Summary: Tensors in PyTorch can represent various types of data like images, words, and numbers. You can easily create, manipulate, and gather information from tensors in PyTorch. PyTorch allows for seamless interaction with NumPy arrays and provides tools for working with different tensor datatypes.
You can tell the number of dimensions a tensor in PyTorch has by the number of square brackets on the outside ([) and you only need to count one side. (View Highlight)
Another important concept for tensors is their shape attribute. The shape tells you how the elements inside them are arranged. (View Highlight)
