Skip to content
Related Articles

Related Articles

Improve Article
Save Article
Like Article

How to Convert Pytorch tensor to Numpy array?

  • Last Updated : 30 Jun, 2021

In this article, we are going to convert Pytorch tensor to NumPy array.

Method 1: Using numpy().

 Attention geek! Strengthen your foundations with the Python Programming Foundation Course and learn the basics.  

To begin with, your interview preparations Enhance your Data Structures concepts with the Python DS Course. And to begin with your Machine Learning Journey, join the Machine Learning - Basic Level Course

Syntax: tensor_name.numpy()



Example 1: Converting one-dimensional a tensor to NumPy array

Python3




# importing torch module
import torch
  
# import numpy module
import numpy
  
# create one dimensional tensor with
# float type elements
b = torch.tensor([10.12, 20.56, 30.00, 40.3, 50.4])
  
print(b)
  
# convert this into numpy array using
# numpy() method
b = b.numpy()
  
# display
b

Output:

tensor([10.1200, 20.5600, 30.0000, 40.3000, 50.4000])
array([10.12, 20.56, 30.  , 40.3 , 50.4 ], dtype=float32)

Example 2: Converting two-dimensional tensors to NumPy array

Python3




# importing torch module
import torch
  
# import numpy module
import numpy
  
# create two dimensional tensor with
# integer type elements
b = torch.tensor([[1, 2, 3, 4, 5], [3, 4, 5, 6, 7], 
                  [4, 5, 6, 7, 8]])
  
print(b)
  
# convert this into numpy array using
# numpy() method
b = b.numpy()
  
# display
b

Output:

tensor([[1, 2, 3, 4, 5],
       [3, 4, 5, 6, 7],
       [4, 5, 6, 7, 8]])
array([[1, 2, 3, 4, 5],
      [3, 4, 5, 6, 7],
      [4, 5, 6, 7, 8]])

Method 2: Using numpy.array() method.

This is also used to convert a tensor into NumPy array.

Syntax: numpy.array(tensor_name)

Example: Converting two-dimensional tensor to NumPy array

Python3




# importing torch module
import torch
  
# import numpy module
import numpy
  
# create two dimensional tensor with 
# integer type elements
b = torch.tensor([[1, 2, 3, 4, 5], [3, 4, 5, 6, 7], 
                  [4, 5, 6, 7, 8]])
  
print(b)
  
# convert this into numpy array using 
# numpy.array() method
b = numpy.array(b)
  
# display
b

Output:

tensor([[1, 2, 3, 4, 5],
       [3, 4, 5, 6, 7],
       [4, 5, 6, 7, 8]])
array([[1, 2, 3, 4, 5],
      [3, 4, 5, 6, 7],
      [4, 5, 6, 7, 8]])



My Personal Notes arrow_drop_up
Recommended Articles
Page :