Data augmentation importance in Computer Vision - Interactive Code Practice

Practice - 5 Tasks

1fill in blank

easy

Complete the code to import the library used for image data augmentation in Keras.

Computer Vision

from tensorflow.keras.preprocessing.image import [1]

Drag options to blanks, or click blank then click option'

AImageTransformer

BImageAugmentor

CImageDataGenerator

DImageLoader

Attempts:

3 left

💡 Hint

Common Mistakes

Using a non-existent class like ImageAugmentor.

Confusing with image loading classes.

The ImageDataGenerator class in Keras is used to perform image data augmentation.

2fill in blank

medium

Complete the code to create an ImageDataGenerator that applies horizontal flips to images.

Computer Vision

datagen = ImageDataGenerator([1]=True)

Drag options to blanks, or click blank then click option'

Ahorizontal_flip

Bvertical_flip

Crotation_range

Dzoom_range

Attempts:

3 left

💡 Hint

Common Mistakes

Using vertical_flip instead of horizontal_flip.

Confusing with rotation or zoom parameters.

The horizontal_flip parameter enables random horizontal flipping of images during augmentation.

3fill in blank

hard

Fix the error in the code to correctly apply data augmentation to the training images.

Computer Vision

train_generator = datagen.flow_from_directory(
    'train_data',
    target_size=(150, 150),
    batch_size=32,
    class_mode=[1]
)

Drag options to blanks, or click blank then click option'

Anone

Bsparse

Cbinary

Dcategorical

Attempts:

3 left

💡 Hint

Common Mistakes

Using 'binary' for multi-class problems.

Using 'none' which disables labels.

For multi-class classification, categorical is the correct class_mode to get one-hot encoded labels.

4fill in blank

hard

Fill both blanks to create a dictionary comprehension that maps image filenames to their augmented versions using the datagen.

Computer Vision

augmented_images = {img: datagen.[1](img) for img in images if img.[2]('.jpg')}

Drag options to blanks, or click blank then click option'

Aflow

Bendswith

Cstartswith

Dfit

Attempts:

3 left

💡 Hint

Common Mistakes

Using 'fit' instead of 'flow' to generate images.

Using 'startswith' instead of 'endswith' for file extension check.

The flow method generates augmented images from input images, and endswith checks if the filename ends with '.jpg'.

5fill in blank

hard

Fill all three blanks to complete the code that applies rotation and zoom augmentation, then fits the generator to training images.

Computer Vision

datagen = ImageDataGenerator(
    rotation_range=[1],
    zoom_range=[2]
)
datagen.[3](train_images)

Drag options to blanks, or click blank then click option'

A20

B0.15

Cfit

Dflow

Attempts:

3 left

💡 Hint

Common Mistakes

Using 'flow' instead of 'fit' to prepare the generator.

Confusing rotation_range with zoom_range values.

rotation_range=20 means images can rotate up to 20 degrees, zoom_range=0.15 means zooming up to 15%, and fit prepares the generator with the training images.

Practice

1. Why is data augmentation important in training computer vision models?

easy

A. It increases the variety of training images to help the model generalize better.

B. It reduces the size of the training dataset to speed up training.

C. It removes noisy images from the dataset automatically.

D. It guarantees 100% accuracy on the training data.

Solution

1. Step 1: Understand data augmentation purpose

   Data augmentation creates new images by slightly changing existing ones to increase variety.

2. Step 2: Connect augmentation to model learning

   More variety helps the model learn features that work on new, unseen images, improving generalization.

3. Final Answer:

   It increases the variety of training images to help the model generalize better. -> Option A

4. Quick Check:

   Data augmentation = better generalization [OK]

Hint: Think: more image variety means better learning [OK]

Common Mistakes:

• Confusing augmentation with data reduction
• Believing augmentation removes bad images
• Assuming augmentation guarantees perfect accuracy

2. Which of the following is a correct way to apply horizontal flip augmentation using Python's torchvision library?

easy

A. transforms.FlipHorizontal(prob=0.5)

B. transforms.HorizontalFlip(0.5)

C. transforms.RandomHorizontalFlip(p=0.5)

D. transforms.RandomFlipHorizontal()

Solution

1. Step 1: Recall torchvision syntax for horizontal flip

   The correct transform is RandomHorizontalFlip with a probability parameter p.

2. Step 2: Check each option's correctness

   Only transforms.RandomHorizontalFlip(p=0.5) matches the correct syntax and parameter name.

3. Final Answer:

   transforms.RandomHorizontalFlip(p=0.5) -> Option C

4. Quick Check:

   Correct torchvision flip syntax = transforms.RandomHorizontalFlip(p=0.5) [OK]

Hint: Look for 'RandomHorizontalFlip' with parameter p= [OK]

Common Mistakes:

• Using wrong class names like HorizontalFlip
• Incorrect parameter names like prob instead of p
• Missing the probability parameter

3. What will be the output shape of the augmented image after applying the following PyTorch transform?

transform = transforms.Compose([
  transforms.Resize((128, 128)),
  transforms.RandomRotation(30),
  transforms.ToTensor()
])
augmented_image = transform(original_image)

medium

A. [128, 3, 128]

B. [128, 128, 3]

C. [1, 128, 128]

D. [3, 128, 128]

Solution

1. Step 1: Analyze the transform steps

   Resize changes image to 128x128 pixels. RandomRotation keeps size same. ToTensor converts image to tensor with channels first.

2. Step 2: Determine tensor shape format

   PyTorch tensors from images have shape [channels, height, width]. For RGB images, channels=3.

3. Final Answer:

   [3, 128, 128] -> Option D

4. Quick Check:

   PyTorch image tensor shape = [channels, height, width] [OK]

Hint: PyTorch image tensors are channels first: [3, H, W] [OK]

Common Mistakes:

• Confusing channel order with height and width
• Assuming rotation changes image size
• Mixing up tensor shape formats

4. You wrote this augmentation code but get an error:

transform = transforms.Compose([
  transforms.RandomRotation(45),
  transforms.RandomHorizontalFlip(0.3),
  transforms.ToTensor()
])

What is the likely cause?

medium

A. RandomHorizontalFlip expects a keyword argument p, not a positional float.

B. RandomRotation requires integer degrees, not float.

C. ToTensor must come before RandomRotation.

D. Compose cannot combine these transforms.

Solution

1. Step 1: Check RandomHorizontalFlip usage

   RandomHorizontalFlip requires the probability parameter as a keyword argument p=, not a positional argument.

2. Step 2: Verify other transform usages

   RandomRotation accepts float degrees, ToTensor can be last, Compose supports these transforms.

3. Final Answer:

   RandomHorizontalFlip expects a keyword argument p, not a positional float. -> Option A

4. Quick Check:

   RandomHorizontalFlip(p=0.3) correct syntax [OK]

Hint: Check if transform params use correct keywords [OK]

Common Mistakes:

• Passing probability as positional argument
• Thinking rotation degrees must be integer
• Misordering transforms in Compose

5. You have a small dataset of 100 images for a classification task. Which data augmentation strategy will most likely improve your model's ability to recognize objects in new photos?

hard

A. Only resize images to a fixed size without any other changes.

B. Apply random flips, rotations up to 30 degrees, and brightness changes during training.

C. Add Gaussian noise to all images without any geometric transforms.

D. Train without augmentation but increase model layers.

Solution

1. Step 1: Consider dataset size and augmentation needs

   Small datasets benefit from augmentations that create varied views of images to prevent overfitting.

2. Step 2: Evaluate augmentation types

   Random flips, rotations, and brightness changes simulate real-world variations, improving generalization better than noise alone or no augmentation.

3. Final Answer:

   Apply random flips, rotations up to 30 degrees, and brightness changes during training. -> Option B

4. Quick Check:

   Varied augmentations = better generalization on small data [OK]

Hint: Use varied simple transforms for small datasets [OK]

Common Mistakes:

• Ignoring augmentation on small datasets
• Using only noise without geometric changes
• Relying on bigger models instead of data variety