Multi-class classification model in TensorFlow

Introduction

A multi-class classification model helps us teach a computer to tell which category something belongs to when there are more than two choices.

Sorting emails into categories like work, personal, or spam.

Recognizing handwritten digits from 0 to 9.

Classifying types of fruits in pictures like apples, bananas, or oranges.

Detecting the type of animal in a photo among cats, dogs, and birds.

Syntax

TensorFlow

model = tf.keras.Sequential([
    tf.keras.layers.Dense(units, activation='relu', input_shape=(input_features,)),
    tf.keras.layers.Dense(number_of_classes, activation='softmax')
])

model.compile(
    optimizer='adam',
    loss='sparse_categorical_crossentropy',
    metrics=['accuracy']
)

The last layer uses softmax to give probabilities for each class.

Use sparse_categorical_crossentropy loss when labels are integers representing classes.

Examples

This example builds a model for 3 classes with 4 input features.

TensorFlow

model = tf.keras.Sequential([
    tf.keras.layers.Dense(16, activation='relu', input_shape=(4,)),
    tf.keras.layers.Dense(3, activation='softmax')
])

model.compile(optimizer='adam', loss='sparse_categorical_crossentropy', metrics=['accuracy'])

This example is for 5 classes with 10 input features.

TensorFlow

model = tf.keras.Sequential([
    tf.keras.layers.Dense(32, activation='relu', input_shape=(10,)),
    tf.keras.layers.Dense(5, activation='softmax')
])

model.compile(optimizer='adam', loss='sparse_categorical_crossentropy', metrics=['accuracy'])

Sample Model

This program trains a simple multi-class model on small sample data with 3 classes. It then predicts classes for new samples.

TensorFlow

import tensorflow as tf
import numpy as np

# Sample data: 6 samples, 4 features each
X_train = np.array([
    [5.1, 3.5, 1.4, 0.2],
    [7.0, 3.2, 4.7, 1.4],
    [6.3, 3.3, 6.0, 2.5],
    [5.0, 3.6, 1.4, 0.2],
    [6.7, 3.1, 4.4, 1.4],
    [7.6, 3.0, 6.6, 2.1]
])

# Labels: 3 classes (0, 1, 2)
y_train = np.array([0, 1, 2, 0, 1, 2])

# Build model
model = tf.keras.Sequential([
    tf.keras.layers.Dense(10, activation='relu', input_shape=(4,)),
    tf.keras.layers.Dense(3, activation='softmax')
])

# Compile model
model.compile(optimizer='adam', loss='sparse_categorical_crossentropy', metrics=['accuracy'])

# Train model
history = model.fit(X_train, y_train, epochs=10, verbose=0)

# Predict on new data
X_new = np.array([
    [5.9, 3.0, 5.1, 1.8],
    [5.0, 3.4, 1.5, 0.2]
])
predictions = model.predict(X_new)
predicted_classes = predictions.argmax(axis=1)

print(f"Training accuracy after 10 epochs: {history.history['accuracy'][-1]:.2f}")
print(f"Predicted classes for new samples: {predicted_classes.tolist()}")

Important Notes

Make sure your labels are integers starting from 0 for sparse categorical loss.

Softmax outputs probabilities that add up to 1 for each sample.

More epochs usually improve accuracy but watch out for overfitting.

Summary

Multi-class models classify inputs into more than two categories.

Use softmax activation in the last layer to get class probabilities.

Use sparse_categorical_crossentropy loss when labels are integer class IDs.

Practice

1.

What activation function is commonly used in the last layer of a multi-class classification model in TensorFlow?

easy

A. Sigmoid

B. ReLU

C. Softmax

D. Tanh

Solution

1. Step 1: Understand the purpose of the last layer in multi-class classification

   The last layer outputs probabilities for each class, so the activation must convert raw scores to probabilities.

2. Step 2: Identify the activation function that outputs probabilities summing to 1

   Softmax converts logits into probabilities that sum to 1, suitable for multi-class classification.

3. Final Answer:

   Softmax -> Option C

4. Quick Check:

   Softmax = last layer activation [OK]

Hint: Use softmax for multi-class output probabilities [OK]

Common Mistakes:

• Using sigmoid which is for binary classification
• Using ReLU which does not output probabilities
• Using tanh which outputs values between -1 and 1

2.

Which loss function should you use in TensorFlow for a multi-class classification model with integer labels?

easy

A. binary_crossentropy

B. sparse_categorical_crossentropy

C. mean_squared_error

D. hinge

Solution

1. Step 1: Identify the label format

   Labels are integer class IDs, not one-hot encoded vectors.

2. Step 2: Choose loss function matching integer labels for multi-class

   Sparse categorical crossentropy works with integer labels directly, unlike categorical crossentropy which needs one-hot labels.

3. Final Answer:

   sparse_categorical_crossentropy -> Option B

4. Quick Check:

   Integer labels = sparse_categorical_crossentropy [OK]

Hint: Use sparse_categorical_crossentropy for integer class labels [OK]

Common Mistakes:

• Using binary_crossentropy which is for two classes
• Using mean_squared_error which is for regression
• Using hinge loss which is for SVMs

3.

What will be the shape of the output tensor from the last layer of this TensorFlow model for multi-class classification with 4 classes?

model = tf.keras.Sequential([
  tf.keras.layers.Dense(10, activation='relu'),
  tf.keras.layers.Dense(4, activation='softmax')
])
inputs = tf.random.uniform((5, 8))
outputs = model(inputs)
print(outputs.shape)

medium

A. (4, 5)

B. (8, 4)

C. (5, 10)

D. (5, 4)

Solution

1. Step 1: Understand input and output shapes

   Input batch size is 5, each input has 8 features. The last Dense layer outputs 4 units (classes).

2. Step 2: Determine output shape from last layer

   Output shape is (batch_size, number_of_classes) = (5, 4).

3. Final Answer:

   (5, 4) -> Option D

4. Quick Check:

   Batch size 5, classes 4 = (5, 4) [OK]

Hint: Output shape = (batch_size, number_of_classes) [OK]

Common Mistakes:

• Confusing batch size and feature dimensions
• Swapping rows and columns in output shape
• Assuming output shape matches input feature size

4.

Identify the error in this TensorFlow multi-class classification model code:

model = tf.keras.Sequential([
  tf.keras.layers.Dense(16, activation='relu'),
  tf.keras.layers.Dense(3, activation='sigmoid')
])
model.compile(optimizer='adam', loss='sparse_categorical_crossentropy', metrics=['accuracy'])

medium

A. Last layer activation should be softmax, not sigmoid

B. Loss function should be binary_crossentropy

C. Optimizer 'adam' is invalid

D. Dense layer units must be 1 for multi-class

Solution

1. Step 1: Check last layer activation for multi-class

   Sigmoid outputs independent probabilities, not suitable for multi-class where classes are exclusive.

2. Step 2: Correct activation for multi-class classification

   Softmax outputs probabilities summing to 1, appropriate for multi-class classification.

3. Final Answer:

   Last layer activation should be softmax, not sigmoid -> Option A

4. Quick Check:

   Multi-class needs softmax activation [OK]

Hint: Use softmax activation for multi-class last layer [OK]

Common Mistakes:

• Using sigmoid activation for multi-class output
• Confusing loss functions for classification types
• Thinking optimizer name 'adam' is invalid

5.

You want to build a multi-class classification model with 5 classes. Your labels are integers from 0 to 4. Which of the following code snippets correctly defines and compiles the model?

Option A:
model = tf.keras.Sequential([
  tf.keras.layers.Dense(32, activation='relu'),
  tf.keras.layers.Dense(5, activation='softmax')
])
model.compile(optimizer='adam', loss='sparse_categorical_crossentropy', metrics=['accuracy'])

Option B:
model = tf.keras.Sequential([
  tf.keras.layers.Dense(32, activation='relu'),
  tf.keras.layers.Dense(5, activation='sigmoid')
])
model.compile(optimizer='adam', loss='categorical_crossentropy', metrics=['accuracy'])

Option C:
model = tf.keras.Sequential([
  tf.keras.layers.Dense(32, activation='relu'),
  tf.keras.layers.Dense(1, activation='softmax')
])
model.compile(optimizer='adam', loss='sparse_categorical_crossentropy', metrics=['accuracy'])

Option D:
model = tf.keras.Sequential([
  tf.keras.layers.Dense(32, activation='relu'),
  tf.keras.layers.Dense(5, activation='softmax')
])
model.compile(optimizer='adam', loss='binary_crossentropy', metrics=['accuracy'])

hard

A. Option A

B. Option B

C. Option C

D. Option D

Solution

1. Step 1: Check output layer units and activation

   For 5 classes, output units must be 5 with softmax activation to get class probabilities.

2. Step 2: Check loss function matches label format

   Labels are integers, so sparse_categorical_crossentropy is correct loss.

3. Step 3: Verify optimizer and metrics

   Adam optimizer and accuracy metric are appropriate choices.

4. Final Answer:

   Option A -> Option A

5. Quick Check:

   Correct output units, activation, and loss for integer labels [OK]

Hint: Match output units and loss to label format [OK]

Common Mistakes:

• Using sigmoid activation for multi-class output
• Using binary_crossentropy loss for multi-class
• Setting output units to 1 instead of number of classes