Custom callbacks in TensorFlow - Cheat Sheet & Quick Revision

Recall & Review

beginner

What is a custom callback in TensorFlow?

A custom callback is a user-defined function or class that allows you to insert your own code at specific points during model training, such as at the start or end of an epoch or batch.

beginner

Which method in a custom callback runs at the end of each training epoch?

The method on_epoch_end(self, epoch, logs=None) runs at the end of each training epoch and can be used to perform actions like logging or adjusting learning rates.

intermediate

How do you create a custom callback in TensorFlow?

You create a custom callback by subclassing tf.keras.callbacks.Callback and overriding the methods you want, such as on_train_begin, on_epoch_end, or on_batch_end.

intermediate

Why use custom callbacks instead of built-in callbacks?

Custom callbacks let you add personalized behavior during training that built-in callbacks don’t support, like saving extra data, custom logging, or stopping training based on your own rules.

beginner

What is the purpose of the logs parameter in callback methods?

The logs parameter is a dictionary that contains training metrics like loss and accuracy for the current batch or epoch, which you can use inside your callback to monitor or react to training progress.

Which base class should you extend to create a custom callback in TensorFlow?

A tf.keras.Model

B tf.keras.callbacks.Callback

C tf.data.Dataset

D tf.keras.layers.Layer

Custom callbacks are created by subclassing tf.keras.callbacks.Callback.

Which method is called at the start of training in a custom callback?

A on_train_begin

B on_epoch_end

C on_train_end

D on_batch_begin

The on_train_begin method runs at the start of training.

What does the logs dictionary typically contain during training?

A Training metrics like loss and accuracy

B Model architecture details

C Hardware specifications

D Dataset samples

The logs dictionary contains training metrics such as loss and accuracy.

Which method would you override to execute code after each batch during training?

A on_epoch_end

B on_train_begin

C on_batch_end

D on_train_end

The on_batch_end method runs after each batch.

Why might you want to stop training early using a custom callback?

A To increase the batch size

B To load a different dataset

C To change the model architecture

D To save time if the model is not improving

Stopping early can save time if the model stops improving.

Explain how to create and use a custom callback in TensorFlow to print the loss after each epoch.

Think about which method runs after each epoch and how to get loss info.

Describe three practical uses of custom callbacks during model training.

Consider what you might want to do automatically during training.

Practice

1. What is the main purpose of creating a custom callback in TensorFlow?

easy

A. To run your own code at specific points during model training

B. To change the model architecture automatically

C. To increase the dataset size during training

D. To convert the model to a different format

Solution

1. Step 1: Understand what callbacks do

   Callbacks let you add custom actions during training, like logging or stopping early.

2. Step 2: Identify the role of custom callbacks

   Custom callbacks let you run your own code at points like start/end of epochs or batches.

3. Final Answer:

   To run your own code at specific points during model training -> Option A

4. Quick Check:

   Custom callbacks = run code during training [OK]

Hint: Callbacks run code during training steps [OK]

Common Mistakes:

• Thinking callbacks change model structure
• Confusing callbacks with data augmentation
• Assuming callbacks convert model formats

2. Which method should you override in a custom callback to execute code at the end of each training epoch?

easy

A. on_train_begin

B. on_epoch_end

C. on_batch_begin

D. on_train_end

Solution

1. Step 1: Recall callback method names

   Common callback methods include on_train_begin, on_epoch_end, on_batch_begin, on_train_end.

2. Step 2: Match method to event

   on_epoch_end runs code after each epoch finishes, which is what the question asks.

3. Final Answer:

   on_epoch_end -> Option B

4. Quick Check:

   End of epoch method = on_epoch_end [OK]

Hint: End of epoch callback method is on_epoch_end [OK]

Common Mistakes:

• Using on_train_begin for epoch end
• Confusing batch and epoch methods
• Overriding on_train_end instead

3. What will be printed after training if this custom callback is used?

import tensorflow as tf
class MyCallback(tf.keras.callbacks.Callback):
    def on_epoch_end(self, epoch, logs=None):
        print(f"Epoch {epoch+1} ended with loss {logs['loss']:.2f}")

model = tf.keras.Sequential([tf.keras.layers.Dense(1)])
model.compile(optimizer='sgd', loss='mse')
model.fit([[1.0]], [[2.0]], epochs=2, callbacks=[MyCallback()])

medium

A. Error because logs is None

B. Epoch 0 ended with loss X\nEpoch 1 ended with loss Y

C. No output printed during training

D. Epoch 1 ended with loss X\nEpoch 2 ended with loss Y (X and Y are numbers)

Solution

1. Step 1: Understand on_epoch_end behavior

   The method prints epoch number +1 and loss from logs after each epoch.

2. Step 2: Check training epochs and output

   Training runs 2 epochs, so prints for epoch 1 and 2 with loss values (numbers).

3. Final Answer:

   Epoch 1 ended with loss X\nEpoch 2 ended with loss Y (X and Y are numbers) -> Option D

4. Quick Check:

   Prints after each epoch with loss [OK]

Hint: Epoch count starts at 0, print adds 1 [OK]

Common Mistakes:

• Assuming epoch numbering starts at 1 internally
• Expecting no print output
• Thinking logs is None causing error

4. Identify the error in this custom callback code that tries to stop training when loss is below 0.1:

class StopCallback(tf.keras.callbacks.Callback):
    def on_epoch_end(self, epoch, logs=None):
        if logs['loss'] < 0.1:
            self.model.stop_training = True

model.fit(x_train, y_train, epochs=10, callbacks=[StopCallback()])

medium

A. on_epoch_end method must return a value

B. stop_training should be called as a method

C. logs dictionary might be None causing KeyError

D. Callback class must inherit from tf.keras.Model

Solution

1. Step 1: Check logs usage

   logs can be None if no metrics are passed, so logs['loss'] may cause KeyError.

2. Step 2: Confirm correct way to stop training

   Setting self.model.stop_training = True is correct; no method call needed.

3. Final Answer:

   logs dictionary might be None causing KeyError -> Option C

4. Quick Check:

   Check logs is not None before accessing [OK]

Hint: Always check logs is not None before using keys [OK]

Common Mistakes:

• Calling stop_training as a method
• Expecting on_epoch_end to return a value
• Inheriting from wrong base class

5. You want to save the model weights only when validation accuracy improves during training. Which custom callback method and logic should you implement?

hard

A. Override on_epoch_end, check logs['val_accuracy'], save weights if improved

B. Override on_train_begin, save weights before training starts

C. Override on_batch_end, save weights after every batch

D. Override on_train_end, save weights after training finishes

Solution

1. Step 1: Identify when to check validation accuracy

   Validation accuracy is updated at epoch end, so on_epoch_end is the right method.

2. Step 2: Implement logic to save weights only if val_accuracy improves

   Inside on_epoch_end, compare current val_accuracy with previous best and save if better.

3. Final Answer:

   Override on_epoch_end, check logs['val_accuracy'], save weights if improved -> Option A

4. Quick Check:

   Save on epoch end if val_accuracy improves [OK]

Hint: Use on_epoch_end to monitor validation metrics [OK]

Common Mistakes:

• Saving weights too often (every batch)
• Saving only before or after all training
• Not checking if accuracy improved before saving