Compiling models (optimizer, loss, metrics) in TensorFlow - Practice Problems & Coding Challenges

Challenge - 5 Problems

❓ Predict Output

intermediate

Output of model training metrics

Consider the following TensorFlow model compilation and training code snippet. What will be the printed output for the training accuracy after the first epoch?

TensorFlow

import tensorflow as tf
import numpy as np

model = tf.keras.Sequential([
    tf.keras.layers.Dense(1, input_shape=(2,), activation='sigmoid')
])

model.compile(optimizer='sgd', loss='binary_crossentropy', metrics=['accuracy'])

# Dummy data
x_train = np.array([[0,0],[0,1],[1,0],[1,1]])
y_train = np.array([0,1,1,0])

history = model.fit(x_train, y_train, epochs=1, verbose=0)
print(f"Training accuracy: {history.history['accuracy'][0]:.2f}")

A Training accuracy: 0.50

B Training accuracy: 1.00

C Training accuracy: 0.25

D Training accuracy: 0.00

💡 Hint

Think about the model's initial random weights and the simple dataset.

With random initial weights and only one epoch, the model is unlikely to perfectly classify all samples, so accuracy around 0.5 is expected.

❓ Model Choice

intermediate

Choosing the correct loss function for multi-class classification

You want to compile a TensorFlow model to classify images into 5 categories. The labels are one-hot encoded vectors. Which loss function should you choose?

A tf.keras.losses.SparseCategoricalCrossentropy()

B tf.keras.losses.CategoricalCrossentropy()

C tf.keras.losses.BinaryCrossentropy()

D tf.keras.losses.MeanSquaredError()

💡 Hint

One-hot encoded labels require a specific crossentropy loss.

CategoricalCrossentropy is used when labels are one-hot encoded. SparseCategoricalCrossentropy is for integer labels.

❓ Hyperparameter

advanced

Effect of optimizer choice on training speed

You compile two identical models with the same architecture and loss but different optimizers: Adam and SGD. Which statement about their training behavior is generally true?

A Adam adapts learning rates and often converges faster than SGD.

B SGD usually converges faster than Adam on most problems.

C Both optimizers always produce the same training speed and results.

D Adam requires manual learning rate decay to work properly.

💡 Hint

Think about how Adam adjusts learning rates automatically.

Adam optimizer adapts learning rates per parameter and often converges faster than vanilla SGD.

❓ Metrics

advanced

Interpreting multiple metrics in model.compile

If you compile a model with metrics=['accuracy', 'precision', 'recall'], what will be the output after training?

A The metrics will be ignored and only loss will be reported.

B Only 'accuracy' will be tracked because 'precision' and 'recall' are invalid metric names.

C The model will raise a ValueError due to invalid metric names.

D The training history will include keys 'accuracy', 'precision', and 'recall' with their values per epoch.

💡 Hint

TensorFlow supports standard metrics such as 'precision' and 'recall'.

TensorFlow recognizes 'precision' and 'recall' as valid metrics and tracks them along with accuracy.

🔧 Debug

expert

Identifying the cause of a metric reporting error

You compile a TensorFlow model with metrics=['accuracy'] but during training, you get this error: "ValueError: Shapes (None, 1) and (None, 10) are incompatible". What is the most likely cause?

A The loss function is missing from model.compile.

B The optimizer is incompatible with the accuracy metric.

C The model output shape does not match the shape of the labels provided.

D The batch size is too large for the model.

💡 Hint

Check the shapes of model outputs and labels carefully.

This error usually means the model predicts a shape different from the labels, causing metric calculation to fail.