PyTorch

Original author(s)	Adam Paszke Sam Gross Soumith Chintala Gregory Chanan
Developer(s)	Meta AI
Initial release	September 2016; 7 years ago (2016-09)[1]
Stable release	2.4.0[2]  / 24 July 2024; 17 days ago (24 July 2024)
Repository	github.com/pytorch/pytorch
Written in	Python C++ CUDA
Operating system	Linux macOS Windows
Platform	IA-32, x86-64, ARM64
Available in	English
Type	Library for machine learning and deep learning
License	BSD-3[3]
Website	pytorch.org

PyTorch is a machine learning library based on the Torch library,^[4][5][6] used for applications such as computer vision and natural language processing,^[7] originally developed by Meta AI and now part of the Linux Foundation umbrella.^{[8][9][10][11]} It is recognized as one of the two most popular machine learning libraries alongside TensorFlow, offering free and open-source software released under the modified BSD license. Although the Python interface is more polished and the primary focus of development, PyTorch also has a C++ interface.^[12]

A number of pieces of deep learning software are built on top of PyTorch, including Tesla Autopilot,^[13] Uber's Pyro,^[14] Hugging Face's Transformers,^[15] PyTorch Lightning,^[16][17] and Catalyst.^[18][19]

PyTorch provides two high-level features:^[20]

• Tensor computing (like NumPy) with strong acceleration via graphics processing units (GPU)
• Deep neural networks built on a tape-based automatic differentiation system

Meta (formerly known as Facebook) operates both PyTorch and Convolutional Architecture for Fast Feature Embedding (Caffe2), but models defined by the two frameworks were mutually incompatible. The Open Neural Network Exchange (ONNX) project was created by Meta and Microsoft in September 2017 for converting models between frameworks. Caffe2 was merged into PyTorch at the end of March 2018.^[21] In September 2022, Meta announced that PyTorch would be governed by PyTorch Foundation, a newly created independent organization – a subsidiary of Linux Foundation.^[22]

PyTorch 2.0 was released on 15 March 2023.^[23]

PyTorch defines a class called Tensor (torch.Tensor) to store and operate on homogeneous multidimensional rectangular arrays of numbers. PyTorch Tensors are similar to NumPy Arrays, but can also be operated on a CUDA-capable NVIDIA GPU. PyTorch has also been developing support for other GPU platforms, for example, AMD's ROCm^[24] and Apple's Metal Framework.^[25]

PyTorch supports various sub-types of Tensors.^[26]

Note that the term "tensor" here does not carry the same meaning as tensor in mathematics or physics. The meaning of the word in machine learning is only superficially related to its original meaning as a certain kind of object in linear algebra. Tensors in PyTorch are simply multi-dimensional arrays.

PyTorch defines a module called nn (torch.nn) to describe neural networks and to support training. This module offers a comprehensive collection of building blocks for neural networks, including various layers and activation functions, enabling the construction of complex models. Networks are built by inheriting from the torch.nn module and defining the sequence of operations in the forward() function.

The following program shows the low-level functionality of the library with a simple example

import torch
dtype = torch.float
device = torch.device("cpu")  # Execute all calculations on the CPU
# device = torch.device("cuda:0")  # Executes all calculations on the GPU

# Create a tensor and fill it with random numbers
a = torch.randn(2, 3, device=device, dtype=dtype)
print(a)
# Output: tensor([[-1.1884,  0.8498, -1.7129],
#                  [-0.8816,  0.1944,  0.5847]])

b = torch.randn(2, 3, device=device, dtype=dtype)
print(b)
# Output: tensor([[ 0.7178, -0.8453, -1.3403],
#                  [ 1.3262,  1.1512, -1.7070]])

print(a * b)
# Output: tensor([[-0.8530, -0.7183,  2.58],
#                  [-1.1692,  0.2238, -0.9981]])

print(a.sum()) 
# Output: tensor(-2.1540)

print(a[1,2]) # Output of the element in the third column of the second row (zero based)
# Output: tensor(0.5847)

print(a.max())
# Output: tensor(0.8498)

The following code-block shows an example of the higher level functionality provided nn module. A neural network with linear layers is defined in the example.

import torch
from torch import nn # Import the nn sub-module from PyTorch

class NeuralNetwork(nn.Module):  # Neural networks are defined as classes
    def __init__(self):  # Layers and variables are defined in the __init__ method
        super().__init__()  # Must be in every network.
        self.flatten = nn.Flatten()   # Construct a flattening layer.
        self.linear_relu_stack = nn.Sequential(  # Construct a stack of layers.
            nn.Linear(28*28, 512),  # Linear Layers have an input and output shape
            nn.ReLU(),  # ReLU is one of many activation functions provided by nn
            nn.Linear(512, 512),
            nn.ReLU(),
            nn.Linear(512, 10), 
        )

    def forward(self, x):  # This function defines the forward pass.
        x = self.flatten(x)
        logits = self.linear_relu_stack(x)
        return logits

• Comparison of deep learning software
• Differentiable programming
• DeepSpeed

• Official website