Data augmentation in pipeline in TensorFlow - Cheat Sheet & Quick Revision

Recall & Review

beginner

What is data augmentation in a machine learning pipeline?

Data augmentation is a technique to create new training data by making small changes to existing data. It helps the model learn better by showing it more varied examples.

beginner

Why do we use data augmentation in the training pipeline?

We use data augmentation to increase the size and diversity of the training data. This reduces overfitting and helps the model generalize better to new data.

beginner

Name three common data augmentation techniques for images.

Common techniques include flipping images horizontally, rotating images by small angles, and zooming in or out slightly.

intermediate

How can data augmentation be integrated into a TensorFlow pipeline?

In TensorFlow, data augmentation can be added as part of the tf.data pipeline using functions like map() to apply augmentation operations on the fly during training.

intermediate

What is the benefit of applying data augmentation on the fly during training instead of beforehand?

Applying augmentation on the fly saves storage space and creates new variations each epoch, making the training data more diverse without needing to save all augmented images.

Which of the following is NOT a typical image data augmentation technique?

A Sorting pixels by brightness

B Adding random noise

C Horizontal flipping

D Random rotation

Sorting pixels by brightness is not a data augmentation technique; it changes the image content drastically and is not used for augmentation.

In TensorFlow, which method is commonly used to apply data augmentation in a pipeline?

A tf.constant()

B tf.keras.Model.compile()

C tf.Variable.assign()

D tf.data.Dataset.map()

tf.data.Dataset.map() applies a function to each element in the dataset, making it ideal for applying augmentation on the fly.

What is a key advantage of using data augmentation during training?

A It increases training data diversity

B It reduces the model size

C It speeds up training

D It removes the need for validation data

Data augmentation increases the diversity of training data, helping the model generalize better.

Which statement about data augmentation is TRUE?

A It always decreases model accuracy

B It can help prevent overfitting

C It requires manual labeling of new data

D It is only useful for text data

Data augmentation helps prevent overfitting by providing more varied training examples.

When applying data augmentation on the fly, what happens each training epoch?

A The same augmented images are reused

B The dataset size shrinks

C New random augmentations are applied each time

D No augmentation is applied after the first epoch

On-the-fly augmentation applies new random changes each epoch, increasing data variety.

Explain how data augmentation improves model training and how it can be implemented in a TensorFlow pipeline.

Think about why showing the model more varied images helps it learn better.

Describe the difference between applying data augmentation before training and applying it on the fly during training.

Consider storage needs and data variety over multiple training passes.

Practice

1. What is the main purpose of data augmentation in a TensorFlow training pipeline?

easy

A. To speed up the training process by skipping some images

B. To reduce the size of the training dataset

C. To create more varied training data by randomly changing original images

D. To convert images into grayscale only

Solution

1. Step 1: Understand data augmentation concept

   Data augmentation creates new training images by applying random changes like flips or rotations to original images.

2. Step 2: Identify the purpose in training pipeline

   This helps the model see more varied examples, improving learning and reducing overfitting.

3. Final Answer:

   To create more varied training data by randomly changing original images -> Option C

4. Quick Check:

   Data augmentation = varied training data [OK]

Hint: Augmentation adds variety to training images [OK]

Common Mistakes:

• Thinking augmentation reduces dataset size
• Believing augmentation speeds training by skipping data
• Assuming augmentation only converts images to grayscale

2. Which of the following is the correct way to add a random flip augmentation layer in a TensorFlow Sequential pipeline?

easy

A. tf.keras.Sequential([tf.keras.layers.RandomFlip('horizontal')])

B. tf.keras.Sequential([tf.keras.layers.FlipRandom('horizontal')])

C. tf.keras.Sequential([tf.keras.layers.RandomFlip(mode='vertical')])

D. tf.keras.Sequential([tf.keras.layers.RandomFlip('diagonal')])

Solution

1. Step 1: Recall TensorFlow augmentation syntax

   The correct layer is RandomFlip with argument 'horizontal' or 'vertical' as a string.

2. Step 2: Check each option

   tf.keras.Sequential([tf.keras.layers.RandomFlip('horizontal')]) uses correct class and argument. tf.keras.Sequential([tf.keras.layers.FlipRandom('horizontal')]) uses wrong class name. tf.keras.Sequential([tf.keras.layers.RandomFlip(mode='vertical')]) uses keyword argument 'mode' which is invalid. tf.keras.Sequential([tf.keras.layers.RandomFlip('diagonal')]) uses unsupported flip mode 'diagonal'.

3. Final Answer:

   tf.keras.Sequential([tf.keras.layers.RandomFlip('horizontal')]) -> Option A

4. Quick Check:

   Correct layer and argument = tf.keras.Sequential([tf.keras.layers.RandomFlip('horizontal')]) [OK]

Hint: Use RandomFlip('horizontal') exactly as named [OK]

Common Mistakes:

• Using wrong layer class name
• Passing arguments with wrong keywords
• Using unsupported flip modes

3. Given the following TensorFlow code snippet, what will be the output shape of the augmented images?

import tensorflow as tf
aug = tf.keras.Sequential([
  tf.keras.layers.RandomFlip('horizontal'),
  tf.keras.layers.RandomRotation(0.1)
])
input_image = tf.random.uniform([1, 128, 128, 3])
output_image = aug(input_image)
print(output_image.shape)

medium

A. (1, 128, 128, 3)

B. (128, 128, 3)

C. (1, 256, 256, 3)

D. (1, 128, 128)

Solution

1. Step 1: Understand input and augmentation layers

   Input shape is (1, 128, 128, 3) meaning batch size 1, 128x128 image with 3 color channels. RandomFlip and RandomRotation do not change image size.

2. Step 2: Check output shape after augmentation

   Augmentation layers keep the shape same, so output shape remains (1, 128, 128, 3).

3. Final Answer:

   (1, 128, 128, 3) -> Option A

4. Quick Check:

   Augmentation keeps shape = (1, 128, 128, 3) [OK]

Hint: Augmentation layers keep input shape unchanged [OK]

Common Mistakes:

• Assuming rotation changes image size
• Ignoring batch dimension in output
• Dropping color channels

4. Identify the error in this TensorFlow data augmentation pipeline code:

import tensorflow as tf
aug = tf.keras.Sequential([
  tf.keras.layers.RandomFlip('horizontal'),
  tf.keras.layers.RandomRotation(0.2, 0.3)
])

medium

A. Missing input shape in Sequential

B. RandomFlip does not accept 'horizontal' as argument

C. Sequential cannot contain augmentation layers

D. RandomRotation requires a single float or tuple, not two separate floats

Solution

1. Step 1: Check RandomRotation layer arguments

   RandomRotation expects either a single float or a tuple like (min_factor, max_factor). Passing two separate floats is invalid.

2. Step 2: Verify other parts

   RandomFlip('horizontal') is valid. Sequential can contain augmentation layers. Input shape is optional here.

3. Final Answer:

   RandomRotation requires a single float or tuple, not two separate floats -> Option D

4. Quick Check:

   RandomRotation argument format error = RandomRotation requires a single float or tuple, not two separate floats [OK]

Hint: RandomRotation needs one float or tuple, not two floats [OK]

Common Mistakes:

• Passing multiple floats instead of tuple to RandomRotation
• Thinking RandomFlip argument is invalid
• Believing Sequential can't hold augmentation layers

5. You want to build a TensorFlow data augmentation pipeline that randomly flips images horizontally, rotates them by up to 20%, and zooms in or out by up to 10%. Which of the following code snippets correctly implements this pipeline?

hard

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

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

C. tf.keras.Sequential([
tf.keras.layers.RandomFlip('horizontal'),
tf.keras.layers.RandomRotation(0.02),
tf.keras.layers.RandomZoom(10)
])

D. tf.keras.Sequential([
tf.keras.layers.RandomFlip('vertical'),
tf.keras.layers.RandomRotation(20),
tf.keras.layers.RandomZoom((0.1, 0.1))
])

Solution

1. Step 1: Check flip and rotation parameters

   RandomFlip('horizontal') is correct. RandomRotation expects a float fraction (0.2 means 20%).

2. Step 2: Check zoom parameters

   RandomZoom(0.1) means zoom in/out by 10%. tf.keras.Sequential([ tf.keras.layers.RandomFlip('horizontal'), tf.keras.layers.RandomRotation(0.2), tf.keras.layers.RandomZoom((0.1, 0.2)) ]) uses zoom (0.1, 0.2) which is uneven zoom, not requested.

3. Final Answer:

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

4. Quick Check:

   Correct flip, rotation fraction, and zoom float = tf.keras.Sequential([ tf.keras.layers.RandomFlip('horizontal'), tf.keras.layers.RandomRotation(0.2), tf.keras.layers.RandomZoom(0.1) ]) [OK]

Hint: Use fractions for rotation and single float for zoom [OK]

Common Mistakes:

• Using degrees instead of fraction for rotation
• Passing large numbers to zoom
• Choosing wrong flip direction