Data augmentation as regularization in TensorFlow - Model Metrics & Evaluation

Metrics & Evaluation - Data augmentation as regularization

Which metric matters for Data Augmentation as Regularization and WHY

When using data augmentation as a way to help your model learn better, the key metrics to watch are validation loss and validation accuracy. These show how well your model performs on new, unseen data. Data augmentation helps the model not just memorize the training data but learn patterns that work on different examples. So, if validation accuracy improves and validation loss decreases, it means augmentation is helping the model generalize better.

Confusion Matrix Example

Imagine a simple classification task with 100 samples. After training with data augmentation, the confusion matrix might look like this:

      | Predicted Positive | Predicted Negative |
      |--------------------|--------------------|
      | True Positive (TP): 40 | False Positive (FP): 5 |
      | False Negative (FN): 10 | True Negative (TN): 45 |
    

Total samples = TP + FP + TN + FN = 40 + 5 + 45 + 10 = 100

From this, we calculate:

• Precision = TP / (TP + FP) = 40 / (40 + 5) = 0.89
• Recall = TP / (TP + FN) = 40 / (40 + 10) = 0.80
• Accuracy = (TP + TN) / Total = (40 + 45) / 100 = 0.85

Precision vs Recall Tradeoff with Data Augmentation

Data augmentation can help improve recall by showing the model more varied examples, so it misses fewer true cases. However, sometimes it may slightly reduce precision if the model becomes less strict and predicts more positives, including some wrong ones.

Example: For a face recognition app, data augmentation helps the model recognize faces in different lighting or angles, improving recall (finding more real faces). But if precision drops, it might wrongly identify some non-faces as faces.

Choosing the right balance depends on your goal. If missing a face is worse, prioritize recall. If false alarms are costly, prioritize precision.

What Good vs Bad Metrics Look Like with Data Augmentation

Good:

• Validation accuracy steadily increases compared to no augmentation.
• Validation loss decreases or stays stable, showing better generalization.
• Precision and recall both improve or stay balanced.
• Confusion matrix shows fewer false negatives and false positives.

Bad:

• Validation accuracy does not improve or gets worse.
• Validation loss increases, indicating overfitting or poor learning.
• Precision or recall drops significantly, showing imbalance.
• Confusion matrix shows many errors despite augmentation.

Common Pitfalls in Metrics with Data Augmentation

• Accuracy Paradox: High accuracy can be misleading if classes are imbalanced. Always check precision and recall.
• Data Leakage: Augmented data too similar to test data can inflate validation metrics falsely.
• Overfitting Indicators: If training accuracy is high but validation accuracy is low, augmentation might not be enough or incorrectly applied.
• Ignoring Validation Loss: Only looking at accuracy can miss if the model is uncertain or confused.

Self Check

Your model trained with data augmentation has 98% accuracy but only 12% recall on the positive class (e.g., fraud). Is this good for production?

Answer: No, it is not good. Even though accuracy is high, the model misses 88% of the positive cases (fraud). This low recall means many fraud cases go undetected, which is risky. You should improve recall, possibly by adjusting augmentation, model, or threshold.

Key Result

Data augmentation improves validation accuracy and recall by helping the model generalize better, but watch for tradeoffs in precision and overfitting.

Practice

1. What is the main purpose of data augmentation in TensorFlow models?

easy

A. To increase the size and variety of training data to improve model generalization

B. To reduce the number of layers in the model

C. To speed up the training process by using smaller batches

D. To convert images to grayscale before training

Solution

1. Step 1: Understand data augmentation concept

   Data augmentation creates new training examples by slightly changing existing data, which helps the model see more variety.

2. Step 2: Connect augmentation to model performance

   This variety helps the model learn general patterns instead of memorizing, improving its ability to work on new data.

3. Final Answer:

   To increase the size and variety of training data to improve model generalization -> Option A

4. Quick Check:

   Data augmentation = improve generalization [OK]

Hint: Augmentation adds data variety to help model learn better [OK]

Common Mistakes:

• Thinking augmentation reduces model size
• Confusing augmentation with batch size changes
• Assuming augmentation changes image color only

2. Which of the following is the correct way to add random horizontal flipping to a TensorFlow model using Keras preprocessing layers?

easy

A. tf.keras.layers.RandomFlip('vertical')

B. tf.keras.layers.RandomRotation(0.5)

C. tf.keras.layers.RandomFlip('horizontal')

D. tf.keras.layers.RandomZoom(0.2)

Solution

1. Step 1: Identify the correct augmentation layer for horizontal flip

   TensorFlow provides RandomFlip with options 'horizontal', 'vertical', or 'horizontal_and_vertical'. For horizontal flip, use 'horizontal'.

2. Step 2: Match the syntax

   The correct syntax is tf.keras.layers.RandomFlip('horizontal'). Other options apply different augmentations.

3. Final Answer:

   tf.keras.layers.RandomFlip('horizontal') -> Option C

4. Quick Check:

   RandomFlip('horizontal') = horizontal flip [OK]

Hint: RandomFlip('horizontal') flips images left-right [OK]

Common Mistakes:

• Using 'vertical' instead of 'horizontal' for horizontal flip
• Confusing RandomFlip with RandomRotation
• Using RandomZoom for flipping

3. Consider this TensorFlow code snippet for data augmentation:

import tensorflow as tf
aug_layer = tf.keras.Sequential([
  tf.keras.layers.RandomFlip('horizontal'),
  tf.keras.layers.RandomRotation(0.1)
])

input_image = tf.ones((1, 100, 100, 3))
augmented_image = aug_layer(input_image)
print(augmented_image.shape)

What will be the printed output?

medium

A. (1, 100, 100, 3)

B. (100, 100, 3)

C. (1, 100, 100)

D. (100, 3)

Solution

1. Step 1: Understand input and augmentation output shapes

   The input image has shape (1, 100, 100, 3), where 1 is batch size, 100x100 is image size, and 3 is color channels.

2. Step 2: Check if augmentation changes shape

   RandomFlip and RandomRotation only change pixel values, not shape. So output shape remains the same as input.

3. Final Answer:

   (1, 100, 100, 3) -> Option A

4. Quick Check:

   Augmentation keeps shape same = (1, 100, 100, 3) [OK]

Hint: Augmentation changes pixels, not shape [OK]

Common Mistakes:

• Assuming augmentation changes image dimensions
• Ignoring batch dimension in shape
• Confusing channel dimension with batch

4. You wrote this code to add random rotation to your model input:

aug_layer = tf.keras.layers.RandomRotation(1.5)
augmented = aug_layer(input_images)

But you get an error: "ValueError: Rotation factor must be between -1 and 1". What is the likely cause?

medium

A. The rotation factor 1.5 is valid; error is from input_images shape

B. Rotation factor 1.5 is out of allowed range; it must be between -1 and 1

C. Rotation factor 1.5 is interpreted as 50 radians, which is too large

D. Rotation factor must be a tuple, not a single float

Solution

1. Step 1: Check allowed range for RandomRotation factor

   RandomRotation expects a float between -1 and 1 representing the fraction of 2π radians.

2. Step 2: Identify the error cause

   The factor 1.5 > 1 triggers the ValueError since it is outside the allowed range [-1, 1].

3. Final Answer:

   Rotation factor 1.5 is out of allowed range; it must be between -1 and 1 -> Option B

4. Quick Check:

   Rotation factor must be between -1 and 1 [OK]

Hint: Rotation factor must be between -1 and 1 [OK]

Common Mistakes:

• Believing the rotation factor 1.5 is valid
• Confusing radians with fraction factor
• Passing tuple instead of float

5. You want to add data augmentation to your TensorFlow model to reduce overfitting. Which of these combined augmentation layers is best to add inside your model for regularization?

hard

A. tf.keras.Sequential([tf.keras.layers.RandomTranslation(0.5, 0.5), tf.keras.layers.RandomRotation(1.5)])

B. tf.keras.Sequential([tf.keras.layers.RandomContrast(0.5), tf.keras.layers.RandomBrightness(0.5)])

C. tf.keras.Sequential([tf.keras.layers.RandomCrop(50, 50), tf.keras.layers.RandomFlip('vertical')])

D. tf.keras.Sequential([tf.keras.layers.RandomFlip('horizontal'), tf.keras.layers.RandomRotation(0.2), tf.keras.layers.RandomZoom(0.1)])

Solution

1. Step 1: Evaluate augmentation types for regularization

   Good augmentations for regularization include flips, small rotations, and zooms to add variety without distorting data too much.

2. Step 2: Check each option for correctness and validity

   tf.keras.Sequential([tf.keras.layers.RandomFlip('horizontal'), tf.keras.layers.RandomRotation(0.2), tf.keras.layers.RandomZoom(0.1)]) combines horizontal flip, small rotation (0.2), and small zoom (0.1), all valid and helpful. tf.keras.Sequential([tf.keras.layers.RandomContrast(0.5), tf.keras.layers.RandomBrightness(0.5)]) uses RandomContrast and RandomBrightness, which are less common and may distort colors too much. tf.keras.Sequential([tf.keras.layers.RandomCrop(50, 50), tf.keras.layers.RandomFlip('vertical')]) uses RandomCrop(50, 50) which is valid syntax if input is larger. Vertical flip alone is less common. tf.keras.Sequential([tf.keras.layers.RandomTranslation(0.5, 0.5), tf.keras.layers.RandomRotation(1.5)]) uses RandomRotation(1.5) which is invalid (rotation factor must be ≤1).

3. Final Answer:

   tf.keras.Sequential([tf.keras.layers.RandomFlip('horizontal'), tf.keras.layers.RandomRotation(0.2), tf.keras.layers.RandomZoom(0.1)]) -> Option D

4. Quick Check:

   Combine valid flips, rotations, zooms for best augmentation [OK]

Hint: Use small flips, rotations, zooms for effective augmentation [OK]

Common Mistakes:

• Using invalid rotation factors >1
• Choosing only color augmentations
• Applying too large crops or translations