Data augmentation in PyTorch

Introduction

Data augmentation helps create more training examples by changing existing data. This makes models learn better and avoid mistakes.

When you have a small number of images to train a model.

When you want your model to recognize objects from different angles or lighting.

When you want to reduce overfitting by showing varied data.

When you want to improve model accuracy without collecting new data.

Syntax

PyTorch

import torchvision.transforms as transforms

transform = transforms.Compose([
    transforms.RandomHorizontalFlip(),
    transforms.RandomRotation(30),
    transforms.ToTensor()
])

Use transforms.Compose to combine multiple augmentations.

Apply augmentations only on training data, not on validation or test data.

Examples

Flips the image horizontally with a 50% chance.

PyTorch

transforms.RandomHorizontalFlip(p=0.5)

Rotates the image randomly within ±45 degrees.

PyTorch

transforms.RandomRotation(degrees=45)

Randomly changes brightness and contrast to make images look different.

PyTorch

transforms.ColorJitter(brightness=0.2, contrast=0.2)

Crops a random part of the image and resizes it to 224x224 pixels.

PyTorch

transforms.RandomResizedCrop(size=224)

Sample Model

This code loads the CIFAR10 training data and applies random horizontal flip and rotation to each image. It then prints the shape of one batch of images and their labels.

PyTorch

import torch
from torchvision import datasets, transforms
from torch.utils.data import DataLoader

# Define data augmentation transforms
transform = transforms.Compose([
    transforms.RandomHorizontalFlip(),
    transforms.RandomRotation(20),
    transforms.ToTensor()
])

# Load CIFAR10 training dataset with augmentation
train_dataset = datasets.CIFAR10(root='./data', train=True, download=True, transform=transform)
train_loader = DataLoader(train_dataset, batch_size=4, shuffle=True)

# Get one batch of images and labels
images, labels = next(iter(train_loader))

print(f'Batch image tensor shape: {images.shape}')
print(f'Batch labels: {labels}')

Important Notes

Always apply the same normalization after augmentation to keep data consistent.

Augmentation increases training time but improves model generalization.

Do not apply random augmentations to validation or test sets to get fair evaluation.

Summary

Data augmentation creates new training data by changing existing data.

It helps models learn better and avoid overfitting.

Use torchvision transforms like RandomHorizontalFlip and RandomRotation in PyTorch.

Practice

1. What is the main purpose of data augmentation in PyTorch training pipelines?

easy

A. To reduce the size of the training dataset

B. To create new training data by modifying existing data

C. To speed up model training by skipping data preprocessing

D. To convert data into a different file format

Solution

1. Step 1: Understand data augmentation concept

   Data augmentation means making new training examples by changing existing ones, like flipping or rotating images.

2. Step 2: Identify the purpose in training

   This helps the model see more variety and avoid memorizing only the original data, improving learning.

3. Final Answer:

   To create new training data by modifying existing data -> Option B

4. Quick Check:

   Data augmentation = create new data [OK]

Hint: Data augmentation means changing data to get more examples [OK]

Common Mistakes:

• Thinking it reduces dataset size
• Confusing augmentation with speeding training
• Believing it changes file formats

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

easy

A. transforms.RandomHorizontalFlip(p=0.5)

B. transforms.HorizontalFlip(prob=0.5)

C. transforms.RandomFlip(direction='horizontal')

D. transforms.FlipHorizontal(0.5)

Solution

1. Step 1: Recall torchvision transform syntax

   The correct transform for horizontal flip is RandomHorizontalFlip with a probability parameter p.

2. Step 2: Match correct syntax

   transforms.RandomHorizontalFlip(p=0.5) uses transforms.RandomHorizontalFlip(p=0.5), which is the exact PyTorch syntax.

3. Final Answer:

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

4. Quick Check:

   Correct transform name and parameter = C [OK]

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

Common Mistakes:

• Using wrong transform names
• Using 'prob' instead of 'p'
• Incorrect parameter names or missing parentheses

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

transform = transforms.Compose([
    transforms.RandomRotation(30),
    transforms.ToTensor()
])

image = Image.open('sample.jpg')
tensor_image = transform(image)
print(tensor_image.shape)

medium

A. [3, H, W] where H and W are original image height and width

B. [H, W, 3] where H and W are original image height and width

C. [1, H, W] grayscale image shape

D. [3, 30, 30] fixed size after rotation

Solution

1. Step 1: Understand transforms.Compose and RandomRotation

   RandomRotation rotates the image but keeps the original size (height and width). ToTensor converts the image to a tensor with shape [channels, height, width].

2. Step 2: Determine output tensor shape

   Since the image is color (3 channels), the tensor shape will be [3, H, W], where H and W are original height and width.

3. Final Answer:

   [3, H, W] where H and W are original image height and width -> Option A

4. Quick Check:

   Rotation keeps size, ToTensor outputs [3, H, W] [OK]

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

Common Mistakes:

• Confusing channel order as last dimension
• Assuming rotation changes image size
• Thinking output is grayscale shape

4. Identify the error in this PyTorch data augmentation code snippet:

transform = transforms.Compose([
    transforms.RandomHorizontalFlip(prob=0.5),
    transforms.RandomRotation(degrees=45),
    transforms.ToTensor()
])

medium

A. RandomRotation degrees must be a tuple, not a single number

B. ToTensor should come before RandomRotation

C. RandomHorizontalFlip should use keyword argument p=0.5

D. Compose cannot combine multiple transforms

Solution

1. Step 1: Check RandomHorizontalFlip usage

   RandomHorizontalFlip requires the probability argument as p=0.5, not prob=0.5.

2. Step 2: Verify other transforms

   RandomRotation accepts a single number for degrees, ToTensor can come last, and Compose supports multiple transforms.

3. Final Answer:

   RandomHorizontalFlip should use keyword argument p=0.5 -> Option C

4. Quick Check:

   Correct argument name = p [OK]

Hint: Check argument names carefully in transform constructors [OK]

Common Mistakes:

• Passing positional argument instead of keyword
• Thinking degrees must be tuple
• Misordering transforms in Compose

5. You want to augment a dataset of images to improve model robustness. Which combination of transforms would best increase variety without changing image size or color channels?

Options:
A) RandomHorizontalFlip(p=0.5) + RandomRotation(15) + ColorJitter(brightness=0.2)
B) RandomResizedCrop(size=224) + Grayscale(num_output_channels=1)
C) RandomVerticalFlip(p=1.0) + RandomRotation(90) + ToTensor()
D) Resize(128) + RandomCrop(64) + RandomHorizontalFlip(p=0.5)

hard

A. Resize and crop to smaller size (changes image size)

B. RandomResizedCrop and converting to grayscale (changes size and channels)

C. Vertical flip and 90-degree rotation (may change orientation drastically)

D. RandomHorizontalFlip, small RandomRotation, and ColorJitter to vary brightness

Solution

1. Step 1: Analyze each option's effect on size and channels

   RandomHorizontalFlip, small RandomRotation, and ColorJitter to vary brightness flips, rotates slightly, and changes brightness without resizing or changing channels. RandomResizedCrop and converting to grayscale (changes size and channels) changes size and converts to grayscale. Vertical flip and 90-degree rotation (may change orientation drastically) rotates 90 degrees and flips vertically, which changes orientation drastically. Resize and crop to smaller size (changes image size) resizes and crops, changing size.

2. Step 2: Choose the option that keeps size and channels but increases variety

   RandomHorizontalFlip, small RandomRotation, and ColorJitter to vary brightness best fits the requirement by augmenting with flips, small rotations, and brightness changes without altering size or channels.

3. Final Answer:

   RandomHorizontalFlip, small RandomRotation, and ColorJitter to vary brightness -> Option D

4. Quick Check:

   Keep size and channels, add mild augmentations = A [OK]

Hint: Pick augmentations that don't resize or change color channels [OK]

Common Mistakes:

• Choosing transforms that resize images
• Converting images to grayscale unintentionally
• Using large rotations that distort orientation