/torchdistill

PyTorch-based modular, configuration-driven framework for knowledge distillation. 🏆18 methods including SOTA are implemented so far. 🎁 Trained models, training logs and configurations are available for ensuring the reproducibiliy.

Primary LanguagePythonMIT LicenseMIT

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

PyPI version Build Status

torchdistill (formerly kdkit) offers various knowledge distillation methods and enables you to design (new) experiments simply by editing a yaml file instead of Python code. Even when you need to extract intermediate representations in teacher/student models, you will NOT need to reimplement the models, that often change the interface of the forward, but instead specify the module path(s) in the yaml file.

Forward hook manager

Using ForwardHookManager, you can extract intermediate representations in model without modifying the interface of its forward function.
This example notebook will give you a better idea of the usage.

Top-1 validation accuracy for ILSVRC 2012 (ImageNet)

T: ResNet-34* Pretrained KD AT FT CRD Tf-KD SSKD L2 PAD-L2
S: ResNet-18 69.76* 71.37 70.90 70.45 70.93 70.52 70.09 71.08 71.71
Original work N/A N/A 70.70 N/A** 71.17 70.42 71.62 70.90 71.71

* The pretrained ResNet-34 and ResNet-18 are provided by torchvision.
** FT is assessed with ILSVRC 2015 in the original work.
For the 2nd row (S: ResNet-18), the checkpoint (trained weights), configuration and log files are available, and the configurations reuse the hyperparameters such as number of epochs used in the original work except for KD.

Examples

Executable code can be found in examples/ such as

Citation

[Preprint]

@article{matsubara2020torchdistill,
  title={torchdistill: A Modular, Configuration-Driven Framework for Knowledge Distillation},
  author={Matsubara, Yoshitomo},
  year={2020}
  eprint={2011.12913},
  archivePrefix={arXiv},
  primaryClass={cs.LG}
}

How to setup

  • Python 3.6 >=
  • pipenv (optional)

Install by pip/pipenv

pip3 install torchdistill
# or use pipenv
pipenv install torchdistill

Install from this repository

git clone https://github.com/yoshitomo-matsubara/torchdistill.git
cd torchdistill/
pip3 install -e .
# or use pipenv
pipenv install "-e ."

Issues / Contact

The documentation is work-in-progress. In the meantime, feel free to create an issue if you have a feature request or email me ( yoshitom@uci.edu ) if you would like to ask me in private.

References