K-fold cross-validation in TensorFlow - Practice Problems & Coding Challenges

Challenge - 5 Problems

❓ Predict Output

intermediate

Output of K-fold split indices

Given the following code snippet using sklearn's KFold, what will be the output of the printed train and test indices for fold 1?

TensorFlow

from sklearn.model_selection import KFold
import numpy as np

X = np.array([10, 20, 30, 40, 50])
kf = KFold(n_splits=5, shuffle=False)

for fold, (train_index, test_index) in enumerate(kf.split(X), 1):
    if fold == 1:
        print('Train indices:', train_index)
        print('Test indices:', test_index)

A

Train indices: [1 2 3 4]
Test indices: [0]

B

Train indices: [0 1 2 3]
Test indices: [4]

C

Train indices: [0 2 3 4]
Test indices: [1]

D

Train indices: [0 1 3 4]
Test indices: [2]

💡 Hint

Remember that KFold splits data into equal parts without shuffling by default.

With 5 splits and no shuffle, fold 1 test set is the first element (index 0), so train indices are the rest.

❓ Model Choice

intermediate

Choosing model evaluation strategy

You have a small dataset and want to estimate your TensorFlow model's performance reliably. Which cross-validation strategy is best to reduce variance in performance estimates?

A Use 10-fold cross-validation with shuffling

B Use a single train-test split with 80% training data

C Use 5-fold cross-validation without shuffling

D Use leave-one-out cross-validation without shuffling

💡 Hint

More folds with shuffling usually give better performance estimates on small datasets.

10-fold CV with shuffling reduces bias and variance better than fewer folds or no shuffling.

❓ Hyperparameter

advanced

Effect of number of folds on training time

If you increase the number of folds in K-fold cross-validation from 5 to 10 for training a TensorFlow model, what is the expected effect on total training time?

A Training time will be unpredictable and may increase or decrease randomly

B Training time will roughly double because the model trains on more folds

C Training time will stay the same because total data trained is unchanged

D Training time will decrease because each fold trains on less data

💡 Hint

Each fold requires training a separate model on a subset of data.

Doubling folds means training twice as many models, roughly doubling total training time.

❓ Metrics

advanced

Calculating average accuracy from K-fold results

You performed 4-fold cross-validation on a classification model and got accuracies: [0.82, 0.85, 0.80, 0.83]. What is the correct average accuracy to report?

A 0.825

B 0.8250

C 82.5%

D All of the above

💡 Hint

Average accuracy is the mean of fold accuracies; formatting can vary.

All options represent the same average accuracy in different formats.

🔧 Debug

expert

Identifying error in K-fold TensorFlow training loop

Consider this TensorFlow K-fold training loop code snippet. What error will it raise? ```python from sklearn.model_selection import KFold import tensorflow as tf import numpy as np X = np.random.rand(100, 10) y = np.random.randint(0, 2, 100) kf = KFold(n_splits=5, shuffle=True) for train_idx, test_idx in kf.split(X): model = tf.keras.Sequential([ tf.keras.layers.Dense(1, activation='sigmoid') ]) model.compile(optimizer='adam', loss='binary_crossentropy', metrics=['accuracy']) model.fit(X[train_idx], y[train_idx], epochs=3) loss, acc = model.evaluate(X[test_idx], y[test_idx]) print(f"Test accuracy: {acc}") print(model.predict(X)) ```

A No error; code runs and prints predictions

B ValueError due to shape mismatch in model.predict input

C NameError because model is undefined outside the loop

D RuntimeError because model.fit is called multiple times on same model

💡 Hint

Check where the variable 'model' is defined and used.

The variable 'model' is defined inside the loop and not accessible after the loop ends, causing NameError.