Need help with torchdistill?
Click the “chat” button below for chat support from the developer who created it, or find similar developers for support.

About the developer

422 Stars 41 Forks MIT License 878 Commits 5 Opened issues


A coding-free framework built on PyTorch for reproducible deep learning studies. 🏆20 knowledge distillation methods presented at CVPR, ICLR, ECCV, NeurIPS, ICCV, etc are implemented so far. 🎁 Trained models, training logs and configurations are available for ensuring the reproducibiliy and benchmark.

Services available


Need anything else?

Contributors list

# 73,990
750 commits
# 629,561
1 commit

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

PyPI version Build Status DOI:10.1007/978-3-030-76423-4_3

torchdistill (formerly kdkit) offers various state-of-the-art knowledge distillation methods and enables you to design (new) experiments simply by editing a declarative yaml config 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. Refer to this paper for more details.

In addition to knowledge distillation, this framework helps you design and perform general deep learning experiments (WITHOUT coding) for reproducible deep learning studies. i.e., it enables you to train models without teachers simply by excluding teacher entries from a declarative yaml config file. You can find such examples below and in configs/sample/.

Forward hook manager

Using ForwardHookManager, you can extract intermediate representations in model without modifying the interface of its forward function.
This example notebook Open In Colab will give you a better idea of the usage such as knowledge distillation and analysis of intermediate representations.

1 experiment → 1 declarative PyYAML config file

In torchdistill, many components and PyTorch modules are abstracted e.g., models, datasets, optimizers, losses, and more! You can define them in a declarative PyYAML config file so that can be seen as a summary of your experiment, and in many cases, you will NOT need to write Python code at all. Take a look at some configurations available in configs/. You'll see what modules are abstracted and how they are defined in a declarative PyYAML config file to design an experiment.

Top-1 validation accuracy for ILSVRC 2012 (ImageNet)

| T: ResNet-34* | Pretrained | KD | AT | FT | CRD | Tf-KD | SSKD | L2 | PAD-L2 | KR |
| :--- | ---: | ---: | ---: | ---: | ---: | ---: | ---: | ---: | ---: | ---: |
| S: ResNet-18 | 69.76* | 71.37 | 70.90 | 71.56 | 70.93 | 70.52 | 70.09 | 71.08 | 71.71 | 71.64 |
| Original work | N/A | N/A | 70.70 | 71.43** | 71.17 | 70.42 | 71.62 | 70.90 | 71.71 | 71.61 |

* 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), most of the results are reported in this paper, and their checkpoints (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.


Executable code can be found in examples/ such as - Image classification: ImageNet (ILSVRC 2012), CIFAR-10, CIFAR-100, etc - Object detection: COCO 2017, etc - Semantic segmentation: COCO 2017, PASCAL VOC, etc - Text classification: GLUE, etc

For CIFAR-10 and CIFAR-100, some models are reimplemented and available as pretrained models in torchdistill. More details can be found here.

Some Transformer models fine-tuned by torchdistill for GLUE tasks are available at Hugging Face Model Hub. Sample GLUE benchmark results and details can be found here.

Google Colab Examples

The following examples are available in demo/. Note that the examples are for Google Colab users. Usually, examples/ would be a better reference if you have your own GPU(s).

CIFAR-10 and CIFAR-100

  • Training without teacher models Open In Colab
  • Knowledge distillation Open In Colab


  • Fine-tuning without teacher models Open In Colab
  • Knowledge distillation Open In Colab

These examples write out test prediction files for you to see the test performance at the GLUE leaderboard system.

PyTorch Hub

If you find models on PyTorch Hub or GitHub repositories supporting PyTorch Hub, you can import them as teacher/student models simply by editing a declarative yaml config file.

e.g., If you use a pretrained ResNeSt-50 available in rwightman/pytorch-image-models (aka timm) as a teacher model for ImageNet dataset, you can import the model via PyTorch Hub with the following entry in your declarative yaml config file.

    name: 'resnest50d'
    repo_or_dir: 'rwightman/pytorch-image-models'
      num_classes: 1000
      pretrained: True

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
cd torchdistill/
pip3 install -e .
# or use pipenv
pipenv install "-e ."

Issues / Questions / Requests

The documentation is work-in-progress. In the meantime, feel free to create an issue if you find a bug.
If you have either a question or feature request, start a new discussion here.


If you use torchdistill in your research, please cite the following paper.
[Paper] [Preprint]

  title={torchdistill: A Modular, Configuration-Driven Framework for Knowledge Distillation},
  author={Matsubara, Yoshitomo},
  booktitle={International Workshop on Reproducible Research in Pattern Recognition},


We use cookies. If you continue to browse the site, you agree to the use of cookies. For more information on our use of cookies please see our Privacy Policy.