Built-in datasets (torchvision.datasets) in PyTorch - Cheat Sheet & Quick Revision

Recall & Review

beginner

What is torchvision.datasets used for in PyTorch?

torchvision.datasets provides ready-to-use popular datasets for computer vision tasks. It helps you quickly load and use datasets like MNIST, CIFAR-10, and FashionMNIST without manual downloading or preprocessing.

beginner

How do you load the MNIST dataset using torchvision.datasets?

You can load MNIST by calling torchvision.datasets.MNIST with parameters like root (folder to save data), train (True for training set), and download=True to get the data automatically.

mnist_train = torchvision.datasets.MNIST(root='./data', train=True, download=True)

beginner

What is the role of the transform parameter in torchvision.datasets?

The transform parameter lets you apply data changes like converting images to tensors or normalizing pixel values. This helps prepare data for training your model.

beginner

Name three popular datasets available in torchvision.datasets.

Three popular datasets are:

• MNIST - handwritten digits
• CIFAR-10 - small color images in 10 classes
• FashionMNIST - grayscale clothing images in 10 classes

beginner

How can you access the labels and images from a dataset loaded with torchvision.datasets?

Each dataset object acts like a list of (image, label) pairs. You can get one sample by indexing, for example dataset[0] returns the first image and its label.

Which parameter in torchvision.datasets.MNIST downloads the dataset if not present?

A train=True

B download=True

C transform=True

D root=True

The download=True parameter tells PyTorch to download the dataset if it is not already in the specified root folder.

What type of data does torchvision.datasets.CIFAR10 provide?

A Small color images in 10 classes

B Text documents

C Grayscale handwritten digits

D Audio clips

CIFAR-10 contains small 32x32 color images divided into 10 different classes like airplanes, cars, and animals.

What does the transform argument usually do in torchvision.datasets?

A Applies data preprocessing like converting images to tensors

B Splits dataset into train and test

C Downloads the dataset

D Changes the dataset size

The transform argument applies preprocessing steps such as converting images to tensors or normalizing pixel values.

How do you get the label of the first image in a dataset loaded with torchvision.datasets?

A dataset[1][0]

B dataset.label(0)

C dataset.get_label(0)

D dataset[0][1]

Each dataset item is a tuple (image, label). So dataset[0][1] accesses the label of the first image.

Which of these datasets is NOT part of torchvision.datasets?

A COCO Captioning

B CIFAR-10

C ImageNet

D MNIST

ImageNet is not a built-in dataset class in torchvision.datasets; it requires manual download and is typically loaded using ImageFolder.

Explain how to load and prepare the MNIST dataset using torchvision.datasets for training a model.

Think about how you get the data, prepare it, and then use it in training.

Describe the purpose of the transform parameter in torchvision.datasets and give an example of a common transform.

Consider what you need to do to raw images before feeding them to a model.