Live briefing
Everything about PyTorch
Deep learning library
PyTorch is an open-source deep learning library, originally developed by Meta Platforms and currently developed with support from the Linux Foundation. The successor to Torch, PyTorch provides a high-level API that builds upon optimised, low-level implementations of deep learning algorithms and architectures, such as the Transformer, or SGD. Notably, this API simplifies model training and inference to a few lines of code. PyTorch allows for automatic parallelization of training and, internally, implements CUDA bindings that speed training further by leveraging GPU resources. Wikipedia →
🧭 Start here: a 6-step reading path
- Read the overview: PyTorchA 5-minute orientation
- Skim a recent paper: Analysis of the Application Efficiency of TensorFlow and PyTorch in Convolutional Neural NetworkInfluential work since 2022
- Pick up a classic book: Deep Learning for Coders with fastai and PytorchThe most-reprinted book on the subject
- Read the landmark paper: PyTorch distributedCited 496 times
- Go sideways: Comparison of deep learning softwareA closely related topic
- Go sideways: CuPyA closely related topic
📖 Definitions
No dictionary entry for this exact phrase.
🗂️ The subject at a glance
🏆 Landmark papers (most cited)
PyTorch distributed
TorchANI: A Free and Open Source PyTorch-Based Deep Learning Implementation of the ANI Neural Network Potentials
PyTorch FSDP: Experiences on Scaling Fully Sharded Data Parallel
TorchMetrics - Measuring Reproducibility in PyTorch
Auto-Pytorch: Multi-Fidelity MetaLearning for Efficient and Robust AutoDL
Selene: a PyTorch-based deep learning library for sequence data
Foolbox Native: Fast adversarial attacks to benchmark the robustness of machine learning models in PyTorch, TensorFlow, and JAX
REANN: A PyTorch-based end-to-end multi-functional deep neural network package for molecular, reactive, and periodic systems
🆕 Influential since 2022
Analysis of the Application Efficiency of TensorFlow and PyTorch in Convolutional Neural Network
Evaluation of gene expression programming and artificial neural networks in PyTorch for the prediction of local scour depth around a bridge pier
AdaPT: Fast Emulation of Approximate DNN Accelerators in PyTorch
magnum.np: a PyTorch based GPU enhanced finite difference micromagnetic simulation framework for high level development and inverse design
Pytorch Image Quality: Metrics for Image Quality Assessment
📚 Books worth reading
Deep Learning for Coders with fastai and PytorchJeremy Howard, Sylvain Gugger · 2020
Mastering PytorchAshish Ranjan Jha, Gopinath Pillai · 2021
Modern Computer Vision with PytorchV. Kishore Ayyadevara, Yeshwanth Reddy · 2020
Transformers for Natural Language ProcessingDenis Rothman · 2021
Modern Time Series Forecasting with PythonManu Joseph · 2022- 📕Python Deep LearningDonald R. Brewer · 2022
Machine Learning with Pytorch and Scikit-LearnSebastian Raschka, Yuxi (Hayden) Liu · 2022
Hands-On Machine Learning with Scikit-Learn and PyTorchAurélien Géron · 2025
Ranked by number of editions on Open Library, a rough measure of how lasting a book is.
🔗 Related topics
- Comparison of deep learning software The following tables compare notable software frameworks, libraries, and computer programs for deep learning applications. Licenses here are a summary…
- CuPy CuPy is an open source library for GPU-accelerated computing with Python programming language, providing support for multi-dimensional arrays, sparse matrices…
- Torch (machine learning) Torch is an open-source machine learning library, a scientific computing framework, and a scripting language based on Lua. It provides LuaJIT interfaces…
- Open Neural Network Exchange The Open Neural Network Exchange (ONNX) [ˈɒnɪks] is an open-source artificial intelligence ecosystem of technology companies and research organizations…
- Outline of deep learning The following outline is provided as an overview of, and topical guide to, deep learning: Deep learning is a subfield of machine learning and artificial…
- Triton (programming language) Triton is an open-source domain-specific language and compiler for writing compute kernels for graphics processing units (GPUs). Triton is used in deep…
- Horovod (machine learning) Horovod is a free and open-source distributed deep learning training framework for TensorFlow, Keras, PyTorch and Apache MXNet. It is designed to scale…
- Chainer Chainer is an open source deep learning framework written purely in Python on top of NumPy and CuPy Python libraries. The development is led by Japanese…