Open Source Software

Summary

Open source software (OSS) is an essential component of our research activities. I open issues and submit pull requests for existing OSSes. To boost my research, I also develop and open-source (mostly machine learning) frameworks. I hope would be useful for the research community too.

Author

torchdistill: A Modular, Configuration-Driven Framework for Knowledge Distillation (PyTorch Ecosystem)
sc2bench: Supervised Compression for Split Computing

Contributor

pytorch/torchvision: Datasets, Transforms and Models specific to Computer Vision
huggingface/transformers: Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models, for both inference and training
huggingface/datasets: The largest hub of ready-to-use datasets for AI models with fast, easy-to-use and efficient data manipulation tools
openreview/openreview-py: Official Python client library for the OpenReview API

Related Publications

torchdistill Meets Hugging Face Libraries for Reproducible, Coding-Free Deep Learning Studies: A Case Study on NLP

EMNLP 2023 Workshop for Natural Language Processing Open Source Software (NLP-OSS)

Yoshitomo Matsubara

This work was done prior to joining Amazon.

Paper OpenReview Preprint Code PyPI

SC2 Benchmark: Supervised Compression for Split Computing

Transactions on Machine Learning Research (TMLR)

Yoshitomo Matsubara, Ruihan Yang, Marco Levorato, Stephan Mandt

This work was done prior to joining Amazon.

OpenReview Video Preprint Code PyPI

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

ICPR 2020 Workshop on Reproducible Research in Pattern Recognition (RRPR)

Yoshitomo Matsubara

Paper Preprint Code PyPI