Data transforms in PyTorch

Introduction

Data transforms help prepare and change data so a machine learning model can learn better. They make data easier to use and improve model results.

When images need to be resized to fit the model input size.

When you want to convert raw data into tensors for PyTorch models.

When you want to normalize data so all values are on a similar scale.

When you want to add random changes like flipping or rotating images to make the model more robust.

When you want to convert data types, like from PIL images to PyTorch tensors.

Syntax

PyTorch

transform = torchvision.transforms.Compose([
    torchvision.transforms.Resize((height, width)),
    torchvision.transforms.ToTensor(),
    torchvision.transforms.Normalize(mean, std)
])

Compose lets you combine many transforms in order.

Transforms like Resize, ToTensor, and Normalize are common for image data.

Examples

Convert an image to a PyTorch tensor with values between 0 and 1.

PyTorch

transform = torchvision.transforms.ToTensor()

Normalize tensor values to have mean 0 and standard deviation 1 after normalization.

PyTorch

transform = torchvision.transforms.Normalize(mean=[0.5], std=[0.5])

Resize images to 28x28, randomly flip horizontally, then convert to tensor.

PyTorch

transform = torchvision.transforms.Compose([
    torchvision.transforms.Resize((28, 28)),
    torchvision.transforms.RandomHorizontalFlip(),
    torchvision.transforms.ToTensor()
])

Sample Model

This code creates a white image, resizes it, converts it to a tensor, and normalizes it. Then it prints the tensor shape and pixel values.

PyTorch

import torch
from torchvision import transforms
from PIL import Image
import numpy as np

# Create a dummy image (100x100 pixels, white color)
image = Image.fromarray(np.full((100, 100, 3), fill_value=255, dtype=np.uint8))

# Define transforms: resize to 64x64, convert to tensor, normalize
transform = transforms.Compose([
    transforms.Resize((64, 64)),
    transforms.ToTensor(),
    transforms.Normalize(mean=[1.0, 1.0, 1.0], std=[1.0, 1.0, 1.0])
])

# Apply transform
transformed_image = transform(image)

# Print shape and some pixel values
print(f"Transformed image shape: {transformed_image.shape}")
print(f"Pixel value at (0,0): {transformed_image[:,0,0]}")

Important Notes

Normalization subtracts the mean and divides by std for each channel, so here mean=1 and std=1 makes pixel values zero after normalization.

Transforms are applied in order inside Compose.

Always convert images to tensors before feeding to PyTorch models.

Summary

Data transforms prepare raw data for machine learning models.

Use Compose to chain multiple transforms like resize, flip, tensor conversion, and normalization.

Transforms improve model training and prediction quality.

Practice

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

easy

A. To prepare and modify raw data before feeding it to a model

B. To create new neural network layers

C. To evaluate model accuracy

D. To save the trained model to disk

Solution

1. Step 1: Understand the role of data transforms

   Data transforms modify raw data to make it suitable for model input, such as resizing or normalizing images.

2. Step 2: Differentiate from other tasks

   Creating layers, evaluating accuracy, or saving models are separate tasks unrelated to data transforms.

3. Final Answer:

   To prepare and modify raw data before feeding it to a model -> Option A

4. Quick Check:

   Data transforms = prepare data [OK]

Hint: Transforms prepare data, not model or evaluation tasks [OK]

Common Mistakes:

• Confusing transforms with model building
• Thinking transforms evaluate model performance
• Mixing transforms with saving models

2. Which of the following is the correct way to chain multiple transforms using PyTorch's torchvision?

easy

A. transforms.Sequence(transforms.Resize(256), transforms.ToTensor())

B. transforms.Chain([transforms.Resize(256), transforms.ToTensor()])

C. transforms.Pipeline(transforms.Resize(256), transforms.ToTensor())

D. transforms.Compose([transforms.Resize(256), transforms.ToTensor()])

Solution

1. Step 1: Recall the correct class for chaining transforms

   PyTorch uses transforms.Compose to chain multiple transforms in a list.

2. Step 2: Check syntax correctness

   Only transforms.Compose accepts a list of transforms; others like Sequence, Pipeline, Chain do not exist in torchvision.

3. Final Answer:

   transforms.Compose([transforms.Resize(256), transforms.ToTensor()]) -> Option D

4. Quick Check:

   Use Compose for chaining transforms [OK]

Hint: Remember Compose takes a list of transforms [OK]

Common Mistakes:

• Using non-existent classes like Sequence or Pipeline
• Passing transforms as separate arguments instead of a list
• Confusing Compose with other transform functions

3. What will be the output shape of the tensor after applying the following transform to a 3-channel image of size 100x100?
transform = transforms.Compose([transforms.Resize(50), transforms.ToTensor()])

medium

A. [1, 50, 50]

B. [50, 50, 3]

C. [3, 50, 50]

D. [50, 3, 50]

Solution

1. Step 1: Understand Resize effect

   transforms.Resize(50) resizes the image to 50x50 pixels, keeping the number of channels unchanged (3 channels).

2. Step 2: Understand ToTensor output shape

   transforms.ToTensor() converts the image to a tensor with shape [channels, height, width], so shape is [3, 50, 50].

3. Final Answer:

   [3, 50, 50] -> Option C

4. Quick Check:

   Tensor shape = [channels, height, width] [OK]

Hint: Tensor shape is channels first after ToTensor [OK]

Common Mistakes:

• Assuming channels last format
• Confusing Resize parameter as channels
• Mixing height and width order

4. Identify the error in this transform code snippet:

transform = transforms.Compose([
    transforms.Resize(128),
    transforms.Normalize(mean=[0.5], std=[0.5]),
    transforms.ToTensor()
])

medium

A. ToTensor should be first

B. Normalize should come after ToTensor

C. Resize must be after Normalize

D. No error, code is correct

Solution

1. Step 1: Check order of transforms

   transforms.Normalize expects a tensor input, but here it is before ToTensor, which converts image to tensor.

2. Step 2: Correct order

   ToTensor must come before Normalize to convert image to tensor first, then normalize it.

3. Final Answer:

   Normalize should come after ToTensor -> Option B

4. Quick Check:

   Normalize after ToTensor [OK]

Hint: Normalize needs tensor input, so place after ToTensor [OK]

Common Mistakes:

• Placing Normalize before ToTensor
• Assuming Resize order matters with Normalize
• Thinking ToTensor can be anywhere

5. You want to apply random horizontal flip and then normalize an image tensor. Which of the following transform sequences is correct to ensure proper data augmentation and normalization?

hard

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

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

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

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

Solution

1. Step 1: Understand transform order for augmentation and normalization

   RandomHorizontalFlip works on PIL images, so it must come before ToTensor.

2. Step 2: Normalize after converting to tensor

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

3. Final Answer:

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

4. Quick Check:

   Flip before ToTensor, Normalize after ToTensor [OK]

Hint: Augment on images, normalize on tensors [OK]

Common Mistakes:

• Applying Normalize before ToTensor
• Applying RandomHorizontalFlip after ToTensor
• Mixing order of augmentation and normalization