Aarhus University Seal

Continual Inference: A Library for Efficient Online Inference with Deep Neural Networks in PyTorch

Research output: Contribution to book/anthology/report/proceedingArticle in proceedingsResearchpeer-review

We present Continual Inference, a Python library for implementing Continual Inference Networks (CINs), a class of Neural Networks designed for redundancy-free online inference. This paper offers a comprehensive introduction and guide to CINs and their implementation, as well as best-practices and code examples for composing basic modules into complex neural network architectures that perform online inference with an order of magnitude less floating-point operations than their non-CIN counterparts. Continual Inference provides drop-in replacements of PyTorch modules and is readily downloadable via the Python Package Index and at www.github.com/lukashedegaard/continual-inference.

Original languageEnglish
Title of host publicationComputer Vision – ECCV 2022 Workshops, Proceedings
EditorsLeonid Karlinsky, Tomer Michaeli, Ko Nishino
Number of pages14
Publication year2023
ISBN (print)9783031250811
Publication statusPublished - 2023
Event17th European Conference on Computer Vision, ECCV 2022 - Tel Aviv, Israel
Duration: 23 Oct 202227 Oct 2022


Conference17th European Conference on Computer Vision, ECCV 2022
ByTel Aviv
SeriesLecture Notes in Computer Science (LNCS)

Bibliographical note

Publisher Copyright:
© 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

    Research areas

  • Continual Inference Network, Deep Neural Network, Library, Online inference, Python, PyTorch

See relations at Aarhus University Citationformats

ID: 316015909