Intoduction to Pytorch Tensors

Tensor and its function

PyTorch is a Python-based scientific computing package that uses the power of graphics processing units. It is also one of the preferred deep learning research platforms built to provide maximum flexibility and speed. Here are few tensor functions discussed

torch.new_tensor
torch.new_empty
torch.bitwise_not
torch.clamp
torch.div()

# Import torch and other required modules
import torch

Function 1 - torch.new_tensor

Replaces a tensor with a new tensor

# Example 1
data = torch.tensor([[1, 2], [3, 4.]])
new_data = [[[1, 2, 3],[3, 4, 5]],[[6, 7, 8],[8, 9, 10]]]
data.new_tensor(new_data)

tensor([[[ 1.,  2.,  3.],
         [ 3.,  4.,  5.]],

        [[ 6.,  7.,  8.],
         [ 8.,  9., 10.]]])

Here a 2 dimentional matrix tensor is replacdd with a 3-d array. The original datatype is preserved