Working with PyTorch Tensors

PyTorch is a popular,open source,optimized tensor library widely used in deep learning and AI Research, developed by a group of researchers at Facebook AI. The torch package contains data structures for multi-dimensional tensors and mathematical operations over these are defined.

Here, we seek to cover some useful functions that the torch package provides for manipulating tensors.

TORCH.CAT- Concatenates the given sequence of tensors in the given dimension
TORCH.UNBIND- Removes a tensor dimension
TORCH.MOVEDIM- Moves the dimension(s) of input at the position(s) in source to the position(s) in destination
TORCH.SQUEEZE- Returns a tensor with all the dimensions of input of size 1 removed.
TORCH.UNSQUEEZE- Returns a new tensor with a dimension of size one inserted at the specified position.

Before we begin, let's install and import PyTorch

# Import torch and other required modules
import torch

FUNCTION 1- TORCH.CAT

torch.cat(tensors, dim=0, *, out=None)

Concatenates the given sequence of tensors in the given dimension.
All tensors must either have the same shape (except in the concatenating dimension) or be empty.

The argument tensors denotes the sequence of tensors to be concatenated

dim is an optional argument that specifies the dimension along which we want tensors to be concatenated (default dim=0)

out is an optional keyword argument

# Example 1
ip_tensor_1=torch.tensor([[1,2,3],[4,5,6]])
ip_tensor_2=torch.tensor([[7,8,9],[10,11,12]])

torch.cat((ip_tensor_1,ip_tensor_2),dim=0)

tensor([[ 1,  2,  3],
        [ 4,  5,  6],
        [ 7,  8,  9],
        [10, 11, 12]])

As we specified dim=0 the input tensors have been concatenated along dimension 0.

The input tensors each had shape (2,3) and as the tensors were concatenated along dimension 0, the output tensor is of shape (4,3)