Multi-class classification model in TensorFlow - Practice Problems & Coding Challenges

Challenge - 5 Problems

❓ Model Choice

intermediate

Choosing the correct output layer for multi-class classification

You want to build a neural network in TensorFlow to classify images into 5 different categories. Which output layer configuration is correct for this multi-class classification task?

A Dense(5, activation='softmax')

B Dense(1, activation='sigmoid')

C Dense(1, activation='softmax')

D Dense(5, activation='sigmoid')

💡 Hint

For multi-class classification, the output layer should have one neuron per class with a softmax activation.

Softmax activation outputs probabilities for each class summing to 1, which is needed for multi-class classification. Sigmoid is for binary or multi-label tasks.

❓ Metrics

intermediate

Correct loss function for multi-class classification

Which loss function should you use in TensorFlow when training a multi-class classification model with one-hot encoded labels?

A tf.keras.losses.SparseCategoricalCrossentropy()

B tf.keras.losses.BinaryCrossentropy()

C tf.keras.losses.MeanSquaredError()

D tf.keras.losses.CategoricalCrossentropy()

💡 Hint

One-hot encoded labels require a loss function that compares probability distributions.

CategoricalCrossentropy is used with one-hot labels. SparseCategoricalCrossentropy is for integer labels. BinaryCrossentropy is for binary tasks.

❓ Predict Output

advanced

Output shape of model predictions

Given the following TensorFlow model for 4-class classification, what is the shape of the output predictions for a batch of 10 samples?

TensorFlow

import tensorflow as tf
model = tf.keras.Sequential([
    tf.keras.layers.Dense(16, activation='relu', input_shape=(8,)),
    tf.keras.layers.Dense(4, activation='softmax')
])
import numpy as np
sample_input = np.random.random((10, 8))
predictions = model(sample_input)
predictions_shape = predictions.shape

A (10, 4)

B (4, 10)

C (10, 1)

D (1, 4)

💡 Hint

The output shape matches the batch size and number of classes.

For 10 samples and 4 classes, the output shape is (10, 4), each row is a probability distribution over classes.

❓ Hyperparameter

advanced

Effect of batch size on training stability

In training a multi-class classification model, what is a common effect of increasing the batch size too much?

A Training becomes more noisy and always improves generalization

B Model always overfits immediately

C Training becomes less noisy but may converge to sharp minima causing worse generalization

D Training speed decreases significantly without affecting accuracy

💡 Hint

Think about how batch size affects gradient noise and generalization.

Larger batch sizes reduce gradient noise, which can lead to convergence to sharp minima and worse generalization.

🔧 Debug

expert

Identifying the cause of poor multi-class model accuracy

You trained a multi-class classification model with 3 classes using one-hot encoded labels. The model's accuracy stays around 33% (random guess). Which of the following is the most likely cause?

A Using CategoricalCrossentropy loss with one-hot encoded labels

B Using SparseCategoricalCrossentropy loss with one-hot encoded labels

C Using softmax activation in the output layer

D Using Adam optimizer

💡 Hint

Check if the loss function matches the label format.

SparseCategoricalCrossentropy expects integer labels, not one-hot. Using it with one-hot labels causes poor training and accuracy.

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