Custom Dataset class 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 you organize data and labels so you can easily use them for training models.

beginner

Which two methods must you always define in a PyTorch Custom Dataset class?

You must define __len__ to return the number of samples, and __getitem__ to get a single data sample by index.

beginner

How does the __getitem__ method work in a Custom Dataset?

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

intermediate

Why might you want to add data transformations inside a Custom Dataset?

Transformations like resizing or normalizing images help prepare data in a consistent way before training. Adding them inside the Dataset keeps data ready and clean.

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 faster and easier.

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

A __getitem__

B __len__

C load_data

D get_sample

The __len__ method returns how many samples the dataset contains.

What does the __getitem__ method return?

A A single data sample and its label

B The entire dataset

C The dataset size

D The data loader

The __getitem__ method returns one data sample and its label by index.

Why add transformations inside a Custom Dataset?

A To make data loading slower

B To avoid using DataLoader

C To increase dataset size

D To prepare data consistently before training

Transformations prepare data in a consistent way, like resizing or normalizing.

What does a DataLoader do when used with a Custom Dataset?

A Defines __getitem__ method

B Creates the dataset

C Handles batching and shuffling automatically

D Loads data from disk manually

DataLoader helps by batching, shuffling, and loading data in parallel.

Which PyTorch class do you inherit from to create a Custom Dataset?

A torch.utils.data.Dataset

B torch.Tensor

C torch.optim.Optimizer

D torch.nn.Module

You inherit from torch.utils.data.Dataset to create a Custom Dataset.

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

Think about the two main methods and the purpose of the class.

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

Consider what happens to data before it is returned.