Dataset class (custom datasets) in PyTorch - Cheat Sheet & Quick Revision

Recall & Review

beginner

What is the purpose of creating a custom Dataset class in PyTorch?

A custom Dataset class lets you load and prepare your own data in a way PyTorch understands. It helps organize data loading, transformation, and access for training models.

beginner

Which two methods must you implement when creating a custom Dataset class in PyTorch?

You must implement __len__ to return the size of the dataset and __getitem__ to get one data sample by index.

beginner

How does the __getitem__ method work in a custom Dataset?

It takes an index number and returns the data sample (like an image and label) at that position. This allows PyTorch to get data one piece at a time during training.

intermediate

Why might you want to apply transformations inside a custom Dataset?

Applying transformations (like resizing or normalization) inside the Dataset ensures data is prepared consistently every time it is loaded, making training smoother and more reliable.

intermediate

What is the benefit of using a custom Dataset with a DataLoader in PyTorch?

The DataLoader can automatically handle batching, shuffling, and parallel loading of data from your custom Dataset, making training efficient and easy.

Which method in a custom Dataset returns the total number of samples?

A load_data

B __getitem__

C __len__

D get_sample

The __len__ method returns the size of the dataset.

What should __getitem__ return in a custom Dataset?

A A single data sample (e.g., image and label)

B The batch of data

C The dataset size

D The entire dataset

__getitem__ returns one data sample at the given index.

Why use transformations inside a custom Dataset?

A To prepare data consistently for training

B To change the dataset size

C To speed up training by skipping data

D To shuffle the data

Transformations prepare data (like resizing or normalizing) consistently each time it is loaded.

Which PyTorch class helps load data in batches from a Dataset?

A BatchLoader

B DataLoader

C DatasetLoader

D DataBatcher

DataLoader loads data in batches and can shuffle or load in parallel.

What is the base class you inherit from to create a custom Dataset?

A torch.data.DataLoader

B torch.nn.Module

C torch.Tensor

D torch.utils.data.Dataset

Custom datasets inherit from torch.utils.data.Dataset.

Explain how to create a custom Dataset class in PyTorch and why it is useful.

Think about the two key methods and the role of the Dataset.

Describe how transformations can be integrated into a custom Dataset and their benefits.

Consider what happens to data before it is returned.

Practice

1. What is the main purpose of creating a custom Dataset class in PyTorch?

easy

A. To organize and provide access to your data for training models

B. To define the neural network architecture

C. To perform data visualization

D. To optimize the training speed automatically

Solution

1. Step 1: Understand Dataset role

   A custom Dataset class is designed to organize data and provide easy access to samples and labels.

2. Step 2: Differentiate from other components

   Neural network architecture and visualization are separate tasks, not handled by Dataset classes.

3. Final Answer:

   To organize and provide access to your data for training models -> Option A

4. Quick Check:

   Dataset class = data organization [OK]

Hint: Dataset class organizes data for model input [OK]

Common Mistakes:

• Confusing Dataset with model definition
• Thinking Dataset handles visualization
• Assuming Dataset optimizes training speed

2. Which method must be implemented in a PyTorch custom Dataset class to return the number of samples?

easy

A. __getitem__

B. __init__

C. __len__

D. load_data

Solution

1. Step 1: Recall Dataset methods

   __len__ returns the total number of samples in the dataset.

2. Step 2: Differentiate from other methods

   __getitem__ fetches a sample, __init__ initializes the dataset, load_data is not a standard method.

3. Final Answer:

   __len__ -> Option C

4. Quick Check:

   Count samples = __len__ [OK]

Hint: Use __len__ to get dataset size [OK]

Common Mistakes:

• Using __getitem__ to get length
• Confusing __init__ with length method
• Assuming load_data is required

3. What will be the output of this code snippet?

import torch
from torch.utils.data import Dataset

class MyDataset(Dataset):
    def __init__(self):
        self.data = [10, 20, 30]
    def __len__(self):
        return len(self.data)
    def __getitem__(self, idx):
        return self.data[idx] * 2

dataset = MyDataset()
print(len(dataset))
print(dataset[1])

medium

A. 3 and 40

B. 3 and 20

C. Error due to missing DataLoader

D. 3 and 30

Solution

1. Step 1: Calculate length of dataset

   len(dataset) calls __len__, which returns length of self.data = 3.

2. Step 2: Calculate dataset[1]

   dataset[1] calls __getitem__ with idx=1, returns self.data[1]*2 = 20*2 = 40.

3. Final Answer:

   3 and 40 -> Option A

4. Quick Check:

   Length=3, item*2=40 [OK]

Hint: Remember __getitem__ transforms data on access [OK]

Common Mistakes:

• Confusing index values
• Expecting error without DataLoader
• Forgetting the multiplication by 2

4. Identify the error in this custom Dataset class:

from torch.utils.data import Dataset

class SampleDataset(Dataset):
    def __init__(self, data):
        self.data = data
    def __len__(self):
        return self.data
    def __getitem__(self, idx):
        return self.data[idx]

medium

A. __getitem__ should return the index, not data element

B. __len__ should return an integer, not the data list

C. Missing __init__ method

D. Dataset class should inherit from torch.nn.Module

Solution

1. Step 1: Check __len__ method

   __len__ returns self.data, which is a list, but it must return an integer length.

2. Step 2: Verify other methods

   __getitem__ correctly returns data element; __init__ is present; Dataset inheritance is correct.

3. Final Answer:

   __len__ should return an integer, not the data list -> Option B

4. Quick Check:

   __len__ must return length integer [OK]

Hint: __len__ must return integer length [OK]

Common Mistakes:

• Returning list instead of length in __len__
• Confusing Dataset with nn.Module
• Omitting __init__ method

5. You want to create a custom Dataset that loads images and their labels from a folder. Which of these is the best approach to implement the __getitem__ method?

hard

A. Load all images in __init__ and return preloaded images in __getitem__

B. Return the file path as a string without loading the image

C. Only return labels in __getitem__, ignore images

D. Load the image file from disk, apply transformations, and return the image and label

Solution

1. Step 1: Understand __getitem__ role

   __getitem__ should load and return the actual data sample and label when requested.

2. Step 2: Evaluate options

   Loading image on demand with transformations is efficient and standard. Returning file path or only labels is incomplete. Loading all images in __init__ can use too much memory.

3. Final Answer:

   Load the image file from disk, apply transformations, and return the image and label -> Option D

4. Quick Check:

   __getitem__ loads and returns data [OK]

Hint: Load and transform data inside __getitem__ [OK]

Common Mistakes:

• Loading all data in __init__ causing memory issues
• Returning file paths instead of data
• Ignoring images and returning only labels