PyTorchVideo: A Deep Learning Library for Video Understanding

We introduce PyTorchVideo, an open-source deep-learning library that provides a rich set of modular, efficient, and reproducible components for a variety of video understanding tasks, including classification, detection, self-supervised learning, and low-level processing. The library covers a full s...

Full description

Saved in:
Bibliographic Details
Published in:arXiv.org 2021-11
Main Authors: Fan, Haoqi, Murrell, Tullie, Wang, Heng, Kalyan Vasudev Alwala, Li, Yanghao, Li, Yilei, Xiong, Bo, Nikhila Ravi, Li, Meng, Yang, Haichuan, Malik, Jitendra, Girshick, Ross, Feiszli, Matt, Adcock, Aaron, Wan-Yen, Lo, Feichtenhofer, Christoph
Format: Article
Language:English
Subjects:
Deep learning
Electronic devices
Libraries
Machine learning
Video data
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:We introduce PyTorchVideo, an open-source deep-learning library that provides a rich set of modular, efficient, and reproducible components for a variety of video understanding tasks, including classification, detection, self-supervised learning, and low-level processing. The library covers a full stack of video understanding tools including multimodal data loading, transformations, and models that reproduce state-of-the-art performance. PyTorchVideo further supports hardware acceleration that enables real-time inference on mobile devices. The library is based on PyTorch and can be used by any training framework; for example, PyTorchLightning, PySlowFast, or Classy Vision. PyTorchVideo is available at https://pytorchvideo.org/
ISSN:2331-8422