using fewer examples worsens overfitting

5. You have a small dataset of 500 images for a new classification task. How does transfer learning help you save time and data compared to training a model from scratch in TensorFlow?

hard

A. By training a large model from scratch with all layers trainable

B. By using a pre-trained model and freezing most layers, you need fewer images and less training time

C. By ignoring pre-trained weights and only using the architecture

D. By increasing the dataset size artificially without changing the model

Solution

1. Step 1: Understand small dataset challenges

   Small datasets cause overfitting and long training if model is trained from scratch.

2. Step 2: Explain transfer learning benefits

   Using a pre-trained model with frozen layers reuses learned features, needing fewer images and less time.

3. Final Answer:

   By using a pre-trained model and freezing most layers, you need fewer images and less training time -> Option B

4. Quick Check:

   Transfer learning saves time and data by reusing knowledge [OK]

Hint: Freeze layers in pre-trained model to save data and time [OK]

Common Mistakes:

• Training large model from scratch with small data
• Ignoring pre-trained weights loses transfer learning advantage
• Assuming data size increase alone solves training time