Learning rate for fine-tuning in TensorFlow - Interactive Code Practice

Practice - 5 Tasks

1fill in blank

easy

Complete the code to set the learning rate for fine-tuning a TensorFlow model.

TensorFlow

optimizer = tf.keras.optimizers.Adam(learning_rate=[1])

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

A0.1

B0.001

C1

D10

Attempts:

3 left

💡 Hint

Common Mistakes

Using a large learning rate like 0.1 or 1 causes unstable training.

The learning rate for fine-tuning is usually small, like 0.001, to avoid large updates that could harm the pretrained weights.

2fill in blank

medium

Complete the code to compile the model with the Adam optimizer using the correct learning rate for fine-tuning.

TensorFlow

model.compile(optimizer=tf.keras.optimizers.Adam(learning_rate=[1]), loss='categorical_crossentropy', metrics=['accuracy'])

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

A0.1

B1

C0.01

D0.0001

Attempts:

3 left

💡 Hint

Common Mistakes

Choosing a learning rate too large, which can cause the model to forget learned features.

For fine-tuning, a very small learning rate like 0.0001 helps to gently adjust the pretrained model.

3fill in blank

hard

Fix the error in the code to correctly set the learning rate for fine-tuning.

TensorFlow

optimizer = tf.keras.optimizers.Adam(learning_rate=[1])

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

A1

B'0.001'

C0.001

D0.01

Attempts:

3 left

💡 Hint

Common Mistakes

Putting the learning rate value inside quotes, making it a string.

The learning rate must be a float number, not a string. So 0.001 is correct, not '0.001'.

4fill in blank

hard

Fill both blanks to create a learning rate schedule for fine-tuning that starts at 0.001 and decays by 0.1 every 10 epochs.

TensorFlow

lr_schedule = tf.keras.optimizers.schedules.ExponentialDecay(initial_learning_rate=[1], decay_steps=[2], decay_rate=0.1)

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

A0.001

B1000

C10

D0.01

Attempts:

3 left

💡 Hint

Common Mistakes

Using decay_steps as 10 instead of a larger number representing steps.

The initial learning rate is 0.001. Decay steps are set to 1000 (assuming 100 steps per epoch * 10 epochs) to decay every 10 epochs.

5fill in blank

hard

Fill all three blanks to define an Adam optimizer with a learning rate schedule starting at 0.0005, decaying every 500 steps by 0.5.

TensorFlow

lr_schedule = tf.keras.optimizers.schedules.ExponentialDecay(initial_learning_rate=[1], decay_steps=[2], decay_rate=[3])
optimizer = tf.keras.optimizers.Adam(learning_rate=lr_schedule)

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

A0.0005

B500

C0.5

D0.05

Attempts:

3 left

💡 Hint

Common Mistakes

Using decay rate greater than 1 which would increase learning rate.

The initial learning rate is 0.0005, decay steps 500, and decay rate 0.5 to reduce the learning rate by half every 500 steps.

Practice

1. Why is it recommended to use a smaller learning rate when fine-tuning a pre-trained TensorFlow model?

easy

A. To increase the batch size automatically

B. To speed up training drastically

C. To make gentle updates and avoid destroying learned features

D. To skip the need for validation data

Solution

1. Step 1: Understand fine-tuning purpose

   Fine-tuning adjusts a pre-trained model slightly to new data without losing learned knowledge.

2. Step 2: Reason about learning rate effect

   A smaller learning rate makes small changes, preserving useful features learned before.

3. Final Answer:

   To make gentle updates and avoid destroying learned features -> Option C

4. Quick Check:

   Small learning rate = gentle fine-tuning [OK]

Hint: Small learning rate prevents big changes during fine-tuning [OK]

Common Mistakes:

• Using a large learning rate that overwrites learned features
• Ignoring the need to freeze layers before fine-tuning
• Assuming learning rate affects batch size

2. Which of the following TensorFlow code snippets correctly sets a smaller learning rate for fine-tuning?

easy

A. optimizer = tf.keras.optimizers.Adam(learning_rate=0.0001)

B. optimizer = tf.keras.optimizers.Adam(learning_rate=0.001)

C. optimizer = tf.keras.optimizers.Adam(learning_rate=0.01)

D. optimizer = tf.keras.optimizers.Adam(learning_rate=0.1)

Solution

1. Step 1: Identify typical fine-tuning learning rates

   Fine-tuning usually uses smaller rates like 0.0001 to avoid big weight changes.

2. Step 2: Compare given learning rates

   0.0001 is smaller than 0.001, 0.01, and 0.1, making it suitable for fine-tuning.

3. Final Answer:

   optimizer = tf.keras.optimizers.Adam(learning_rate=0.0001) -> Option A

4. Quick Check:

   Smaller learning rate = 0.0001 [OK]

Hint: Pick the smallest learning rate value for fine-tuning [OK]

Common Mistakes:

• Choosing a learning rate too large for fine-tuning
• Confusing learning rate with batch size
• Not using tf.keras.optimizers.Adam correctly

3. Consider this TensorFlow code for fine-tuning a model:

base_model.trainable = True
optimizer = tf.keras.optimizers.Adam(learning_rate=0.01)
model.compile(optimizer=optimizer, loss='sparse_categorical_crossentropy', metrics=['accuracy'])
history = model.fit(train_data, epochs=3)

What is the likely outcome of using this learning rate during fine-tuning?

medium

A. The model will fine-tune smoothly with stable accuracy improvements

B. The model may have unstable training and lose pre-trained knowledge

C. The training will be very slow but stable

D. The model will skip training and keep old weights

Solution

1. Step 1: Analyze learning rate size

   Learning rate 0.01 is relatively large for fine-tuning, which risks big weight changes.

2. Step 2: Predict training behavior

   Large learning rate can cause unstable training and overwrite useful pre-trained features.

3. Final Answer:

   The model may have unstable training and lose pre-trained knowledge -> Option B

4. Quick Check:

   Large learning rate = unstable fine-tuning [OK]

Hint: Large learning rate can harm fine-tuning stability [OK]

Common Mistakes:

• Assuming higher learning rate always improves training speed
• Ignoring the effect of unfreezing the base model
• Thinking loss function controls learning rate impact

4. You wrote this code to fine-tune a TensorFlow model but notice training loss is not decreasing:

base_model.trainable = True
optimizer = tf.keras.optimizers.Adam(learning_rate=0.1)
model.compile(optimizer=optimizer, loss='categorical_crossentropy')
history = model.fit(train_data, epochs=5)

What is the main issue and how to fix it?

medium

A. Learning rate is too high; reduce it to 0.0001

B. Loss function is wrong; use 'sparse_categorical_crossentropy'

C. Base model should be frozen; set trainable = False

D. Epochs are too few; increase to 50

Solution

1. Step 1: Identify learning rate problem

   Learning rate 0.1 is very high for fine-tuning, causing unstable or no learning.

2. Step 2: Suggest fix

   Lowering learning rate to 0.0001 allows gentle updates and loss decrease.

3. Final Answer:

   Learning rate is too high; reduce it to 0.0001 -> Option A

4. Quick Check:

   High learning rate blocks loss decrease [OK]

Hint: Lower learning rate if loss doesn't improve during fine-tuning [OK]

Common Mistakes:

• Changing loss function unnecessarily
• Freezing base model after unfreezing
• Increasing epochs without fixing learning rate

5. You want to fine-tune a pre-trained TensorFlow model on a small dataset. Which learning rate strategy is best to balance learning speed and stability?

hard

A. Start with a small learning rate (e.g., 0.0001), then gradually increase it

B. Use a large learning rate (e.g., 0.1) from the start for faster training

C. Train all layers from scratch with a medium learning rate (e.g., 0.01)

D. Freeze the base model, train the new layers with a higher learning rate, then unfreeze and fine-tune with a smaller learning rate

Solution

1. Step 1: Understand fine-tuning best practice

   Freeze base model first to train new layers safely with higher learning rate.

2. Step 2: Fine-tune with smaller learning rate after unfreezing

   Unfreeze base model and use smaller learning rate to gently adjust pre-trained weights.

3. Final Answer:

   Freeze the base model, train the new layers with a higher learning rate, then unfreeze and fine-tune with a smaller learning rate -> Option D

4. Quick Check:

   Freeze first, then fine-tune with small learning rate [OK]

Hint: Freeze base, train new layers high LR, then fine-tune low LR [OK]

Common Mistakes:

• Using large learning rate from start causing unstable training
• Training all layers from scratch wasting pre-trained knowledge
• Not freezing base model before fine-tuning