PyTorch

PyTorch

Original author(s)	Adam Paszke Sam Gross Soumith Chintala Gregory Chanan
Developer(s)	Facebook's AI Research lab (FAIR)
Initial release	September 2016; 5 years ago (2016-09)[1]
Stable release	1.10.0[2]  / 21 October 2021; 2 months ago (21 October 2021)
Repository	github.com/pytorch/pytorch
Written in	Python C++ CUDA
Operating system	Linux macOS Windows
Platform	IA-32, x86-64
Available in	English
Type	Library for machine learning and deep learning
License	BSD
Website	pytorch.org

PyTorch is an open source machine learning library based on the Torch library,^[3][4][5] used for applications such as computer vision and natural language processing,^[6] primarily developed by Facebook's AI Research lab (FAIR).^[7][8][9] It is 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.^[10]

A number of pieces of deep learning software are built on top of PyTorch, including Tesla Autopilot,^[11] Uber's Pyro,^[12] 's Transformers,^[13] PyTorch Lightning,^[14][15] and Catalyst.^[16][17]

PyTorch provides two high-level features:^[18]

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

History[]

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 Facebook and Microsoft in September 2017 for converting models between frameworks. Caffe2 was merged into PyTorch at the end of March 2018.^[19]

PyTorch tensors[]

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 supports various sub-types of Tensors.^[20]

Modules[]

Autograd module[]

PyTorch uses a method called automatic differentiation. A recorder records what operations have performed, and then it replays it backward to compute the gradients. This method is especially powerful when building neural networks to save time on one epoch by calculating differentiation of the parameters at the forward pass.

Optim module[]

torch.optim is a module that implements various optimization algorithms used for building neural networks. Most of the commonly used methods are already supported, so there is no need to build them from scratch.

nn module[]

PyTorch autograd makes it easy to define computational graphs and take gradients, but raw autograd can be a bit too low-level for defining complex neural networks. This is where the nn module can help.

Example[]

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

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

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

# Creation of a tensor and filling of a tensor with random numbers
b = torch.randn(2, 3, device=device, dtype=dtype)
print(b) # Output of tensor B
# Output: tensor([[ 0.7178, -0.8453, -1.3403],
#                  [ 1.3262,  1.1512, -1.7070]])

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

print(a.sum()) # Output of the sum of all elements in tensor A
# Output: tensor(-2.1540)

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

print(a.min()) # Output of the minimum value in tensor A
# Output: tensor(-1.7129)

See also[]

• Comparison of deep learning software
• Differentiable programming
• DeepSpeed
• Torch (machine learning)
• Tensor

References[]

External links[]

• Official website