Image dataset from folders in PyTorch - Practice Problems & Coding Challenges

Challenge - 5 Problems

❓ Predict Output

intermediate

Output of loading images with ImageFolder

What will be the output shape of the first image tensor loaded using torchvision.datasets.ImageFolder with default ToTensor transform?

PyTorch

from torchvision import datasets, transforms
transform = transforms.ToTensor()
dataset = datasets.ImageFolder(root='data/train', transform=transform)
image, label = dataset[0]
print(image.shape)

A torch.Size([H, W]) where H and W are image height and width

B torch.Size([H, W, 3]) where H and W are image height and width

C torch.Size([1, H, W]) where H and W are image height and width

D torch.Size([3, H, W]) where H and W are image height and width

💡 Hint

Remember that ToTensor converts images to CxHxW format.

The ToTensor() transform converts PIL images to tensors with shape (channels, height, width). For color images, channels = 3 (RGB).

❓ data_output

intermediate

Number of classes in ImageFolder dataset

Given an ImageFolder dataset loaded from a folder with subfolders 'cats', 'dogs', and 'rabbits', what is the value of dataset.classes?

PyTorch

from torchvision import datasets
 dataset = datasets.ImageFolder(root='data/train')
print(dataset.classes)

A ['rabbits', 'dogs', 'cats']

B ['dogs', 'cats', 'rabbits']

C ['cats', 'dogs', 'rabbits']

D ['cats', 'rabbits', 'dogs']

💡 Hint

ImageFolder sorts folder names alphabetically to assign classes.

ImageFolder sorts the folder names alphabetically to create the classes list. So the order is ['cats', 'dogs', 'rabbits'].

🔧 Debug

advanced

Identify error loading images with ImageFolder

What error will occur when running this code if the root folder contains a file that is not an image or folder? from torchvision import datasets dataset = datasets.ImageFolder(root='data/train') image, label = dataset[0]

PyTorch

from torchvision import datasets
dataset = datasets.ImageFolder(root='data/train')
image, label = dataset[0]

A PIL.UnidentifiedImageError

B IndexError

C FileNotFoundError

D TypeError

💡 Hint

ImageFolder tries to open all files as images.

If a file is not a valid image, PIL will raise UnidentifiedImageError when ImageFolder tries to open it.

🚀 Application

advanced

Transform pipeline for ImageFolder dataset

Which transform pipeline correctly resizes images to 128x128, converts to tensor, and normalizes with mean=0.5 and std=0.5 for all channels?

A transforms.Compose([transforms.ToTensor(), transforms.Resize((128,128)), transforms.Normalize((0.5,), (0.5,))])

B transforms.Compose([transforms.Resize((128,128)), transforms.ToTensor(), transforms.Normalize((0.5,0.5,0.5), (0.5,0.5,0.5))])

C transforms.Compose([transforms.Resize(128), transforms.ToTensor(), transforms.Normalize((0.5,0.5,0.5), (0.5,0.5,0.5))])

D transforms.Compose([transforms.Resize((128,128)), transforms.Normalize((0.5,0.5,0.5), (0.5,0.5,0.5)), transforms.ToTensor()])

💡 Hint

Resize should come before ToTensor, and Normalize after ToTensor.

The correct order is Resize, then ToTensor, then Normalize. Resize needs a tuple for size. Normalize expects 3 values for RGB channels.

🧠 Conceptual

expert

Why use ImageFolder for image datasets?

What is the main advantage of using torchvision.datasets.ImageFolder to load image datasets organized in folders?

A It automatically assigns labels based on folder names and loads images efficiently.

B It converts images to grayscale automatically.

C It only works with PNG images.

D It requires images to be in a single folder without subfolders.

💡 Hint

Think about how labels are assigned in ImageFolder.

ImageFolder reads images from subfolders and assigns labels based on folder names, simplifying dataset creation.

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