![](./resources/mmselfsup_logo.png)
📘Documentation | 🛠️Installation | 👀Model Zoo | 🆕Update News | 🤔Reporting Issues
English | 简体中文
MMSelfSup is an open source self-supervised representation learning toolbox based on PyTorch. It is a part of the OpenMMLab project.
The master branch works with PyTorch 1.5 or higher.
-
Methods All in One
MMSelfsup provides state-of-the-art methods in self-supervised learning. For comprehensive comparison in all benchmarks, most of the pre-training methods are under the same setting.
-
Modular Design
MMSelfSup follows a similar code architecture of OpenMMLab projects with modular design, which is flexible and convenient for users to build their own algorithms.
-
Standardized Benchmarks
MMSelfSup standardizes the benchmarks including logistic regression, SVM / Low-shot SVM from linearly probed features, semi-supervised classification, object detection and semantic segmentation.
-
Compatibility
Since MMSelfSup adopts similar design of modulars and interfaces as those in other OpenMMLab projects, it supports smooth evaluation on downstream tasks with other OpenMMLab projects like object detection and segmentation.
This project is released under the Apache 2.0 license.
MMSelfSup v0.8.0 was released in 31/03/2022.
Highlights of the new version:
- Support SimMIM
- Add KNN benchmark, support KNN test with checkpoint and extracted backbone weights
- Support ImageNet-21k dataset
Please refer to changelog.md for details and release history.
Differences between MMSelfSup and OpenSelfSup codebases can be found in compatibility.md.
Please refer to model_zoo.md for a comprehensive set of pre-trained models and benchmarks.
Supported algorithms:
- Relative Location (ICCV'2015)
- Rotation Prediction (ICLR'2018)
- DeepCLuster (ECCV'2018)
- NPID (CVPR'2018)
- ODC (CVPR'2020)
- MoCo v1 (CVPR'2020)
- SimCLR (ICML'2020)
- MoCo v2 (ArXiv'2020)
- BYOL (NeurIPS'2020)
- SwAV (NeurIPS'2020)
- DenseCL (CVPR'2021)
- SimSiam (CVPR'2021)
- MoCo v3 (ICCV'2021)
- MAE
- SimMIM
More algorithms are in our plan.
Benchmarks | Setting |
---|---|
ImageNet Linear Classification (Multi-head) | Goyal2019 |
ImageNet Linear Classification (Last) | |
ImageNet Semi-Sup Classification | |
Places205 Linear Classification (Multi-head) | Goyal2019 |
iNaturalist2018 Linear Classification (Multi-head) | Goyal2019 |
PASCAL VOC07 SVM | Goyal2019 |
PASCAL VOC07 Low-shot SVM | Goyal2019 |
PASCAL VOC07+12 Object Detection | MoCo |
COCO17 Object Detection | MoCo |
Cityscapes Segmentation | MMSeg |
PASCAL VOC12 Aug Segmentation | MMSeg |
MMSelfSup depends on PyTorch], MMCV and MMClassification.
Please refer to install.md for more detailed instruction.
Please refer to prepare_data.md for dataset preparation and getting_started.md for the basic usage of MMSelfSup.
We also provides tutorials for more details:
- config
- add new dataset
- data pipeline
- add new module
- customize schedules
- customize runtime
- benchmarks
Besides, we provide colab tutorial for basic usage.
If you use this toolbox or benchmark in your research, please cite this project.
@misc{mmselfsup2021,
title={{MMSelfSup}: OpenMMLab Self-Supervised Learning Toolbox and Benchmark},
author={MMSelfSup Contributors},
howpublished={\url{https://github.com/open-mmlab/mmselfsup}},
year={2021}
}
We appreciate all contributions improving MMSelfSup. Please refer to CONTRIBUTING.md for more details about the contributing guideline.
Remarks:
- MMSelfSup originates from OpenSelfSup, and we appreciate all early contributions made to OpenSelfSup. A few contributors are listed here: Xiaohang Zhan, Jiahao Xie, Enze Xie, Xiangxiang Chu, Zijian He.
- The implementation of MoCo and the detection benchmark borrow the code from MoCo.
- The implementation of SwAV borrows the code from SwAV.
- The SVM benchmark borrows the code from fair_self_supervision_benchmark.
mmselfsup/utils/clustering.py
is borrowed from deepcluster.
- MMCV: OpenMMLab foundational library for computer vision.
- MIM: MIM installs OpenMMLab packages.
- MMClassification: OpenMMLab image classification toolbox and benchmark.
- MMDetection: OpenMMLab detection toolbox and benchmark.
- MMDetection3D: OpenMMLab's next-generation platform for general 3D object detection.
- MMRotate: OpenMMLab rotated object detection toolbox and benchmark.
- MMSegmentation: OpenMMLab semantic segmentation toolbox and benchmark.
- MMOCR: OpenMMLab text detection, recognition, and understanding toolbox.
- MMPose: OpenMMLab pose estimation toolbox and benchmark.
- MMHuman3D: OpenMMLab 3D human parametric model toolbox and benchmark.
- MMSelfSup: OpenMMLab self-supervised learning toolbox and benchmark.
- MMRazor: OpenMMLab model compression toolbox and benchmark.
- MMFewShot: OpenMMLab fewshot learning toolbox and benchmark.
- MMAction2: OpenMMLab's next-generation action understanding toolbox and benchmark.
- MMTracking: OpenMMLab video perception toolbox and benchmark.
- MMFlow: OpenMMLab optical flow toolbox and benchmark.
- MMEditing: OpenMMLab image and video editing toolbox.
- MMGeneration: OpenMMLab image and video generative models toolbox.
- MMDeploy: OpenMMLab model deployment framework.