Categorical cross-entropy loss in TensorFlow

Introduction

Categorical cross-entropy loss helps measure how well a model predicts categories by comparing predicted probabilities to the true category labels.

When training a model to classify images into multiple classes like cats, dogs, and birds.

When building a text classifier that assigns sentences to topics such as sports, politics, or technology.

When predicting the type of fruit from pictures where each fruit is a separate category.

When you have one correct category per example and want the model to learn to pick it.

When your labels are one-hot encoded vectors representing categories.

Syntax

TensorFlow

tf.keras.losses.CategoricalCrossentropy(from_logits=False, label_smoothing=0, axis=-1)

from_logits=False means the model outputs probabilities (values between 0 and 1). Set True if outputs are raw scores.

axis=-1 means the last dimension holds the category probabilities.

Examples

Basic use with default settings where y_pred contains probabilities.

TensorFlow

loss = tf.keras.losses.CategoricalCrossentropy()
loss_value = loss(y_true, y_pred)

Use when model outputs raw scores (logits) instead of probabilities.

TensorFlow

loss = tf.keras.losses.CategoricalCrossentropy(from_logits=True)
loss_value = loss(y_true, logits)

Adds label smoothing to make the model less confident and improve generalization.

TensorFlow

loss = tf.keras.losses.CategoricalCrossentropy(label_smoothing=0.1)
loss_value = loss(y_true, y_pred)

Sample Model

This example calculates the categorical cross-entropy loss for three samples with three classes each. The true labels are one-hot vectors, and predictions are probabilities. The loss shows how far predictions are from the true labels.

TensorFlow

import tensorflow as tf
import numpy as np

# True labels (one-hot encoded for 3 classes)
y_true = np.array([[0, 1, 0], [1, 0, 0], [0, 0, 1]], dtype=np.float32)

# Predicted probabilities from model
# Each row sums to 1 and shows predicted chance for each class
y_pred = np.array([[0.05, 0.9, 0.05], [0.8, 0.1, 0.1], [0.1, 0.2, 0.7]], dtype=np.float32)

# Create loss function
loss_fn = tf.keras.losses.CategoricalCrossentropy()

# Calculate loss
loss_value = loss_fn(y_true, y_pred).numpy()

print(f"Categorical cross-entropy loss: {loss_value:.4f}")

Important Notes

Make sure your true labels are one-hot encoded vectors matching the number of classes.

If your model outputs raw scores (logits), set from_logits=True to apply softmax internally.

Label smoothing can help prevent the model from becoming too confident and improve accuracy on new data.

Summary

Categorical cross-entropy loss measures the difference between true categories and predicted probabilities.

Use it when you have multiple classes and one correct class per example.

Set from_logits=True if your model outputs raw scores instead of probabilities.

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