Learn practical skills, build real-world projects, and advance your career

5 functions of Torch Tensor

Those 5 next function creates a specific type of new tensors or they modify the values of the tensors with specific rules

-torch.new_full

-torch.new_empty

-torch.clamp

-torch.cos

-torch.div

# Import torch and other required modules
import torch

Function 1 - torch.newfull

Returns a tensor of a specific given size with a specific given value

# Example 1 - create a full tensor with an 2D array of size [3][3] with all values 2
tensor1 = torch.ones((2,), dtype=torch.float64)
tensor1=tensor1.new_full((3, 3), 2)
tensor1
tensor([[2., 2., 2.],
        [2., 2., 2.],
        [2., 2., 2.]], dtype=torch.float64)

It creates a full tensor with an 2D array of size [3][3] with all values 2