Skip to content
Related Articles
Get the best out of our app
GeeksforGeeks App
Open App

Related Articles

Python Pytorch arrange() method

Improve Article
Save Article
Like Article
Improve Article
Save Article
Like Article

PyTorch is an open-source machine learning library developed by Facebook. It is used for deep neural network and natural language processing purposes.
The function torch.arrange() returns a 1-D tensor of size \left\lceil \frac{\text{end} - \text{start}}{\text{step}} \right\rceil
with values from the interval [start, end)  taken with common difference step beginning from start. 
out_{i+1} = out_i + step

Syntax: torch.arrange(start=0, end, step=1, out=None)
start: the starting value for the set of points. Default: 0. 
end: the ending value for the set of points 
step: the gap between each pair of adjacent points. Default: 1. 
out(Tensor, optional): the output tensor
Return type: A tensor 

Code #1: 


# Importing the PyTorch library
import torch
# Applying the arrange function and
# storing the resulting tensor in 't'
a = torch.arrange(3)
print("a = ", a)
b = torch.arrange(1, 6)
print("b = ", b)
c = torch.arrange(1, 5, 0.5)
print("c = ", c)


a =  tensor([0, 1, 2])
b =  tensor([1, 2, 3, 4, 5])
c =  tensor([1.0000, 1.5000, 2.0000, 2.5000, 3.0000, 3.5000, 4.0000, 4.5000])

 Note that the non-integer step is subject to floating-point rounding errors when comparing against end; to avoid inconsistency, we advise adding a small epsilon to the end in such cases.

My Personal Notes arrow_drop_up
Last Updated : 05 Aug, 2021
Like Article
Save Article
Similar Reads
Related Tutorials