What is PyTorch?

PyTorch is a deep learning library developed by Facebook.

What is PyTorch?

PyTorch is one of the most widely used libraries for deep learning. It offers three things:

Tensor: a multi-dimensional array like a NumPy array that can also run on the GPU.
Autograd: a system that automatically computes the derivatives of the operations performed.
nn: a toolbox of layers, loss functions and optimisers.

import torch
x = torch.tensor([1.0, 2.0, 3.0])
print(x * 2)          # tensor([2., 4., 6.])
print(x.sum().item()) # 6.0

Code runs line by line (eager); debugging is like ordinary Python.

item() and tolist()

To go from tensors to ordinary Python values, item() (single-element tensor) and tolist() (any shape) are used. They are handy when printing and saving outputs:

t = torch.tensor([[1, 2], [3, 4]])
print(t.sum().item())   # 10   (Python int)
print(t.tolist())       # [[1, 2], [3, 4]]
print(t.max().item())   # 4

On a multi-element tensor, item() raises an error.

Exercise First tensor

Create torch.tensor([[1, 2, 3], [4, 5, 6]]). Print it multiplied by 10 with tolist(), then the sum of all elements with item().

Show example solution

import torch

t = torch.tensor([[1, 2, 3], [4, 5, 6]])
print((t * 10).tolist())
print(t.sum().item())

Test yourself

What are the two key features that set PyTorch apart from NumPy?
- Shorter code and coloured output
- Reading tables and plotting
- There is no difference
- GPU support and automatic differentiation
Show answer

GPU support and automatic differentiation — Tensors can be moved to the GPU and autograd computes gradients by itself.
Turn a single-element tensor into a Python number.
```
toplam = t.sum().____()
```
Show answer
```
toplam = t.sum().item()
```
Match the concepts.

torch.tensor

Multi-dimensional array
autograd

Automatic differentiation
torch.nn

Layers and losses
tolist()

To a Python list

Next lesson: Tensor

We Are Enhancing Your Experience

Cookie Preferences

Strictly Necessary Cookies

Analytical Cookies