Categorical cross-entropy loss in TensorFlow - Practice Problems & Coding Challenges

Challenge - 5 Problems

❓ Predict Output

intermediate

Output of categorical cross-entropy loss calculation

What is the output value of the categorical cross-entropy loss for the given true labels and predicted probabilities?

TensorFlow

import tensorflow as tf

true_labels = tf.constant([[0, 1, 0], [1, 0, 0]], dtype=tf.float32)
predicted_probs = tf.constant([[0.1, 0.8, 0.1], [0.7, 0.2, 0.1]], dtype=tf.float32)

loss_fn = tf.keras.losses.CategoricalCrossentropy()
loss_value = loss_fn(true_labels, predicted_probs).numpy()
print(loss_value)

A 0.5108256

B 0.22314353

C 0.28990925

D 0.6931472

💡 Hint

Recall that categorical cross-entropy measures the difference between true labels and predicted probabilities using the negative log likelihood.

The categorical cross-entropy loss is calculated as the average negative log probability of the true class. For the given inputs, the loss is approximately 0.2899.

❓ Model Choice

intermediate

Choosing the correct model output activation for categorical cross-entropy

Which activation function should the model's output layer use when training with categorical cross-entropy loss on multi-class classification?

A Softmax

B Sigmoid

C ReLU

D Linear

💡 Hint

Think about how probabilities for multiple classes should sum up.

Softmax converts raw outputs into probabilities that sum to 1, which is required for categorical cross-entropy loss in multi-class classification.

❓ Hyperparameter

advanced

Effect of label smoothing on categorical cross-entropy loss

What is the main effect of applying label smoothing when using categorical cross-entropy loss during training?

A It speeds up training by reducing the number of classes.

B It prevents overfitting by making the labels less confident, distributing some probability mass to other classes.

C It increases the confidence of the model predictions by sharpening the labels.

D It converts categorical cross-entropy into mean squared error loss.

💡 Hint

Think about how smoothing changes the target labels.

Label smoothing replaces hard 0/1 labels with softer values, which reduces overconfidence and helps generalization.

🔧 Debug

advanced

Identifying the error in categorical cross-entropy loss usage

What error will this code raise when computing categorical cross-entropy loss?

TensorFlow

import tensorflow as tf

true_labels = tf.constant([1, 0, 0])
predicted_probs = tf.constant([[0.7, 0.2, 0.1]])

loss_fn = tf.keras.losses.CategoricalCrossentropy()
loss_value = loss_fn(true_labels, predicted_probs).numpy()
print(loss_value)

A RuntimeError due to invalid probability values

B TypeError because true_labels is not a float tensor

C No error, outputs a valid loss value

D ValueError due to shape mismatch between true labels and predictions

💡 Hint

Check the shapes and types of true labels and predictions.

The true labels tensor shape is (3,) but predictions shape is (1,3), causing a shape mismatch error.

🧠 Conceptual

expert

Why use categorical cross-entropy instead of sparse categorical cross-entropy?

In which scenario is categorical cross-entropy loss preferred over sparse categorical cross-entropy loss?

A When true labels are one-hot encoded vectors

B When using binary classification with two classes

C When the model output is a single scalar value

D When true labels are provided as integer class indices

💡 Hint

Consider the format of the true labels expected by each loss function.

Categorical cross-entropy expects one-hot encoded labels, while sparse categorical cross-entropy expects integer class indices.

Practice

1. What does categorical cross-entropy loss measure in a classification model?

easy

A. The speed of model training

B. The total number of correct predictions

C. The difference between true categories and predicted probabilities

D. The size of the input data

Solution

1. Step 1: Understand the purpose of categorical cross-entropy

   Categorical cross-entropy loss calculates how far the predicted probabilities are from the true categories in classification tasks.

2. Step 2: Compare options with the definition

   Only The difference between true categories and predicted probabilities correctly describes this difference; others describe unrelated concepts.

3. Final Answer:

   The difference between true categories and predicted probabilities -> Option C

4. Quick Check:

   Loss measures prediction error = The difference [OK]

Hint: Loss measures difference between true and predicted labels [OK]

Common Mistakes:

• Confusing loss with accuracy
• Thinking loss measures training speed
• Mixing input data size with loss

2. Which of the following is the correct way to create a categorical cross-entropy loss in TensorFlow when your model outputs probabilities?

easy

A. tf.keras.losses.MeanSquaredError()

B. tf.keras.losses.CategoricalCrossentropy(from_logits=True)

C. tf.keras.losses.BinaryCrossentropy(from_logits=False)

D. tf.keras.losses.CategoricalCrossentropy(from_logits=False)

Solution

1. Step 1: Identify the correct loss function for probabilities

   When the model outputs probabilities, set from_logits=False in CategoricalCrossentropy.

2. Step 2: Check options for correct usage

   tf.keras.losses.CategoricalCrossentropy(from_logits=False) correctly uses CategoricalCrossentropy with from_logits=False; tf.keras.losses.CategoricalCrossentropy(from_logits=True) wrongly sets from_logits=True, and others use wrong loss types.

3. Final Answer:

   tf.keras.losses.CategoricalCrossentropy(from_logits=False) -> Option D

4. Quick Check:

   Probabilities output means from_logits=False [OK]

Hint: Set from_logits=False if outputs are probabilities [OK]

Common Mistakes:

• Using from_logits=True with probabilities
• Choosing binary cross-entropy for multi-class
• Using mean squared error for classification

3. Given the following code, what will be the output loss value?

import tensorflow as tf
loss_fn = tf.keras.losses.CategoricalCrossentropy(from_logits=False)
y_true = [[0, 1, 0]]
y_pred = [[0.1, 0.8, 0.1]]
loss = loss_fn(y_true, y_pred).numpy()
print(round(loss, 3))

medium

A. 0.000

B. 0.223

C. 0.500

D. 1.609

Solution

1. Step 1: Understand the inputs to the loss function

   y_true is one-hot with class 1 true; y_pred predicts 0.8 probability for class 1.

2. Step 2: Calculate categorical cross-entropy

   Loss = -log(predicted probability of true class) = -log(0.8) ≈ 0.223.

3. Final Answer:

   0.223 -> Option B

4. Quick Check:

   Loss = -log(0.8) ≈ 0.223 [OK]

Hint: Loss = -log(probability of true class) [OK]

Common Mistakes:

• Using raw logits without from_logits=True
• Calculating log of wrong class probability
• Rounding errors in loss value

4. Identify the error in this TensorFlow code snippet for categorical cross-entropy loss:

import tensorflow as tf
loss_fn = tf.keras.losses.CategoricalCrossentropy(from_logits=True)
y_true = [[0, 1, 0]]
y_pred = [[0.1, 0.8, 0.1]]
loss = loss_fn(y_true, y_pred).numpy()
print(loss)

medium

A. from_logits should be False because y_pred are probabilities

B. y_true should be integers, not one-hot vectors

C. Loss function should be BinaryCrossentropy

D. No error, code is correct

Solution

1. Step 1: Check the from_logits parameter

   from_logits=True means y_pred are raw scores, but here y_pred are probabilities summing to 1.

2. Step 2: Identify mismatch causing error

   Using from_logits=True with probabilities causes incorrect loss calculation; it should be False.

3. Final Answer:

   from_logits should be False because y_pred are probabilities -> Option A

4. Quick Check:

   Probabilities output means from_logits=False [OK]

Hint: Match from_logits to output type: True for logits, False for probabilities [OK]

Common Mistakes:

• Confusing logits with probabilities
• Using wrong loss function for multi-class
• Assuming one-hot labels must be integers

5. You have a model outputting raw logits for 4 classes. Which is the correct way to compute categorical cross-entropy loss during training in TensorFlow?

hard

A. Use tf.keras.losses.CategoricalCrossentropy(from_logits=True) with one-hot labels

B. Use tf.keras.losses.CategoricalCrossentropy(from_logits=False) with one-hot labels

C. Use tf.keras.losses.BinaryCrossentropy(from_logits=True) with integer labels

D. Use tf.keras.losses.MeanSquaredError() with one-hot labels

Solution

1. Step 1: Understand model output and label format

   The model outputs raw logits (not probabilities), and labels are one-hot encoded for multi-class classification.

2. Step 2: Choose correct loss function and parameters

   For raw logits, set from_logits=True in CategoricalCrossentropy; binary cross-entropy and mean squared error are incorrect for multi-class one-hot labels.

3. Final Answer:

   Use tf.keras.losses.CategoricalCrossentropy(from_logits=True) with one-hot labels -> Option A

4. Quick Check:

   Raw logits + one-hot labels = from_logits=True [OK]

Hint: Raw logits need from_logits=True in categorical cross-entropy [OK]

Common Mistakes:

• Using from_logits=False with logits
• Using binary cross-entropy for multi-class
• Using mean squared error for classification