Datasets in PyTorch QUIZ (MCQ QUESTIONS AND ANSWERS)

Total Correct: 0

Time:20:00

Question: 1

Which method can be used to download a specific built-in dataset in PyTorch if it is not already available locally?

download() method

fetch() method

torchvision.datasets.load()

torch.datasets.get()

Question: 2

What is the recommended approach for handling missing data in a custom PyTorch dataset?

Replace missing values with the mean of the dataset

Ignore samples with missing values

Impute missing values using a machine learning model

Assign a default value to missing data

Question: 3

How can you ensure reproducibility when working with PyTorch datasets and DataLoader?

Use the torch.set_seed() function

Set the learning rate to a fixed value

Increase the number of workers in the DataLoader

Use a larger batch size during training

Question: 4

In PyTorch, what does the term "epoch" refer to during model training?

A single forward pass of the neural network

The entire training dataset passed through the model once

The number of layers in the neural network

The learning rate at a specific iteration

Question: 5

What is the role of the torch.utils.data.ConcatDataset class in PyTorch?

Concatenating different datasets into a single dataset

Concatenating layers of a neural network

Concatenating data along the time axis

Concatenating batches during training

Question: 6

Which method can be used to visualize samples from a PyTorch DataLoader during debugging or exploration?

torch.show()

plt.imshow() from the matplotlib library

print()

torchvision.display()

Question: 7

What does the drop_last parameter in a PyTorch DataLoader control?

Dropping the last batch if it is incomplete

Dropping the last epoch during training

Ignoring the last sample in the dataset

Removing the last layer of the neural network

Question: 8

What is the purpose of the torch.utils.data.random_split function in PyTorch?

To randomly shuffle the dataset

To split the dataset into training and validation sets

To apply random transformations to the data

To create a DataLoader with random sampling

Question: 9

In PyTorch, how can you handle imbalanced classes in a custom dataset during training?

Use a larger learning rate for minority classes

Oversample the minority classes

Undersample the majority classes

Ignore the imbalances and let the model adapt

Question: 10

What is the primary purpose of the torchvision.transforms module when working with image datasets in PyTorch?

To define neural network architectures

To apply data augmentation and preprocessing transformations

To calculate loss functions

To create custom DataLoader objects

Question: 11

When should you consider creating a custom dataset instead of using built-in datasets in PyTorch?

For every machine learning project

When working with small, specific datasets

When using image classification tasks only

When computational resources are limited

Question: 12

Which of the following is a disadvantage of using a large batch_size in a DataLoader?

Faster convergence

Improved memory efficiency

Increased GPU memory usage

More accurate model predictions

Question: 13

What is the role of the num_workers parameter in a PyTorch DataLoader?

To specify the number of GPU devices

To set the learning rate

To control data shuffling

To determine the number of parallel data loading processes

Question: 14

Which PyTorch module is commonly used for computer vision tasks and includes various pre-trained models?

torch.nn

torch.optim

torch.utils.data

torchvision.models

Question: 15

What is the primary advantage of using a DataLoader in PyTorch during model training?

Efficient GPU utilization

Faster convergence

Automated hyperparameter tuning

Improved memory management

Question: 16

Why does PyTorch provide built-in datasets?

Showcase PyTorch's capabilities

Provide convenient access to common datasets for research

Replace custom datasets entirely

Facilitate communication between different frameworks

Question: 17

What is the primary use case for the CIFAR-100 dataset in PyTorch?

Image classification with 100 classes

Object detection in 100 images

Natural language processing tasks

Regression analysis on 100 features

Question: 18

Which of the following is NOT a built-in dataset available in PyTorch?

MNIST

CIFAR-100

ImageNet

TensorFlow MNIST

Question: 19

In PyTorch, what is a common technique used for data normalization during preprocessing?

Min-Max scaling

One-Hot encoding

Z-score normalization

Principal Component Analysis (PCA)

Question: 20

What is the purpose of setting the transform parameter in a PyTorch DataLoader?

To control the learning rate

To specify the number of epochs

To apply data augmentation and preprocessing

To determine the loss function

Question: 21

When creating a custom PyTorch dataset, what should be used to load and process the data within the getitem method?

pandas library

numpy library

Image processing libraries (e.g., PIL)

All of the above

Question: 22

What does data shuffling in a DataLoader help prevent during training?

Overfitting

Model convergence

Data leakage

Stuck in local minima

Question: 23

In PyTorch, what is the role of a DataLoader when working with datasets?

Data augmentation

Model training

GPU acceleration

Data shuffling and batching

Question: 24

What is the purpose of the len method in a custom PyTorch dataset?

To define the length of the dataset

To specify the number of features in each sample

To control data augmentation techniques

To set the learning rate during training

Question: 25

What method must be implemented when creating a custom dataset in PyTorch?

__init__

__len__

__getitem__

__load__

Question: 26

Which class should you inherit from when creating a custom dataset in PyTorch?

torch.Dataset

torch.BaseDataset

torch.CustomDataset

torch.DataLoader

Question: 27

What is a key advantage of creating custom datasets in PyTorch?

Improved efficiency

Greater control over data preprocessing

Faster training times

Automatic data augmentation

Question: 28

How can you check the size of a specific built-in dataset in PyTorch?

Use the torch.info() function

Check the dataset's documentation

Use the len() function on the dataset

Print the dataset object

Question: 29

What is the advantage of using built-in datasets in PyTorch?

They are more efficient than custom datasets

They are pre-trained on large datasets

They provide a standardized way to access common datasets

They are exclusive to PyTorch and not available in other frameworks

Question: 30

Which module in PyTorch is commonly used for handling built-in datasets?

torch.data

torch.datasets

torch.utils

torch.loader