Python Pytorch full() method

0 0 1 minute read

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.full() returns a tensor of size size filled with fill_value.

Syntax: torch.ones(size, fill_value, out=None)

Parameters:
size: a sequence of integers defining the shape of the output tensor
fill_value: the number to fill the output tensor with.
out (Tensor, optional): the output tensor

Return type: A tensor

Code #1:

# Importing the PyTorch library 
import torch 
  
  
# Applying the full function and 
# storing the resulting tensor in 'a' 
a = torch.full([3, 4], 3) 
print("a = ", a) 
  
b = torch.full([2, 5], 3.5) 
print("b = ", b) 

Output:

a =  tensor([[3., 3., 3., 3.],
        [3., 3., 3., 3.],
        [3., 3., 3., 3.]])
b =  tensor([[3.5000, 3.5000, 3.5000, 3.5000, 3.5000],
        [3.5000, 3.5000, 3.5000, 3.5000, 3.5000]])