Data augmentation with transforms in PyTorch - Interactive Code Practice

Practice - 5 Tasks

1fill in blank

easy

Complete the code to import the torchvision transforms module.

PyTorch

from torchvision import [1]

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

Autils

Btransforms

Cdatasets

Dmodels

Attempts:

3 left

💡 Hint

Common Mistakes

Importing datasets instead of transforms

Importing models which is unrelated to data augmentation

The transforms module in torchvision provides common image transformations used for data augmentation.

2fill in blank

medium

Complete the code to create a transform that randomly flips images horizontally.

PyTorch

transform = transforms.[1](p=0.5)

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

AColorJitter

BRandomRotation

CRandomHorizontalFlip

DRandomCrop

Attempts:

3 left

💡 Hint

Common Mistakes

Using RandomRotation which rotates images instead of flipping

Using ColorJitter which changes colors, not flips

RandomHorizontalFlip randomly flips the image horizontally with a given probability p.

3fill in blank

hard

Fix the error in the transform pipeline to convert images to tensor after resizing.

PyTorch

transform = transforms.Compose([
    transforms.Resize((128, 128)),
    transforms.[1](),
])

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

AToTensor

BToPILImage

CNormalize

DRandomCrop

Attempts:

3 left

💡 Hint

Common Mistakes

Using ToPILImage which converts tensor back to image

Using Normalize without converting to tensor first

ToTensor converts a PIL image or numpy array to a PyTorch tensor, which is needed after resizing.

4fill in blank

hard

Fill both blanks to create a transform pipeline that randomly crops and then normalizes images.

PyTorch

transform = transforms.Compose([
    transforms.[1](size=100),
    transforms.ToTensor(),
    transforms.[2](mean=[0.5, 0.5, 0.5], std=[0.5, 0.5, 0.5])
])

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

ARandomCrop

BRandomHorizontalFlip

CNormalize

DResize

Attempts:

3 left

💡 Hint

Common Mistakes

Using Resize instead of RandomCrop for cropping

Using RandomHorizontalFlip instead of Normalize for normalization

RandomCrop crops the image randomly to the given size. Normalize adjusts pixel values to have the specified mean and standard deviation.

5fill in blank

hard

Fill all three blanks to create a transform pipeline that resizes, converts to tensor, and applies random rotation.

PyTorch

transform = transforms.Compose([
    transforms.[1]((64, 64)),
    transforms.[2](),
    transforms.[3](degrees=30)
])

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

AResize

BToTensor

CRandomRotation

DCenterCrop

Attempts:

3 left

💡 Hint

Common Mistakes

Mixing order of transforms causing errors

Using CenterCrop instead of Resize for resizing

The pipeline first Resizes images to 64x64 pixels, then converts them to tensors with ToTensor, and finally applies a random rotation up to 30 degrees with RandomRotation.

Practice

1. What is the main purpose of using transforms.Compose in PyTorch data augmentation?

easy

A. To combine multiple image transformations into one pipeline

B. To train the model faster by skipping data loading

C. To convert images into numpy arrays

D. To save the augmented images to disk automatically

Solution

1. Step 1: Understand the role of transforms.Compose

   transforms.Compose is used to chain several image transformations so they apply sequentially to the input image.

2. Step 2: Identify the correct purpose

   It does not speed up training directly, convert images to numpy, or save images. Its main job is combining transformations.

3. Final Answer:

   To combine multiple image transformations into one pipeline -> Option A

4. Quick Check:

   transforms.Compose = combine transforms [OK]

Hint: Remember Compose chains transforms in order [OK]

Common Mistakes:

• Thinking Compose speeds up training
• Confusing Compose with image saving
• Assuming Compose converts image formats

2. Which of the following is the correct way to apply a horizontal flip and convert an image to a tensor using PyTorch transforms?

easy

A. transforms.Compose(transforms.RandomHorizontalFlip(), transforms.ToTensor())

B. transforms.Compose([transforms.RandomHorizontalFlip(), transforms.ToTensor()])

C. transforms.ToTensor(transforms.RandomHorizontalFlip())

D. transforms.RandomHorizontalFlip(transforms.ToTensor())

Solution

1. Step 1: Check the syntax for combining transforms

   PyTorch requires transforms to be passed as a list inside transforms.Compose([]).

2. Step 2: Validate each option

   transforms.Compose([transforms.RandomHorizontalFlip(), transforms.ToTensor()]) correctly uses a list inside Compose. The other options misuse function calls or pass arguments incorrectly.

3. Final Answer:

   transforms.Compose([transforms.RandomHorizontalFlip(), transforms.ToTensor()]) -> Option B

4. Quick Check:

   Compose needs list of transforms [OK]

Hint: Use Compose with a list of transforms inside brackets [OK]

Common Mistakes:

• Passing transforms as separate arguments instead of a list
• Calling transforms inside each other incorrectly
• Forgetting to convert images to tensor

3. Given the following code, what will be the shape of the output tensor after applying the transforms to a 3-channel 64x64 image?

transform = transforms.Compose([
    transforms.RandomRotation(90),
    transforms.ToTensor()
])
output = transform(image)

medium

A. [1, 64, 64]

B. [64, 64, 3]

C. [3, 64, 64]

D. [64, 3, 64]

Solution

1. Step 1: Understand the transform effects

   RandomRotation rotates the image but does not change its size or channels. ToTensor converts the image to a tensor with shape [channels, height, width].

2. Step 2: Determine output shape

   Input image is 3 channels, 64x64 pixels. After ToTensor, shape is [3, 64, 64]. Rotation keeps size same.

3. Final Answer:

   [3, 64, 64] -> Option C

4. Quick Check:

   ToTensor output shape = [channels, height, width] [OK]

Hint: ToTensor outputs [channels, height, width] shape [OK]

Common Mistakes:

• Confusing channel position in tensor shape
• Assuming rotation changes image size
• Thinking output is a numpy array shape

4. Identify the error in this PyTorch transform pipeline:

transform = transforms.Compose([
    transforms.RandomCrop(32),
    transforms.ToTensor,
    transforms.Normalize((0.5,), (0.5,))
])

medium

A. transforms.ToTensor is missing parentheses to call it

B. Normalize mean and std should be lists, not tuples

C. RandomCrop size should be a tuple, not an integer

D. Compose should not be used with Normalize

Solution

1. Step 1: Check each transform usage

   RandomCrop accepts an integer for size, so that is correct. Normalize accepts tuples for mean and std, so that is correct.

2. Step 2: Identify the missing parentheses

   transforms.ToTensor is a class, but it must be called as transforms.ToTensor() to create the transform instance.

3. Final Answer:

   transforms.ToTensor is missing parentheses to call it -> Option A

4. Quick Check:

   Call ToTensor() with parentheses [OK]

Hint: Always call transforms with parentheses [OK]

Common Mistakes:

• Forgetting parentheses on transform classes
• Thinking Normalize needs lists instead of tuples
• Misunderstanding RandomCrop size argument

5. You want to augment your training images by randomly flipping horizontally, rotating by up to 30 degrees, and normalizing with mean=0.5 and std=0.5 for each channel. Which transform pipeline correctly applies these steps in PyTorch?

hard

A. transforms.Compose([transforms.ToTensor(), transforms.RandomHorizontalFlip(), transforms.RandomRotation(30), transforms.Normalize((0.5,), (0.5,))])

B. transforms.Compose([transforms.Normalize((0.5, 0.5, 0.5), (0.5, 0.5, 0.5)), transforms.RandomHorizontalFlip(), transforms.RandomRotation(30), transforms.ToTensor()])

C. transforms.Compose([transforms.RandomRotation(30), transforms.RandomHorizontalFlip(), transforms.Normalize((0.5, 0.5, 0.5), (0.5, 0.5, 0.5)), transforms.ToTensor()])

D. transforms.Compose([transforms.RandomHorizontalFlip(), transforms.RandomRotation(30), transforms.ToTensor(), transforms.Normalize((0.5, 0.5, 0.5), (0.5, 0.5, 0.5))])

Solution

1. Step 1: Order of transforms matters

   Data augmentation like flipping and rotation must happen before converting to tensor. Normalization happens after ToTensor.

2. Step 2: Check each option's order and parameters

   transforms.Compose([transforms.RandomHorizontalFlip(), transforms.RandomRotation(30), transforms.ToTensor(), transforms.Normalize((0.5, 0.5, 0.5), (0.5, 0.5, 0.5))]) applies flip and rotation first, then ToTensor, then Normalize with correct mean/std for 3 channels. Others have wrong order or missing steps.

3. Final Answer:

   transforms.Compose([transforms.RandomHorizontalFlip(), transforms.RandomRotation(30), transforms.ToTensor(), transforms.Normalize((0.5, 0.5, 0.5), (0.5, 0.5, 0.5))]) -> Option D

4. Quick Check:

   Augment before ToTensor, normalize after [OK]

Hint: Augment first, then ToTensor, then Normalize [OK]

Common Mistakes:

• Normalizing before ToTensor
• Applying augmentations after ToTensor
• Using wrong mean/std shapes for Normalize