torchdistill: A Modular, Configuration-Driven Framework for Knowledge Distillation

TL;DR

torchdistill is an open-source, modular framework built on PyTorch that simplifies the design, reproduction, and experimentation of knowledge distillation methods through declarative configuration files, promoting reproducibility and extensibility.

Contribution

It introduces a highly generalized, maintainable framework for knowledge distillation that supports diverse methods, datasets, and experiments with declarative configurations.

Findings

Successfully reproduced state-of-the-art results on ImageNet and COCO datasets.

Demonstrated efficient training strategies and flexible experiment design.

Provided publicly available source code and models for community use.

Abstract

While knowledge distillation (transfer) has been attracting attentions from the research community, the recent development in the fields has heightened the need for reproducible studies and highly generalized frameworks to lower barriers to such high-quality, reproducible deep learning research. Several researchers voluntarily published frameworks used in their knowledge distillation studies to help other interested researchers reproduce their original work. Such frameworks, however, are usually neither well generalized nor maintained, thus researchers are still required to write a lot of code to refactor/build on the frameworks for introducing new methods, models, datasets and designing experiments. In this paper, we present our developed open-source framework built on PyTorch and dedicated for knowledge distillation studies. The framework is designed to enable users to design experiments by declarative PyYAML configuration files, and helps researchers complete the recently proposed ML Code Completeness Checklist. Using the developed framework, we demonstrate its various efficient training strategies, and implement a variety of knowledge distillation methods. We also reproduce some of their original experimental results on the ImageNet and COCO datasets presented at major machine learning conferences such as ICLR, NeurIPS, CVPR and ECCV, including recent state-of-the-art methods. All the source code, configurations, log files and trained model weights are publicly available at https://github.com/yoshitomo-matsubara/torchdistill .