Deep learning· 2019
PyTorch: An Imperative Style, High-Performance Deep Learning Library
On the reading lists
- #71 in the Top 500 (2026 edition)
- #12 in Deep learning (2026 edition)
Why it matters
Popularized imperative, Pythonic deep learning with dynamic autograd and efficient accelerator execution.
Condensed from the expert lists' notes.
The record
- First released
- 2019 (from arXiv 1912.01703)
- Citations
- 56,399 citations, as counted by Papers With Code (CC BY-SA 4.0)
- Named by
- both expert lists
- Score
- 0.701 · computed rank 71 · consensus 0.85, must-read 1, citations percentile 0.988 (2010s · deep-learning), awards 0, existing lists 0. Method
Editor's notes
- Readability check: fail: A software library description; use the library instead. (AI draft (Claude), not yet reviewed, 2026-10-29)
Data sources
Catalogue data from OpenAlex (CC0), Crossref (CC0 metadata; no abstracts are shown), arXiv, and Papers With Code (CC BY-SA 4.0). Each count names its source. See the method.