PyTorch
![]() | |
Original author(s) |
|
---|---|
Developer(s) | Meta AI |
Initial release | September 2016[1] |
Stable release | 2.4.0[2] ![]() |
Repository | github |
Written in | |
Operating system | |
Platform | IA-32,x86-64,ARM64 |
Available in | English |
Type | Libraryformachine learninganddeep learning |
License | BSD-3[3] |
Website | pytorch |
Part of a series on |
Machine learning anddata mining |
---|
PyTorchis amachine learninglibrarybased on theTorchlibrary,[4][5][6]used for applications such ascomputer visionandnatural language processing,[7]originally developed byMeta AIand now part of theLinux Foundationumbrella.[8][9][10][11]It is recognized as one of the two most popular machine learning libraries alongsideTensorFlow,offeringfree and open-source softwarereleased under themodified BSD license.Although thePythoninterface is more polished and the primary focus of development, PyTorch also has aC++interface.[12]
A number of pieces ofdeep learningsoftware are built on top of PyTorch, includingTesla 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 (likeNumPy) with strong acceleration viagraphics processing units(GPU)
- Deep neural networksbuilt on a tape-basedautomatic differentiationsystem
History
[edit]Meta (formerly known as Facebook) operates bothPyTorchandConvolutional 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 andMicrosoftin September 2017 for converting models between frameworks. Caffe2 was merged into PyTorch at the end of March 2018.[21]In September 2022, Meta announced thatPyTorchwould be governed by PyTorch Foundation, a newly created independent organization – a subsidiary ofLinux Foundation.[22]
PyTorch 2.0 was released on 15 March 2023.[23]
PyTorch tensors
[edit]PyTorch defines a class called Tensor (torch.Tensor
) to store and operate on homogeneous multidimensional rectangular arrays of numbers. PyTorch Tensors are similar toNumPyArrays, but can also be operated on aCUDA-capableNVIDIAGPU. PyTorch has also been developing support for other GPU platforms, for example, AMD'sROCm[24]and Apple'sMetal 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 inlinear algebra.Tensors in PyTorch are simply multi-dimensional arrays.
PyTorch neural networks
[edit]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 thetorch.nn
module and defining the sequence of operations in theforward()
function.
Example
[edit]The following program shows the low-level functionality of the library with a simple example
importtorch
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 providednn
module. A neural network with linear layers is defined in the example.
importtorch
fromtorchimportnn# Import the nn sub-module from PyTorch
classNeuralNetwork(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),
)
defforward(self,x):# This function defines the forward pass.
x=self.flatten(x)
logits=self.linear_relu_stack(x)
returnlogits
See also
[edit]References
[edit]- ^Chintala, Soumith (1 September 2016)."PyTorch Alpha-1 release".
- ^"Release 2.4.0".24 July 2024.Retrieved26 July2024.
- ^Claburn, Thomas (12 September 2022)."PyTorch gets lit under The Linux Foundation".The Register.
- ^Yegulalp, Serdar (19 January 2017)."Facebook brings GPU-powered machine learning to Python".InfoWorld.Retrieved11 December2017.
- ^Lorica, Ben (3 August 2017)."Why AI and machine learning researchers are beginning to embrace PyTorch".O'Reilly Media.Retrieved11 December2017.
- ^Ketkar, Nikhil (2017). "Introduction to PyTorch".Deep Learning with Python.Apress, Berkeley, CA. pp. 195–208.doi:10.1007/978-1-4842-2766-4_12.ISBN9781484227657.
- ^Moez Ali (Jun 2023)."NLP with PyTorch: A Comprehensive Guide".datacamp.Retrieved2024-04-01.
- ^Patel, Mo (2017-12-07)."When two trends fuse: PyTorch and recommender systems".O'Reilly Media.Retrieved2017-12-18.
- ^Mannes, John."Facebook and Microsoft collaborate to simplify conversions from PyTorch to Caffe2".TechCrunch.Retrieved2017-12-18.
FAIR is accustomed to working with PyTorch – a deep learning framework optimized for achieving state of the art results in research, regardless of resource constraints. Unfortunately in the real world, most of us are limited by the computational capabilities of our smartphones and computers.
- ^Arakelyan, Sophia (2017-11-29)."Tech giants are using open source frameworks to dominate the AI community".VentureBeat.Retrieved2017-12-18.
- ^"PyTorch strengthens its governance by joining the Linux Foundation".pytorch.org.Retrieved2022-09-13.
- ^"The C++ Frontend".PyTorch Master Documentation.Retrieved2019-07-29.
- ^Karpathy, Andrej."PyTorch at Tesla - Andrej Karpathy, Tesla".
- ^"Uber AI Labs Open Sources Pyro, a Deep Probabilistic Programming Language".Uber Engineering Blog.2017-11-03.Retrieved2017-12-18.
- ^PYTORCH-TRANSFORMERS: PyTorch implementations of popular NLP Transformers,PyTorch Hub, 2019-12-01,retrieved2019-12-01
- ^PYTORCH-Lightning: The lightweight PyTorch wrapper for ML researchers. Scale your models. Write less boilerplate,Lightning-Team, 2020-06-18,retrieved2020-06-18
- ^"Ecosystem Tools".pytorch.org.Retrieved2020-06-18.
- ^GitHub - catalyst-team/catalyst: Accelerated DL & RL,Catalyst-Team, 2019-12-05,retrieved2019-12-05
- ^"Ecosystem Tools".pytorch.org.Retrieved2020-04-04.
- ^"PyTorch – About".pytorch.org.Archived fromthe originalon 2018-06-15.Retrieved2018-06-11.
- ^"Caffe2 Merges With PyTorch".2018-04-02.
- ^Edwards, Benj (2022-09-12)."Meta spins off PyTorch Foundation to make AI framework vendor neutral".Ars Technica.
- ^"PyTorch 2.0 brings new fire to open-source machine learning".VentureBeat.15 March 2023.Retrieved16 March2023.
- ^"Installing PyTorch for ROCm".rocm.docs.amd.2024-02-09.
- ^"Introducing Accelerated PyTorch Training on Mac".pytorch.org.Retrieved2022-06-04.
- ^"An Introduction to PyTorch – A Simple yet Powerful Deep Learning Library".analyticsvidhya.2018-02-22.Retrieved2018-06-11.