Image augmentation transforms in Computer Vision

Introduction

Image augmentation transforms help create more varied pictures from a few images. This makes machine learning models better at understanding new pictures.

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 the model many versions of the same image.

When you want to simulate real-world changes like rotation, flipping, or zooming.

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

Syntax

Computer Vision

transform = torchvision.transforms.Compose([
    torchvision.transforms.RandomHorizontalFlip(p=0.5),
    torchvision.transforms.RandomRotation(degrees=30),
    torchvision.transforms.ColorJitter(brightness=0.2, contrast=0.2),
    torchvision.transforms.ToTensor()
])

Use Compose to chain multiple transforms together.

Each transform changes the image in a simple way, like flipping or rotating.

Examples

Always flips the image horizontally.

Computer Vision

transform = torchvision.transforms.RandomHorizontalFlip(p=1.0)

Rotates the image randomly within ±45 degrees.

Computer Vision

transform = torchvision.transforms.RandomRotation(degrees=45)

Randomly changes the brightness of the image.

Computer Vision

transform = torchvision.transforms.ColorJitter(brightness=0.5)

Randomly crops and resizes the image to 224x224 pixels, then converts it to a tensor.

Computer Vision

transform = torchvision.transforms.Compose([
    torchvision.transforms.RandomResizedCrop(224),
    torchvision.transforms.ToTensor()
])

Sample Model

This code loads an image from the internet, applies several augmentation transforms, and prints the shape and type of the resulting tensor. The image is flipped, rotated, brightness and contrast changed, then converted to a tensor.

Computer Vision

import torch
from torchvision import transforms
from PIL import Image
import requests
from io import BytesIO

# Load an example image from the web
url = 'https://upload.wikimedia.org/wikipedia/commons/thumb/4/47/PNG_transparency_demonstration_1.png/640px-PNG_transparency_demonstration_1.png'
response = requests.get(url)
img = Image.open(BytesIO(response.content))

# Define augmentation transforms
transform = transforms.Compose([
    transforms.RandomHorizontalFlip(p=1.0),
    transforms.RandomRotation(degrees=30),
    transforms.ColorJitter(brightness=0.3, contrast=0.3),
    transforms.ToTensor()
])

# Apply transforms
augmented_img = transform(img)

# Show shape and type
print(f"Augmented image tensor shape: {augmented_img.shape}")
print(f"Tensor type: {augmented_img.dtype}")

Important Notes

Transforms like RandomHorizontalFlip and RandomRotation add variety to training images.

Always convert images to tensors before feeding them to models.

Augmentation should be applied only to training data, not validation or test data.

Summary

Image augmentation creates new images by changing originals slightly.

Transforms include flipping, rotating, cropping, and color changes.

Using augmentation helps models learn better and avoid overfitting.

Practice

1. What is the main purpose of image augmentation in training machine learning models?

easy

A. To reduce the size of the training dataset

B. To remove noise from images

C. To create more varied training images by modifying originals

D. To convert images to grayscale only

Solution

1. Step 1: Understand image augmentation

   Image augmentation means making small changes to original images to create new ones.

2. Step 2: Purpose in training

   This helps models see more variety and learn better, avoiding overfitting.

3. Final Answer:

   To create more varied training images by modifying originals -> Option C

4. Quick Check:

   Image augmentation = create varied images [OK]

Hint: Augmentation means changing images to get more training data [OK]

Common Mistakes:

• Thinking augmentation reduces dataset size
• Confusing augmentation with noise removal
• Assuming augmentation only changes color

2. Which of the following is the correct way to apply a horizontal flip using PyTorch's torchvision transforms?

easy

A. transforms.RandomHorizontalFlip(p=1.0)

B. transforms.HorizontalFlip()

C. transforms.FlipHorizontal()

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

Solution

1. Step 1: Recall torchvision syntax

   PyTorch uses transforms.RandomHorizontalFlip(p=probability) to flip images horizontally.

2. Step 2: Check options

   Only transforms.RandomHorizontalFlip(p=1.0) matches the correct function and parameter style.

3. Final Answer:

   transforms.RandomHorizontalFlip(p=1.0) -> Option A

4. Quick Check:

   Correct PyTorch flip = RandomHorizontalFlip [OK]

Hint: Look for 'RandomHorizontalFlip' with probability parameter [OK]

Common Mistakes:

• Using non-existent transform names
• Missing the probability parameter
• Confusing horizontal with vertical flip

3. Given the following code snippet using torchvision transforms, what is the output image size after applying the transforms?

transform = transforms.Compose([
    transforms.Resize((128, 128)),
    transforms.RandomCrop(100),
    transforms.ToTensor()
])

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

medium

A. [3, 128, 128]

B. [3, 100, 100]

C. [1, 100, 100]

D. [3, 228, 228]

Solution

1. Step 1: Analyze each transform step

   First, image is resized to 128x128 pixels with 3 color channels (RGB). Then a random crop of size 100x100 is taken.

2. Step 2: Determine output tensor shape

   After cropping, the image size is 100x100 with 3 channels. ToTensor() converts it to a tensor with shape [channels, height, width] = [3, 100, 100].

3. Final Answer:

   [3, 100, 100] -> Option B

4. Quick Check:

   Resize then crop = final size 100x100 [OK]

Hint: Resize then crop means output size = crop size [OK]

Common Mistakes:

• Ignoring the crop step size
• Confusing channel dimension with batch size
• Assuming crop keeps original size

4. The following code is intended to rotate an image by 45 degrees using torchvision transforms, but it raises an error. What is the mistake?

transform = transforms.Compose([
    transforms.Rotate(45),
    transforms.ToTensor()
])

image = Image.open('sample.jpg')
output = transform(image)

medium

A. transforms.Rotate doesn't exist; should use transforms.functional.rotate or transforms.RandomRotation

B. The angle 45 must be in radians, not degrees

C. ToTensor must come before Rotate

D. Image.open returns a tensor, so transform fails

Solution

1. Step 1: Check torchvision transform names

   There is no transforms.Rotate class. Rotation is done with transforms.RandomRotation or using functional API.

2. Step 2: Identify correct usage

   To rotate by a fixed angle, use transforms.RandomRotation([45, 45]) or transforms.functional.rotate. The code as is will cause an AttributeError.

3. Final Answer:

   transforms.Rotate doesn't exist; should use transforms.functional.rotate or transforms.RandomRotation -> Option A

4. Quick Check:

   No transforms.Rotate in torchvision [OK]

Hint: Check transform names carefully; Rotate is not a direct class [OK]

Common Mistakes:

• Using non-existent transform classes
• Confusing degrees and radians
• Wrong order of transforms

5. You want to augment a dataset of images to improve model robustness. Which combination of transforms would best simulate real-world variations while keeping image size constant?

hard

A. transforms.RandomCrop(224), transforms.RandomRotation(180), transforms.Resize(128)

B. transforms.Resize(256), transforms.CenterCrop(224), transforms.RandomVerticalFlip() only

C. transforms.RandomRotation(90), transforms.RandomCrop(200), transforms.ToTensor()

D. transforms.RandomResizedCrop(224), transforms.RandomHorizontalFlip(), transforms.ColorJitter(brightness=0.2, contrast=0.2)

Solution

1. Step 1: Understand augmentation goals

   We want to simulate real-world changes like size, flip, and color while keeping output size fixed.

2. Step 2: Evaluate options

   transforms.RandomResizedCrop(224), transforms.RandomHorizontalFlip(), transforms.ColorJitter(brightness=0.2, contrast=0.2) resizes and crops randomly to 224x224, flips horizontally, and changes brightness/contrast, all common augmentations that keep size constant.

3. Step 3: Check other options

   transforms.Resize(256), transforms.CenterCrop(224), transforms.RandomVerticalFlip() only flips vertically and crops but lacks color changes. transforms.RandomRotation(90), transforms.RandomCrop(200), transforms.ToTensor() changes size unpredictably and transforms.RandomCrop(224), transforms.RandomRotation(180), transforms.Resize(128) resizes after cropping, changing size.

4. Final Answer:

   transforms.RandomResizedCrop(224), transforms.RandomHorizontalFlip(), transforms.ColorJitter(brightness=0.2, contrast=0.2) -> Option D

5. Quick Check:

   Best augmentations keep size fixed and add variety [OK]

Hint: Pick transforms that keep size fixed and add flip + color changes [OK]

Common Mistakes:

• Choosing transforms that change image size unpredictably
• Ignoring color augmentations
• Using only vertical flips which are less common