Data augmentation for images in TensorFlow - Cheat Sheet & Quick Revision

Recall & Review

beginner

What is data augmentation in image processing?

Data augmentation is a technique to create new training images by applying random transformations like rotation, flipping, or zooming to existing images. It helps models learn better by seeing more varied data.

beginner

Name three common image transformations used in data augmentation.

Common transformations include flipping (horizontal or vertical), rotation (turning the image by some degrees), and zooming (scaling the image in or out).

intermediate

How does data augmentation help prevent overfitting?

By showing the model many different versions of images, data augmentation makes the model less likely to memorize exact images and more likely to learn general patterns.

intermediate

In TensorFlow, which layer can be used to apply data augmentation inside a model?

The tf.keras.layers.RandomFlip, RandomRotation, and RandomZoom layers can be used inside a model to apply data augmentation on the fly during training.

advanced

What is the difference between offline and online data augmentation?

Offline augmentation creates and saves new images before training. Online augmentation applies random transformations during training without saving new images, saving storage and adding variety each epoch.

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

A Sorting pixels by brightness

B Flipping

C Adding random noise

D Rotation

Sorting pixels by brightness is not a common augmentation technique because it changes the image structure unnaturally.

What is the main benefit of using data augmentation in training image models?

A Reduce model size

B Increase dataset size and improve model generalization

C Make training faster

D Remove noisy images

Data augmentation increases the variety of training images, helping the model generalize better.

Which TensorFlow layer would you use to flip images randomly during training?

A tf.keras.layers.Conv2D

B tf.keras.layers.Dense

C tf.keras.layers.Dropout

D tf.keras.layers.RandomFlip

RandomFlip applies random horizontal or vertical flips to images during training.

What does online data augmentation mean?

A Applying random transformations during training without saving images

B Augmenting images before training and saving them

C Using only original images without changes

D Augmenting images after training

Online augmentation applies random changes on the fly during training, increasing variety without extra storage.

Which of these is a valid reason to use data augmentation?

A To reduce the number of model parameters

B To make images smaller in file size

C To artificially increase training data diversity

D To convert images to grayscale

Data augmentation creates diverse training examples to help the model learn better.

Explain how data augmentation improves image model training and name some common augmentation techniques.

Think about how showing different versions of images helps the model.

Describe the difference between offline and online data augmentation and why you might choose one over the other.

Consider when and how augmented images are created and used.