|Original author(s)||Adam Paszke, Sam Gross, Soumith Chintala, Gregory Chanan|
|Initial release||October 2016|
1.3.0 / 10 October 2019
|Written in||Python, C++, CUDA|
|Operating system||Linux, macOS, Windows|
|Type||Library for machine learning and deep learning|
PyTorch is an open source machine learning library based on the Torch library, used for applications such as computer vision and natural language processing. It is primarily developed by Facebook's artificial intelligence research group. 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++ frontend. Furthermore, Uber's Pyro probabilistic programming language software uses PyTorch as a backend.
PyTorch provides two high-level features:
- Tensor computing (like NumPy) with strong acceleration via graphics processing units (GPU)
- Deep neural networks built on a tape-based autodiff system
Facebook operated 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.
Tensors, while from mathematics, are different in programming, where they can be treated as multidimensional array data structures (arrays). Tensors in PyTorch are similar to NumPy arrays, but can also be operated on a CUDA-capable Nvidia GPU. PyTorch supports various types of tensors.
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.
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.
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.
- Yegulalp, Serdar (19 January 2017). "Facebook brings GPU-powered machine learning to Python". InfoWorld. Retrieved 11 December 2017.
- Lorica, Ben (3 August 2017). "Why AI and machine learning researchers are beginning to embrace PyTorch". O'Reilly Media. Retrieved 11 December 2017.
- 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. ISBN 9781484227657.
- "Natural Language Processing (NLP) with PyTorch – NLP with PyTorch documentation". dl4nlp.info. Retrieved 2017-12-18.
- Patel, Mo (2017-12-07). "When two trends fuse: PyTorch and recommender systems". O'Reilly Media. Retrieved 2017-12-18.
- Mannes, John. "Facebook and Microsoft collaborate to simplify conversions from PyTorch to Caffe2". TechCrunch. Retrieved 2017-12-18.
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. Retrieved 2017-12-18.
- "The C++ Frontend". PyTorch Master Documentation. Retrieved 2019-07-29.
- "Uber AI Labs Open Sources Pyro, a Deep Probabilistic Programming Language". Uber Engineering Blog. 2017-11-03. Retrieved 2017-12-18.
- "PyTorch – About". pytorch.org. Archived from the original on 2018-06-15. Retrieved 2018-06-11.
- "Caffe2 Merges With PyTorch". 2018-04-02.
- "An Introduction to PyTorch – A Simple yet Powerful Deep Learning Library". analyticsvidhya.com. 2018-02-22. Retrieved 2018-06-11.
|This software article is a stub. You can help Wikipedia by expanding it.|