Learning rate scheduling in TensorFlow - Interactive Code Practice

Practice - 5 Tasks

1fill in blank

easy

Complete the code to create an exponential decay learning rate schedule.

TensorFlow

lr_schedule = tf.keras.optimizers.schedules.ExponentialDecay(initial_learning_rate=0.1, decay_steps=100000, decay_rate=[1], staircase=True)

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

A2.0

B0.5

C1.5

D0.96

Attempts:

3 left

💡 Hint

Common Mistakes

Using a decay rate greater than 1 which increases the learning rate instead of decreasing it.

Using 0 which would immediately reduce the learning rate to zero.

The decay_rate parameter controls how much the learning rate decreases at each decay step. A value less than 1 (like 0.96) means the learning rate will decay exponentially.

2fill in blank

medium

Complete the code to apply the learning rate schedule to the Adam optimizer.

TensorFlow

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

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

Alr_schedule

B0.001

C0.01

D0.1

Attempts:

3 left

💡 Hint

Common Mistakes

Passing a fixed float value instead of the schedule object.

Passing a string instead of the variable.

The learning_rate argument can accept a schedule object like lr_schedule to adjust the learning rate during training.

3fill in blank

hard

Fix the error in the code to correctly create a piecewise constant learning rate schedule.

TensorFlow

boundaries = [10000, 20000]
values = [0.1, 0.01, [1]]
lr_schedule = tf.keras.optimizers.schedules.PiecewiseConstantDecay(boundaries, values)

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

A0.05

B0.1

C0.001

D0

Attempts:

3 left

💡 Hint

Common Mistakes

Using the same number of values as boundaries which causes an error.

Using a value larger than previous learning rates.

The values list must have one more element than the boundaries list. The last value is the learning rate after the last boundary.

4fill in blank

hard

Fill both blanks to create a cosine decay learning rate schedule with restarts.

TensorFlow

lr_schedule = tf.keras.experimental.CosineDecayRestarts(initial_learning_rate=[1], first_decay_steps=[2])

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

A0.05

B1000

C500

D0.1

Attempts:

3 left

💡 Hint

Common Mistakes

Using too large or too small initial learning rate.

Setting first_decay_steps to zero or a negative number.

The initial_learning_rate is typically a small value like 0.1, and first_decay_steps controls how many steps before the first restart, often set to 1000.

5fill in blank

hard

Fill all three blanks to create a learning rate schedule that warms up linearly then decays exponentially.

TensorFlow

def lr_warmup_decay(step):
    warmup_steps = [1]
    if step < warmup_steps:
        return [2] * step / warmup_steps
    else:
        return [3] * tf.math.exp(-0.1 * (step - warmup_steps))

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

A1000

B0.01

C0.001

D0.1

Attempts:

3 left

💡 Hint

Common Mistakes

Confusing warmup_steps with learning rate values.

Using decay base larger than warmup max learning rate.

The warmup_steps is set to 1000 steps. The learning rate warms up linearly from 0 to 0.1, then decays exponentially starting from 0.001.

Practice

1. What is the main purpose of learning rate scheduling in TensorFlow training?

easy

A. To adjust the learning speed during training for better results

B. To increase the batch size automatically

C. To change the model architecture dynamically

D. To stop training early when accuracy is high

Solution

1. Step 1: Understand learning rate scheduling concept

   Learning rate scheduling changes how fast the model learns by adjusting the learning rate during training.

2. Step 2: Identify the main goal

   The goal is to help the model learn better and reach higher accuracy by controlling the learning speed.

3. Final Answer:

   To adjust the learning speed during training for better results -> Option A

4. Quick Check:

   Learning rate scheduling = adjust learning speed [OK]

Hint: Learning rate scheduling controls training speed [OK]

Common Mistakes:

• Confusing learning rate scheduling with batch size changes
• Thinking it changes model structure
• Assuming it stops training early

2. Which of the following is the correct way to create an exponential decay learning rate schedule in TensorFlow?

easy

A. tf.keras.optimizers.schedules.ExponentialDecay(initial_learning_rate=0.1, decay_steps=1000, decay_rate=0.96)

B. tf.keras.optimizers.ExponentialDecay(learning_rate=0.1, steps=1000, rate=0.96)

C. tf.keras.schedules.ExponentialDecay(learning_rate=0.1, decay_steps=1000, decay_rate=0.96)

D. tf.optimizers.schedules.ExponentialDecay(initial_lr=0.1, decay_steps=1000, decay_rate=0.96)

Solution

1. Step 1: Recall TensorFlow API for exponential decay

   The correct class is tf.keras.optimizers.schedules.ExponentialDecay with parameters initial_learning_rate, decay_steps, and decay_rate.

2. Step 2: Match parameters and class name

   tf.keras.optimizers.schedules.ExponentialDecay(initial_learning_rate=0.1, decay_steps=1000, decay_rate=0.96) matches the correct class and parameter names exactly.

3. Final Answer:

   tf.keras.optimizers.schedules.ExponentialDecay(initial_learning_rate=0.1, decay_steps=1000, decay_rate=0.96) -> Option A

4. Quick Check:

   Correct class and parameters = tf.keras.optimizers.schedules.ExponentialDecay(initial_learning_rate=0.1, decay_steps=1000, decay_rate=0.96) [OK]

Hint: Use tf.keras.optimizers.schedules for learning rate schedules [OK]

Common Mistakes:

• Using wrong module like tf.keras.optimizers directly
• Incorrect parameter names like learning_rate instead of initial_learning_rate
• Misspelling class or method names

3. What will be the learning rate after 2000 steps if you use this schedule?

schedule = tf.keras.optimizers.schedules.ExponentialDecay(
    initial_learning_rate=0.1,
    decay_steps=1000,
    decay_rate=0.5)
learning_rate = schedule(2000).numpy()

medium

A. 0.05

B. 0.01

C. 0.1

D. 0.025

Solution

1. Step 1: Understand exponential decay formula

   Learning rate = initial_learning_rate * decay_rate^(step / decay_steps). Here, step=2000, decay_steps=1000, decay_rate=0.5.

2. Step 2: Calculate learning rate at step 2000

   Calculate exponent: 2000 / 1000 = 2.
   Learning rate = 0.1 * (0.5)^2 = 0.1 * 0.25 = 0.025.

3. Final Answer:

   0.025 -> Option D

4. Quick Check:

   0.1 * 0.5^2 = 0.025 [OK]

Hint: Apply formula: lr = initial_lr * decay_rate^(step/decay_steps) [OK]

Common Mistakes:

• Forgetting to divide step by decay_steps
• Using decay_rate power step instead of step/decay_steps
• Mixing up decay_rate and initial_learning_rate

4. Identify the error in this TensorFlow learning rate schedule code:

schedule = tf.keras.optimizers.schedules.ExponentialDecay(
    initial_learning_rate=0.01,
    decay_steps=500,
    decay_rate=0.9)
optimizer = tf.keras.optimizers.Adam(learning_rate=schedule())

medium

A. Adam optimizer does not accept learning rate schedules

B. schedule() is called without step argument, causing an error

C. Decay rate 0.9 is too high and causes slow decay

D. initial_learning_rate should be set in optimizer, not schedule

Solution

1. Step 1: Check how schedule is used

   ExponentialDecay expects a step argument to compute learning rate. Calling schedule() without arguments causes an error.

2. Step 2: Verify optimizer learning rate parameter

   Optimizer accepts schedule object directly, not schedule() call. Passing schedule() calls the function immediately without step.

3. Final Answer:

   schedule() is called without step argument, causing an error -> Option B

4. Quick Check:

   Call schedule without step causes error [OK]

Hint: Pass schedule object, don't call it with () in optimizer [OK]

Common Mistakes:

• Calling schedule() instead of passing schedule object
• Thinking decay_rate value causes error
• Believing Adam can't use schedules

5. You want to train a model where the learning rate starts at 0.1, halves every 1000 steps, but never goes below 0.01. Which TensorFlow schedule setup achieves this?

hard

A. Use CosineDecay with initial_learning_rate=0.1 and alpha=0.01 to set minimum learning rate

B. Use ExponentialDecay with initial_learning_rate=0.1, decay_steps=1000, decay_rate=0.5 and then apply tf.keras.optimizers.schedules.PiecewiseConstantDecay with boundaries=[1000] and values=[0.1, 0.01]

C. Use ExponentialDecay with initial_learning_rate=0.1, decay_steps=1000, decay_rate=0.5 and then use tf.keras.optimizers.schedules.LearningRateSchedule subclass to clip minimum at 0.01

D. Use ExponentialDecay with initial_learning_rate=0.1, decay_steps=1000, decay_rate=0.5 and wrap it with tf.keras.optimizers.schedules.LearningRateSchedule to clip minimum at 0.01

Solution

1. Step 1: Understand the requirement

   Learning rate halves every 1000 steps: ExponentialDecay(initial_learning_rate=0.1, decay_steps=1000, decay_rate=0.5), but never below 0.01 (needs clipping).

2. Step 2: Evaluate schedules

   ExponentialDecay provides exact halving at multiples of decay_steps but lacks built-in minimum. Custom clipping needed.

3. Step 3: Identify correct approach

   Use ExponentialDecay with initial_learning_rate=0.1, decay_steps=1000, decay_rate=0.5 and then use tf.keras.optimizers.schedules.LearningRateSchedule subclass to clip minimum at 0.01 subclasses LearningRateSchedule to wrap ExponentialDecay and clip with tf.maximum(..., 0.01).

4. Final Answer:

   Use ExponentialDecay with initial_learning_rate=0.1, decay_steps=1000, decay_rate=0.5 and then use tf.keras.optimizers.schedules.LearningRateSchedule subclass to clip minimum at 0.01 -> Option C

5. Quick Check:

   ExponentialDecay + subclass clip = halving with floor [OK]

Hint: Subclass LearningRateSchedule to clip ExponentialDecay minimum [OK]

Common Mistakes:

• Using CosineDecay which does smooth decay, not discrete halving every 1000 steps
• Using PiecewiseConstantDecay incorrectly for continuous exponential decay
• Attempting to wrap without proper subclassing