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 these papers 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/.
When you refer to torchdistill in your paper, please cite these papers
instead of this GitHub repository.
If you use torchdistill as part of your work, your citation is appreciated and motivates me to maintain and upgrade this framework!
You can find the API documentation and research projects that leverage torchdistill at https://yoshitomo-matsubara.net/torchdistill/
Using ForwardHookManager, you can extract intermediate representations in model without modifying the interface of its forward function.
This example notebook 
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.
If you want to use your own modules (models, loss functions, datasets, etc) with this framework,
you can do so without editing code in the local package torchdistill/.
See the official documentation and Discussions for more details.
Top-1 validation accuracy for ILSVRC 2012 (ImageNet)
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.
The following examples are available in demo/. Note that these examples are for Google Colab users and compatible with Amazon SageMaker Studio Lab. Usually, examples/ would be a better reference if you have your own GPU(s).
- Training without teacher models
- Knowledge distillation
- Fine-tuning without teacher models
- Knowledge distillation
These examples write out test prediction files for you to see the test performance at the GLUE leaderboard system.
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 huggingface/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.
models:
teacher_model:
name: 'resnest50d'
repo_or_dir: 'huggingface/pytorch-image-models'
kwargs:
num_classes: 1000
pretrained: True- Python >= 3.9
- pipenv (optional)
pip3 install torchdistill
# or use pipenv
pipenv install torchdistill
git clone https://github.com/yoshitomo-matsubara/torchdistill.git
cd torchdistill/
pip3 install -e .
# or use pipenv
pipenv install "-e ."
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.
Please search through Issues and Discussions and make sure your issue/question/request has not been addressed yet.
Pull requests are welcome. Please start with an issue and discuss solutions with me rather than start with a pull request.
If you use torchdistill in your research, please cite the following papers:
[Paper] [Preprint]
@inproceedings{matsubara2021torchdistill,
title={{torchdistill: A Modular, Configuration-Driven Framework for Knowledge Distillation}},
author={Matsubara, Yoshitomo},
booktitle={International Workshop on Reproducible Research in Pattern Recognition},
pages={24--44},
year={2021},
organization={Springer}
}[Paper] [OpenReview] [Preprint]
@inproceedings{matsubara2023torchdistill,
title={{torchdistill Meets Hugging Face Libraries for Reproducible, Coding-Free Deep Learning Studies: A Case Study on NLP}},
author={Matsubara, Yoshitomo},
booktitle={Proceedings of the 3rd Workshop for Natural Language Processing Open Source Software (NLP-OSS 2023)},
publisher={Empirical Methods in Natural Language Processing},
pages={153--164},
year={2023}
}This project has been supported by Travis CI's OSS credits and JetBrain's Free License Programs (Open Source)
since November 2021 and June 2022, respectively.
- 🔍 pytorch/vision/references/classification/
- 🔍 pytorch/vision/references/detection/
- 🔍 pytorch/vision/references/segmentation/
- 🔍 huggingface/transformers/examples/pytorch/text-classification
- 🔍 Geoffrey Hinton, Oriol Vinyals, Jeff Dean. "Distilling the Knowledge in a Neural Network" (Deep Learning and Representation Learning Workshop: NeurIPS 2014)
- 🔍 Adriana Romero, Nicolas Ballas, Samira Ebrahimi Kahou, Antoine Chassang, Carlo Gatta, Yoshua Bengio. "FitNets: Hints for Thin Deep Nets" (ICLR 2015)
- 🔍 Junho Yim, Donggyu Joo, Jihoon Bae, Junmo Kim. "A Gift From Knowledge Distillation: Fast Optimization, Network Minimization and Transfer Learning" (CVPR 2017)
- 🔍 Sergey Zagoruyko, Nikos Komodakis. "Paying More Attention to Attention: Improving the Performance of Convolutional Neural Networks via Attention Transfer" (ICLR 2017)
- 🔍 Nikolaos Passalis, Anastasios Tefas. "Learning Deep Representations with Probabilistic Knowledge Transfer" (ECCV 2018)
- 🔍 Jangho Kim, Seonguk Park, Nojun Kwak. "Paraphrasing Complex Network: Network Compression via Factor Transfer" (NeurIPS 2018)
- 🔍 Byeongho Heo, Minsik Lee, Sangdoo Yun, Jin Young Choi. "Knowledge Transfer via Distillation of Activation Boundaries Formed by Hidden Neurons" (AAAI 2019)
- 🔍 Tong He, Chunhua Shen, Zhi Tian, Dong Gong, Changming Sun, Youliang Yan. "Knowledge Adaptation for Efficient Semantic Segmentation" (CVPR 2019)
- 🔍 Wonpyo Park, Dongju Kim, Yan Lu, Minsu Cho. "Relational Knowledge Distillation" (CVPR 2019)
- 🔍 Sungsoo Ahn, Shell Xu Hu, Andreas Damianou, Neil D. Lawrence, Zhenwen Dai. "Variational Information Distillation for Knowledge Transfer" (CVPR 2019)
- 🔍 Yoshitomo Matsubara, Sabur Baidya, Davide Callegaro, Marco Levorato, Sameer Singh. "Distilled Split Deep Neural Networks for Edge-Assisted Real-Time Systems" (Workshop on Hot Topics in Video Analytics and Intelligent Edges: MobiCom 2019)
- 🔍 Baoyun Peng, Xiao Jin, Jiaheng Liu, Dongsheng Li, Yichao Wu, Yu Liu, Shunfeng Zhou, Zhaoning Zhang. "Correlation Congruence for Knowledge Distillation" (ICCV 2019)
- 🔍 Frederick Tung, Greg Mori. "Similarity-Preserving Knowledge Distillation" (ICCV 2019)
- 🔍 Yonglong Tian, Dilip Krishnan, Phillip Isola. "Contrastive Representation Distillation" (ICLR 2020)
- 🔍 Yoshitomo Matsubara, Marco Levorato. "Neural Compression and Filtering for Edge-assisted Real-time Object Detection in Challenged Networks" (ICPR 2020)
- 🔍 Li Yuan, Francis E.H.Tay, Guilin Li, Tao Wang, Jiashi Feng. "Revisiting Knowledge Distillation via Label Smoothing Regularization" (CVPR 2020)
- 🔍 Guodong Xu, Ziwei Liu, Xiaoxiao Li, Chen Change Loy. "Knowledge Distillation Meets Self-Supervision" (ECCV 2020)
- 🔍 Youcai Zhang, Zhonghao Lan, Yuchen Dai, Fangao Zeng, Yan Bai, Jie Chang, Yichen Wei. "Prime-Aware Adaptive Distillation" (ECCV 2020)
- 🔍 Pengguang Chen, Shu Liu, Hengshuang Zhao, Jiaya Jia. "Distilling Knowledge via Knowledge Review" (CVPR 2021)
- 🔍 Li Liu, Qingle Huang, Sihao Lin, Hongwei Xie, Bing Wang, Xiaojun Chang, Xiaodan Liang. "Exploring Inter-Channel Correlation for Diversity-Preserved Knowledge Distillation" (ICCV 2021)
- 🔍 Tao Huang, Shan You, Fei Wang, Chen Qian, Chang Xu. "Knowledge Distillation from A Stronger Teacher" (NeurIPS 2022)
- 🔍 Roy Miles, Krystian Mikolajczyk. "Understanding the Role of the Projector in Knowledge Distillation" (AAAI 2024)
- 🔍 Shangquan Sun, Wenqi Ren, Jingzhi Li, Rui Wang, Xiaochun Cao. "Logit Standardization in Knowledge Distillation" (CVPR 2024)