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.

Practice

1. What is the main purpose of using torchvision.datasets in PyTorch?

easy

A. To visualize model training progress

B. To create custom neural network layers

C. To easily download and load popular image datasets

D. To optimize model hyperparameters automatically

Solution

1. Step 1: Understand the role of torchvision.datasets

   It provides built-in access to popular image datasets like CIFAR10, MNIST, etc., handling download and loading.

2. Step 2: Compare with other options

   Options A, B, and D relate to different PyTorch functionalities, not dataset loading.

3. Final Answer:

   To easily download and load popular image datasets -> Option C

4. Quick Check:

   torchvision.datasets = dataset loading [OK]

Hint: Remember: torchvision.datasets = easy dataset access [OK]

Common Mistakes:

• Confusing datasets with model layers
• Thinking it handles training visualization
• Assuming it tunes hyperparameters

2. Which of the following is the correct way to import the CIFAR10 dataset from torchvision?

easy

A. from torchvision.datasets import CIFAR10

B. import torchvision.datasets.CIFAR10

C. from torchvision import CIFAR10

D. import CIFAR10 from torchvision.datasets

Solution

1. Step 1: Recall Python import syntax for modules and classes

   The correct syntax to import a class from a module is: from module import Class.

2. Step 2: Apply to torchvision.datasets and CIFAR10

   So, from torchvision.datasets import CIFAR10 is correct. Other options have syntax errors or wrong order.

3. Final Answer:

   from torchvision.datasets import CIFAR10 -> Option A

4. Quick Check:

   Correct import syntax = from torchvision.datasets import CIFAR10 [OK]

Hint: Use 'from module import Class' for dataset imports [OK]

Common Mistakes:

• Using dot notation in import statement incorrectly
• Swapping import order
• Trying to import dataset directly without module

3. What will be the output shape of images loaded from the MNIST dataset using torchvision.datasets with default settings?

medium

A. (28, 28)

B. (1, 28, 28)

C. (3, 28, 28)

D. (32, 32, 3)

Solution

1. Step 1: Recall MNIST image format

   MNIST images are grayscale with size 28x28 pixels.

2. Step 2: Understand PyTorch tensor shape for images

   PyTorch uses channel-first format: (channels, height, width). Grayscale images have 1 channel, so shape is (1, 28, 28).

3. Final Answer:

   (1, 28, 28) -> Option B

4. Quick Check:

   MNIST images = grayscale 28x28 = (1,28,28) [OK]

Hint: PyTorch images: channels first, grayscale = 1 channel [OK]

Common Mistakes:

• Assuming shape is height x width only
• Confusing RGB (3 channels) with grayscale
• Using (28, 28) without channel dimension

4. Consider this code snippet:

from torchvision.datasets import CIFAR10
train_data = CIFAR10(root='./data', train=True, download=True)
print(len(train_data))

What error will occur if download=True is omitted and data is not already downloaded?

medium

A. SyntaxError: Missing download argument

B. No error, data loads automatically

C. FileNotFoundError: No such file or directory

D. RuntimeError: Dataset not found and download=False

Solution

1. Step 1: Understand CIFAR10 dataset download behavior

   If download=False (default) and data is missing, it raises an error because it won't download automatically.

2. Step 2: Identify the error type

   The error raised is a RuntimeError indicating dataset not found and download flag is False.

3. Final Answer:

   RuntimeError: Dataset not found and download=False -> Option D

4. Quick Check:

   Missing data + download=False = RuntimeError [OK]

Hint: Always set download=True first time to avoid RuntimeError [OK]

Common Mistakes:

• Expecting automatic download without flag
• Confusing RuntimeError with SyntaxError
• Assuming FileNotFoundError is raised

5. You want to load the CIFAR10 training dataset with images normalized to mean=0.5 and std=0.5 for each RGB channel. Which code snippet correctly applies this transform using torchvision?

hard

A. from torchvision.datasets import CIFAR10
from torchvision.transforms import Compose, ToTensor, Normalize
transform = Compose([ToTensor(), Normalize((0.5,0.5,0.5), (0.5,0.5,0.5))])
data = CIFAR10(root='./data', train=True, download=True, transform=transform)

B. from torchvision.datasets import CIFAR10
transform = Normalize((0.5,0.5,0.5), (0.5,0.5,0.5))
data = CIFAR10(root='./data', train=True, download=True, transform=transform)

C. from torchvision.datasets import CIFAR10
from torchvision.transforms import ToTensor
transform = ToTensor()
data = CIFAR10(root='./data', train=True, download=True, transform=transform)
data = Normalize((0.5,0.5,0.5), (0.5,0.5,0.5))

D. from torchvision.datasets import CIFAR10
from torchvision.transforms import Compose, Normalize
transform = Compose([Normalize((0.5,0.5,0.5), (0.5,0.5,0.5))])
data = CIFAR10(root='./data', train=True, download=True, transform=transform)

Solution

1. Step 1: Understand required transforms for normalization

   Images must first be converted to tensors with ToTensor() before normalization.

2. Step 2: Check transform composition

   Use Compose to chain ToTensor() and Normalize() in order.

3. Step 3: Verify each option

   from torchvision.datasets import CIFAR10 from torchvision.transforms import Compose, ToTensor, Normalize transform = Compose([ToTensor(), Normalize((0.5,0.5,0.5), (0.5,0.5,0.5))]) data = CIFAR10(root='./data', train=True, download=True, transform=transform) correctly composes both transforms and passes to dataset. Others miss ToTensor() or apply transforms incorrectly.

4. Final Answer:

   Option A code snippet with Compose, ToTensor, Normalize -> Option A

5. Quick Check:

   Normalize after ToTensor using Compose = from torchvision.datasets import CIFAR10 from torchvision.transforms import Compose, ToTensor, Normalize transform = Compose([ToTensor(), Normalize((0.5,0.5,0.5), (0.5,0.5,0.5))]) data = CIFAR10(root='./data', train=True, download=True, transform=transform) [OK]

Hint: Always use ToTensor before Normalize in Compose [OK]

Common Mistakes:

• Applying Normalize without ToTensor first
• Not using Compose to chain transforms
• Applying transforms outside dataset argument