Retraining strategies in ML Python - Interactive Code Practice

Practice - 5 Tasks

1fill in blank

easy

Complete the code to retrain a model using new data.

ML Python

model.fit(new_data, new_labels, epochs=[1])

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

A5

B-1

C0

D10

Attempts:

3 left

💡 Hint

Common Mistakes

Using 0 epochs means no training happens.

Negative epochs cause errors.

Setting epochs to 10 allows the model to train for 10 cycles on the new data, which is a common choice for retraining.

2fill in blank

medium

Complete the code to freeze all layers except the last one before retraining.

ML Python

for layer in model.layers[:-1]:
    layer.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 retrains all layers.

Using None or 0 is invalid for trainable property.

Setting trainable to False freezes the layers so they are not updated during retraining.

3fill in blank

hard

Fix the error in the code to compile the model with a suitable optimizer for retraining.

ML Python

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

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

A'sgd'

B'adagrad'

C'adam'

D'rmsprop'

Attempts:

3 left

💡 Hint

Common Mistakes

Using unsupported optimizer names causes errors.

Choosing SGD may require tuning learning rate.

Adam optimizer is widely used for retraining because it adapts learning rates and converges well.

4fill in blank

hard

Fill both blanks to create a dictionary comprehension that filters new data samples with label 1 for retraining.

ML Python

filtered_data = {i: x for i, x in enumerate(new_data) if new_labels[i] [1] [2]

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

A==

B!=

C1

D0

Attempts:

3 left

💡 Hint

Common Mistakes

Using '!=' filters out the desired class.

Using 0 instead of 1 filters the wrong class.

The comprehension keeps samples where the label equals 1, which is useful to retrain on a specific class.

5fill in blank

hard

Fill all three blanks to update the learning rate and retrain the model with early stopping.

ML Python

from tensorflow.keras.callbacks import EarlyStopping

optimizer = tf.keras.optimizers.Adam(learning_rate=[1])
model.compile(optimizer=optimizer, loss='categorical_crossentropy', metrics=['accuracy'])
early_stop = EarlyStopping(monitor='val_loss', patience=[2], restore_best_weights=[3])
model.fit(train_data, train_labels, epochs=20, validation_split=0.2, callbacks=[early_stop])

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

A0.001

B3

CTrue

D0.1

Attempts:

3 left

💡 Hint

Common Mistakes

Using too high learning rate causes training instability.

Setting patience too low stops training too early.

Not restoring best weights may keep worse model.

Learning rate 0.001 is common for Adam optimizer. Patience 3 waits 3 epochs without improvement before stopping. Restoring best weights ensures best model is kept.

Practice

1. What is the main purpose of retraining a machine learning model?

easy

A. To remove features from the model permanently

B. To make the model run faster on old data

C. To reduce the size of the training dataset

D. To update the model with new data and keep it accurate

Solution

1. Step 1: Understand retraining purpose

   Retraining updates the model using new data to maintain or improve accuracy.

2. Step 2: Compare options

   Options B, C, and D do not describe retraining goals; only A matches the purpose.

3. Final Answer:

   To update the model with new data and keep it accurate -> Option D

4. Quick Check:

   Retraining = update model with new data [OK]

Hint: Retraining means learning from new data to stay accurate [OK]

Common Mistakes:

• Thinking retraining speeds up old data processing
• Confusing retraining with data reduction
• Believing retraining removes features

2. Which of the following is the correct way to fine-tune a pretrained model in Python using TensorFlow?

easy

A. model.fit(new_data, epochs=5, initial_epoch=0)

B. model.train(new_data, epochs=5)

C. model.evaluate(new_data, epochs=5)

D. model.fit(new_data, epochs=5, initial_epoch=existing_epochs)

Solution

1. Step 1: Understand fine-tuning syntax

   Fine-tuning a pretrained model typically uses model.fit starting from epoch 0 after loading pretrained weights.

2. Step 2: Analyze options

   A uses non-existent method 'train'. C uses evaluate, which doesn't train and lacks epochs param. D risks initial_epoch >= epochs error. B correctly trains with model.fit from epoch 0.

3. Final Answer:

   model.fit(new_data, epochs=5, initial_epoch=0) -> Option A

4. Quick Check:

   Fine-tune = model.fit(new_data, epochs=N, initial_epoch=0) [OK]

Hint: Fine-tune pretrained with model.fit(new_data, epochs=N) [OK]

Common Mistakes:

• Using model.train instead of model.fit
• Setting initial_epoch=existing_epochs causing error
• Confusing evaluation with training

3. Consider this Python code snippet for incremental retraining:

old_accuracy = 0.85
model.fit(new_data, epochs=3)
new_accuracy = 0.88
improvement = new_accuracy - old_accuracy
print(improvement)

What will be the printed output?

medium

A. 0.85

B. 0.88

C. 0.03

D. 3

Solution

1. Step 1: Calculate improvement

   Improvement is new_accuracy minus old_accuracy: 0.88 - 0.85 = 0.03.

2. Step 2: Understand print output

   The print statement outputs the improvement variable, which is 0.03.

3. Final Answer:

   0.03 -> Option C

4. Quick Check:

   0.88 - 0.85 = 0.03 [OK]

Hint: Subtract old accuracy from new to find improvement [OK]

Common Mistakes:

• Printing new_accuracy instead of improvement
• Confusing epochs with accuracy values
• Printing old_accuracy by mistake

4. You have this code snippet for retraining a model incrementally:

model.fit(new_data, epochs=5)
model.fit(new_data, epochs=3, initial_epoch=5)

But the second fit call throws an error. What is the likely cause?

medium

A. initial_epoch should be less than epochs

B. initial_epoch cannot be greater than or equal to epochs

C. You must reset the model before second fit

D. epochs must be the same in both fit calls

Solution

1. Step 1: Understand initial_epoch and epochs relation

   initial_epoch must be less than epochs in the current fit call to define the training range properly.

2. Step 2: Analyze the error cause

   Here, initial_epoch=5 is greater than epochs=3, which is invalid and causes an error.

3. Final Answer:

   initial_epoch cannot be greater than or equal to epochs -> Option B

4. Quick Check:

   initial_epoch < epochs required [OK]

Hint: initial_epoch must be less than epochs in fit call [OK]

Common Mistakes:

• Thinking model reset is needed
• Assuming epochs must match both calls
• Setting initial_epoch greater or equal to epochs

5. You have a model trained on data from 2020. New data from 2023 shows some feature distributions changed. Which retraining strategy best balances training time and model accuracy?

hard

A. Fine-tuning the existing model on new data with a low learning rate

B. Full retraining from scratch with combined old and new data

C. Incremental retraining only on new data without old data

D. No retraining; use the old model as is

Solution

1. Step 1: Consider data changes and retraining options

   Feature distribution changed, so model needs updating but full retraining is costly.

2. Step 2: Evaluate strategies

   Full retraining (A) is accurate but slow. Incremental retraining (C) risks forgetting old data. No retraining (D) ignores changes. Fine-tuning (B) updates model efficiently with new data.

3. Final Answer:

   Fine-tuning the existing model on new data with a low learning rate -> Option A

4. Quick Check:

   Fine-tune balances accuracy and training time [OK]

Hint: Fine-tune to update model efficiently with new data [OK]

Common Mistakes:

• Choosing full retraining despite high cost
• Ignoring old data in incremental retraining
• Skipping retraining when data changes