Image dataset from folders in PyTorch

Introduction

We use image datasets from folders to easily load and organize pictures for training machine learning models.

You have images sorted in folders by category and want to train a model to recognize them.

You want to quickly load images with labels without manually writing code to assign labels.

You need to apply transformations like resizing or normalization while loading images.

You want to prepare data for image classification tasks using PyTorch.

Syntax

PyTorch

from torchvision.datasets import ImageFolder
from torchvision import transforms

dataset = ImageFolder(root='path/to/data', transform=transforms.Compose([
    transforms.Resize((224, 224)),
    transforms.ToTensor()
]))

root is the main folder containing subfolders for each class.

transform applies changes to images when loading, like resizing or converting to tensors.

Examples

Loads images from 'data/train' folder without any transformations.

PyTorch

dataset = ImageFolder(root='data/train')

Loads images and resizes them to 128x128 pixels, then converts to tensor.

PyTorch

from torchvision import transforms

transform = transforms.Compose([
    transforms.Resize((128, 128)),
    transforms.ToTensor()
])
dataset = ImageFolder(root='data/train', transform=transform)

Loads validation images and converts them directly to tensors.

PyTorch

dataset = ImageFolder(root='data/val', transform=transforms.ToTensor())

Sample Model

This code loads images from 'sample_data' folder, resizes them to 64x64 pixels, converts to tensors, and loads them in batches of 4. It prints the class names, the shape of one batch of images, and their labels.

PyTorch

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

# Define transformations: resize and convert to tensor
transform = transforms.Compose([
    transforms.Resize((64, 64)),
    transforms.ToTensor()
])

# Load dataset from folder 'sample_data'
dataset = ImageFolder(root='sample_data', transform=transform)

# Create a data loader to iterate in batches
loader = DataLoader(dataset, batch_size=4, shuffle=True)

# Print class names
print('Classes:', dataset.classes)

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

# Print batch shapes and labels
print('Batch image tensor shape:', images.shape)
print('Batch labels:', labels)

Important Notes

Folder names inside the root folder become the class labels automatically.

Images should be organized as root/class_x/xxx.png, root/class_y/yyy.png, etc.

Transforms help prepare images for model input and improve training.

Summary

ImageFolder loads images from folders where each folder is a class label.

Transforms can resize and convert images to tensors automatically.

DataLoader helps to batch and shuffle data for training.

Practice

1.

What does torchvision.datasets.ImageFolder do when loading images?

easy

A. Loads images and converts them to grayscale only

B. Loads images from a single folder without labels

C. Loads images and automatically splits them into training and testing sets

D. Loads images from folders where each folder name is used as a class label

Solution

1. Step 1: Understand ImageFolder functionality

   ImageFolder expects a root directory with subfolders. Each subfolder name is treated as a class label.

2. Step 2: Confirm label assignment

   Images inside each subfolder are assigned the label of that folder automatically.

3. Final Answer:

   Loads images from folders where each folder name is used as a class label -> Option D

4. Quick Check:

   ImageFolder uses folder names as labels [OK]

Hint: Remember: folder names become labels in ImageFolder [OK]

Common Mistakes:

• Thinking ImageFolder loads images without labels
• Assuming ImageFolder splits data automatically
• Believing ImageFolder converts images to grayscale by default

2.

Which of the following is the correct way to apply a transform that resizes images to 64x64 and converts them to tensors when using ImageFolder?

transform = transforms.Compose([
    ?
])
dataset = ImageFolder(root='data/train', transform=transform)

easy

A. transforms.Resize((64, 64)), transforms.ToTensor()

B. transforms.ToTensor(), transforms.Resize(64)

C. transforms.Resize(64), transforms.ToTensor()

D. transforms.ToPILImage(), transforms.Resize((64, 64))

Solution

1. Step 1: Identify correct transform order

   Resize must come before ToTensor because ToTensor expects a PIL image or ndarray.

2. Step 2: Check syntax correctness

   transforms.Resize takes a tuple for width and height. transforms.ToTensor converts PIL image to tensor.

3. Final Answer:

   transforms.Resize((64, 64)), transforms.ToTensor() -> Option A

4. Quick Check:

   Resize then ToTensor is correct order [OK]

Hint: Resize first, then convert to tensor [OK]

Common Mistakes:

• Applying ToTensor before Resize
• Using Resize with a single integer without tuple
• Using ToPILImage instead of ToTensor

3.

Given the following code, what will len(dataloader) print if the dataset has 100 images and batch_size=20?

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

transform = transforms.Compose([
    transforms.Resize((32, 32)),
    transforms.ToTensor()
])
dataset = ImageFolder(root='data/train', transform=transform)
dataloader = DataLoader(dataset, batch_size=20, shuffle=True)

print(len(dataloader))

medium

A. 5

B. 20

C. 100

D. 1

Solution

1. Step 1: Calculate number of batches

   Dataset size is 100 images, batch size is 20, so number of batches = 100 / 20 = 5.

2. Step 2: Confirm DataLoader length meaning

   len(dataloader) returns number of batches per epoch, which is 5 here.

3. Final Answer:

   5 -> Option A

4. Quick Check:

   100 images / 20 batch size = 5 batches [OK]

Hint: len(dataloader) = total images ÷ batch size [OK]

Common Mistakes:

• Confusing batch size with number of batches
• Assuming shuffle changes batch count
• Thinking len(dataloader) returns total images

4.

What is wrong with this code snippet for loading an image dataset?

from torchvision.datasets import ImageFolder
from torchvision import transforms

dataset = ImageFolder(root='data/train', transform=transforms.ToTensor())

medium

A. transforms.ToTensor() cannot be used alone without resizing or other transforms

B. transforms.ToTensor() expects a PIL image, but ImageFolder provides file paths

C. No error; this code works correctly

D. ImageFolder requires a list of image paths, not a root folder

Solution

1. Step 1: Check ImageFolder transform usage

   ImageFolder passes PIL images to the transform function, so transforms.ToTensor() works fine alone.

2. Step 2: Confirm no syntax or logic error

   Using only ToTensor is valid; resizing is optional but not required.

3. Final Answer:

   No error; this code works correctly -> Option C

4. Quick Check:

   ImageFolder passes PIL images, ToTensor alone is valid [OK]

Hint: ImageFolder sends PIL images, ToTensor alone is valid [OK]

Common Mistakes:

• Thinking ToTensor needs Resize always
• Believing ImageFolder needs image paths list
• Assuming ToTensor cannot handle PIL images

5.

You want to load images from folders and apply a transform that randomly flips images horizontally during training but not during validation. How can you set up ImageFolder and transforms for this?

hard

A. Use transforms.RandomHorizontalFlip() in both training and validation transforms

B. Use transforms.RandomHorizontalFlip() in training transform only, and a separate transform without flip for validation

C. Use transforms.RandomHorizontalFlip() only in validation transform

D. Use transforms.RandomHorizontalFlip() outside of transforms.Compose

Solution

1. Step 1: Understand data augmentation purpose

   RandomHorizontalFlip is a data augmentation used only during training to improve generalization.

2. Step 2: Apply transforms separately for train and validation

   Training transform includes RandomHorizontalFlip; validation transform excludes it to keep data consistent.

3. Final Answer:

   Use transforms.RandomHorizontalFlip() in training transform only, and a separate transform without flip for validation -> Option B

4. Quick Check:

   Augment training only, keep validation unchanged [OK]

Hint: Apply random flip only in training transforms [OK]

Common Mistakes:

• Applying random flip in validation data
• Not separating train and validation transforms
• Placing RandomHorizontalFlip outside Compose