Pytorch (Python) MCQ (Quiz) : W3Schools, Tutorials Point

1 .

________ is an open source machine learning library for Python and is completely based on Torch.

A)

Flask

B)

PyBrain

C)

PyTorch

D)

Python Selenium

Correct Answer : PyTorch

Explanation : PyTorch is an open source machine learning library for Python and is completely based on Torch.

2 .

Which company is developed by pytorch?

A)

Google AI Research lab (GAIR)

B)

Amazon AI Research lab (AAIR)

C)

Microsoft AI Research lab (MAIR)

D)

Facebook's AI Research lab (FAIR)

Correct Answer : Facebook's AI Research lab (FAIR)

Explanation : PyTorch is an open source machine learning library based on the Torch library, used for applications such as computer vision and natural language processing, primarily developed by Facebook's AI Research lab. It is free and open-source software released under the Modified BSD license.

3 .

Pytorch initial release date______

A)

September 2016

B)

November 2016

C)

March 2017

D)

December 2017

Correct Answer : September 2016

4 .

Who is the Original author of Pytorch?

A)

Adam Paszke

B)

Sam Gross

C)

Soumith Chintala and Gregory Chanan

D)

All of the above

Correct Answer : All of the above

5 .

The torch.cuda is a package which adds support for CUDA tensor type.

A)

TRUE

B)

FALSE

C)

Can be true or false

D)

Can not say

Correct Answer : TRUE

Explanation : True, The torch.cuda is a package which adds support for CUDA tensor type.

6 .

PyTorch is known for having _____ levels of abstraction.

A)

6

B)

5

C)

3

D)

2

Correct Answer : 3

Explanation :

Tensor : Tensor is an imperative n-dimensional array which runs on GPU.

Variable : It is a node in the computational graph. This stores data and gradient.

Module : Neural network layer will store state the otherwise learnable weight.

7 .

The Conv1d and Conv2D is used to apply 1D and 2D convolution.

A)

TRUE

B)

FALSE

C)

Can be true or false

D)

Can not say

Correct Answer : TRUE

8 .

Which of the following are the advantages of PyTorch?

A)

It includes lot of loss functions

B)

It includes many layers as Torch

C)

It is easy to debug and understand the code

D)

All of the above

Correct Answer : All of the above

9 .

_____ is an imperative n-dimensional array which runs on GPU.

A)

Module

B)

Tensor

C)

Variable

D)

All of the above

Correct Answer : Tensor

10 .

The activation functions are basically divided into ________ types.

A)

1

B)

2

C)

3

D)

4

Correct Answer : 2

Explanation : The activation functions are basically divided into two types: Linear Activation Function and Non-linear Activation Function

11 .

_____ is a package which is used to wrap a tensor.

A)

extend.variable

B)

auto.variable

C)

variable

D)

autograd.variable

Correct Answer : variable

Explanation : Variable is a package which is used to wrap a tensor. The autograd.variable is the central class for the package.

12 .

________ is a technique or way to find the linear relation between the dependent variable and the independent variable by minimizing the distance.

A)

Linear Regression

B)

Bilinear Regression

C)

Discrete Regression

D)

All of the above

Correct Answer : Linear Regression

Explanation : Linear Regression is a technique or way to find the linear relation between the dependent variable and the independent variable by minimizing the distance.

13 .

MSE stands for ?

A)

Mean Simple Error

B)

Machine Squared Error

C)

Mean Squared Evaluate

D)

Mean Squared Error

Correct Answer : Mean Squared Error

Explanation : MSE stands for Mean Squared Error, which is used to create a criterion the measures the mean squared error between each element in an input x and target y.

14 .

How many Loss functions in pytorch?

A)

3

B)

4

C)

5

D)

6

Correct Answer : 3

Explanation :
* MSELoss stands for Mean Squared Error, which is used to create a criterion the measures the mean squared error between each element in an input x and target y.
* CTCLoss stands for Connectionist Temporal Classification Loss, which is used to calculate the loss between continuous time series and target sequence.
* BCELoss stands for Binary Cross Entropy is used to create a criterion to measures the Binary Cross Entropy between the target and the output.

15 .

How many types of pooling layers in pytorch?

A)

One

B)

Two

C)

Three

D)

Four

Correct Answer : Two

Explanation : Pooling layers provide an approach to down sampling feature maps by summarizing the presence of features in patches of the feature map. Two common pooling methods are average pooling and max pooling that summarize the average presence of a feature and the most activated presence of a feature respectively.

Pytorch MCQs with Answers