KD-Lib: A PyTorch library for Knowledge Distillation, Pruning and Quantization

In recent years, the growing size of neural networks has led to a vast amount of research concerning compression techniques to mitigate the drawbacks of such large sizes. Most of these research works can be categorized into three broad families : Knowledge Distillation, Pruning, and Quantization. Wh...

Full description

Saved in:
Bibliographic Details
Published inarXiv.org
Main Authors Shah, Het, Khare, Avishree, Shah, Neelay, Siddiqui, Khizir
Format Paper
LanguageEnglish
Published Ithaca Cornell University Library, arXiv.org 30.11.2020
Subjects
Algorithms
Distillation
Libraries
Measurement
Neural networks
Online AccessGet full text

Cover

More Information
Summary:In recent years, the growing size of neural networks has led to a vast amount of research concerning compression techniques to mitigate the drawbacks of such large sizes. Most of these research works can be categorized into three broad families : Knowledge Distillation, Pruning, and Quantization. While there has been steady research in this domain, adoption and commercial usage of the proposed techniques has not quite progressed at the rate. We present KD-Lib, an open-source PyTorch based library, which contains state-of-the-art modular implementations of algorithms from the three families on top of multiple abstraction layers. KD-Lib is model and algorithm-agnostic, with extended support for hyperparameter tuning using Optuna and Tensorboard for logging and monitoring. The library can be found at - https://github.com/SforAiDl/KD_Lib.
ISSN:2331-8422