Multi-class classification model in TensorFlow - Model Metrics & Evaluation

Metrics & Evaluation - Multi-class classification model

Which metric matters for Multi-class classification and WHY

In multi-class classification, the model predicts one class out of many possible classes. The key metrics to check are accuracy, precision, recall, and F1-score for each class. Accuracy tells how often the model is right overall. Precision shows how many predicted items for a class are correct. Recall shows how many actual items of a class the model found. F1-score balances precision and recall. These metrics help understand if the model is good at distinguishing all classes well.

Confusion matrix for Multi-class classification

A confusion matrix shows how predictions match actual classes. For 3 classes (A, B, C), it looks like this:

      | Predicted A | Predicted B | Predicted C |
      |-------------|-------------|-------------|
      |     50      |      2      |      3      | Actual A
      |      4      |     45      |      1      | Actual B
      |      5      |      2      |     43      | Actual C
    

Each row sums to total samples of that actual class. Diagonal numbers are correct predictions (True Positives for each class). Off-diagonal numbers are errors.

Precision vs Recall tradeoff with examples

Imagine a model classifying animals: cats, dogs, and rabbits.

• High precision for cats: When the model says "cat," it is usually right. This is good if you want to avoid wrongly labeling dogs or rabbits as cats.
• High recall for cats: The model finds most of the actual cats. This is important if missing a cat is costly, like in a pet shelter.

Improving precision may lower recall and vice versa. The F1-score helps balance both.

What "good" vs "bad" metric values look like

For a balanced multi-class problem:

• Good: Accuracy above 85%, precision and recall above 80% for all classes, and F1-scores close to precision and recall.
• Bad: Accuracy below 60%, large differences in precision or recall between classes (e.g., 90% for one class but 30% for another), or very low F1-scores indicating poor balance.

Good metrics mean the model predicts all classes well. Bad metrics mean the model struggles with some classes or overall.

Common pitfalls in metrics for multi-class classification

• Accuracy paradox: High accuracy can be misleading if classes are imbalanced. For example, if 90% of data is class A, predicting only A gives 90% accuracy but poor performance on other classes.
• Ignoring per-class metrics: Overall accuracy hides if some classes are poorly predicted.
• Data leakage: If test data leaks into training, metrics look unrealistically good.
• Overfitting: Very high training accuracy but low test accuracy means the model memorizes training data and won't generalize.

Self-check question

Your multi-class model has 92% accuracy but the recall for class B is 40%. Is it good for production?

Answer: No, because the model misses many actual class B samples. Even with high overall accuracy, poor recall on a class means the model is not reliable for that class. You should improve recall for class B before production.

Key Result

In multi-class classification, balanced precision, recall, and F1-score per class are key to ensure the model predicts all classes well, beyond just overall 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