Compose transforms in PyTorch

Introduction

Compose transforms lets you combine many image changes into one step. This makes preparing images for a model easy and organized.

When you want to resize and normalize images before training a model.

When you need to apply multiple changes like cropping, flipping, and converting images to tensors.

When you want to keep your image processing steps clear and reusable.

When you want to apply the same set of changes to all images in a dataset.

When you want to chain simple image edits without writing separate code for each.

Syntax

PyTorch

transforms.Compose([
    transforms.Transform1(),
    transforms.Transform2(),
    ...
])

Each transform inside Compose is applied in order, one after another.

Use Compose to keep your image processing steps neat and easy to read.

Examples

Resize images to 128x128 pixels, then convert them to tensors.

PyTorch

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

Flip images randomly left-right, convert to tensor, then normalize pixel values.

PyTorch

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

Sample Model

This code downloads an image, resizes it to 64x64 pixels, converts it to a tensor, and normalizes its pixel values. Then it prints the tensor shape and pixel value range.

PyTorch

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

# Download an example image
url = 'https://pytorch.org/assets/images/deeplab1.png'
response = requests.get(url)
img = Image.open(BytesIO(response.content))

# Compose transforms: resize, convert to tensor, normalize
transform = transforms.Compose([
    transforms.Resize((64, 64)),
    transforms.ToTensor(),
    transforms.Normalize(mean=[0.5, 0.5, 0.5], std=[0.5, 0.5, 0.5])
])

# Apply transforms
img_t = transform(img)

# Print shape and pixel stats
print(f"Tensor shape: {img_t.shape}")
print(f"Min pixel value: {img_t.min():.3f}")
print(f"Max pixel value: {img_t.max():.3f}")

Important Notes

Normalize changes pixel values to a range that helps models learn better.

Transforms are applied in the order you list them inside Compose.

Always convert images to tensors before feeding them to PyTorch models.

Summary

Compose lets you chain many image transforms into one step.

Transforms run in the order you list them inside Compose.

Use Compose to keep image preprocessing clean and easy to manage.

Practice

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

easy

A. To chain multiple image transforms into one step

B. To train a neural network model

C. To load datasets from disk

D. To visualize images in a grid

Solution

1. Step 1: Understand Compose functionality

   Compose is used to combine several image transformations so they run one after another.

2. Step 2: Compare with other options

   Training models, loading datasets, and visualization are different tasks not handled by Compose.

3. Final Answer:

   To chain multiple image transforms into one step -> Option A

4. Quick Check:

   Compose chains transforms = C [OK]

Hint: Compose chains transforms in order for easy preprocessing [OK]

Common Mistakes:

• Thinking Compose trains models
• Confusing Compose with dataset loading
• Assuming Compose visualizes images

2. Which of the following is the correct way to create a Compose transform that converts images to tensor and normalizes them?

easy

A. transforms.Compose(transforms.ToTensor(), transforms.Normalize((0.5,), (0.5,)))

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

C. transforms.Compose{transforms.ToTensor(), transforms.Normalize((0.5,), (0.5,))}

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

Solution

1. Step 1: Check Compose syntax

   Compose takes a list of transforms inside square brackets [].

2. Step 2: Verify order and syntax

   transforms.Compose([transforms.ToTensor(), transforms.Normalize((0.5,), (0.5,))]) uses correct list syntax and order: ToTensor first, then Normalize. transforms.Compose(transforms.ToTensor(), transforms.Normalize((0.5,), (0.5,))) misses list brackets, C uses curly braces, D reverses order which is incorrect.

3. Final Answer:

   transforms.Compose([transforms.ToTensor(), transforms.Normalize((0.5,), (0.5,))]) -> Option B

4. Quick Check:

   Compose needs list and correct order = A [OK]

Hint: Use square brackets [] inside Compose and correct transform order [OK]

Common Mistakes:

• Omitting list brackets in Compose
• Using curly braces instead of brackets
• Reversing transform order

3. What will be the output shape of the tensor after applying this Compose transform on a 28x28 grayscale image?

transform = transforms.Compose([
    transforms.ToTensor(),
    transforms.Resize((14, 14))
])
img_tensor = transform(image)

medium

A. [3, 14, 14]

B. [1, 28, 28]

C. [1, 14, 14]

D. [3, 28, 28]

Solution

1. Step 1: Understand ToTensor output

   For a grayscale image, ToTensor() converts it to a tensor with shape [channels, height, width] where channels=1.

2. Step 2: Apply Resize transform

   Resize((14,14)) changes height and width to 14 each, channels remain 1.

3. Final Answer:

   [1, 14, 14] -> Option C

4. Quick Check:

   Grayscale tensor shape after resize = [1,14,14] [OK]

Hint: Grayscale images have 1 channel; Resize changes height and width [OK]

Common Mistakes:

• Assuming 3 channels for grayscale
• Ignoring Resize effect on shape
• Confusing height and width order

4. Identify the error in this Compose transform code:

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

medium

A. ToTensor should be replaced with ToPILImage

B. Normalize parameters are incorrect

C. Compose requires a tuple, not a list

D. Normalize should come after ToTensor

Solution

1. Step 1: Check transform order

   Normalize expects a tensor input, so ToTensor() must come first to convert image to tensor.

2. Step 2: Validate other options

   Parameters for Normalize are correct, Compose accepts list, and ToPILImage is not needed here.

3. Final Answer:

   Normalize should come after ToTensor -> Option D

4. Quick Check:

   Normalize after ToTensor = A [OK]

Hint: Always put ToTensor before Normalize in Compose [OK]

Common Mistakes:

• Placing Normalize before ToTensor
• Confusing list and tuple for Compose
• Replacing ToTensor incorrectly

5. You want to apply a Compose transform that first randomly flips an image horizontally, then converts it to a tensor, and finally normalizes it. Which code snippet correctly implements this?

hard

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

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

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

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

Solution

1. Step 1: Order of transforms

   RandomHorizontalFlip works on PIL images, so it must come before ToTensor which converts to tensor.

2. Step 2: Normalize after ToTensor

   Normalize requires tensor input, so it must come after ToTensor.

3. Step 3: Verify options

   transforms.Compose([transforms.RandomHorizontalFlip(), transforms.ToTensor(), transforms.Normalize((0.5,), (0.5,))]) has correct order: flip, then tensor, then normalize. Others have wrong order causing errors or wrong behavior.

4. Final Answer:

   transforms.Compose([transforms.RandomHorizontalFlip(), transforms.ToTensor(), transforms.Normalize((0.5,), (0.5,))]) -> Option A

5. Quick Check:

   Flip before ToTensor, Normalize last = D [OK]

Hint: Flip before ToTensor; Normalize last in Compose chain [OK]

Common Mistakes:

• Placing Normalize before ToTensor
• Applying flip after ToTensor (wrong input type)
• Mixing order causing runtime errors