mmpretrain

OpenMMLab Pre-training Toolbox and Benchmark

https://github.com/open-mmlab/mmpretrain

Science Score: 64.0%

This score indicates how likely this project is to be science-related based on various indicators:

✓
CITATION.cff file
Found CITATION.cff file
✓
codemeta.json file
Found codemeta.json file
✓
.zenodo.json file
Found .zenodo.json file
○
DOI references
✓
Academic publication links
Links to: arxiv.org
✓
Committers with academic emails
6 of 129 committers (4.7%) from academic institutions
○
Institutional organization owner
○
JOSS paper metadata
○
Scientific vocabulary similarity
Low similarity (9.7%) to scientific vocabulary

Keywords

beit clip constrastive-learning convnext deep-learning image-classification mae masked-image-modeling mobilenet moco multimodal pretrained-models pytorch resnet self-supervised-learning swin-transformer vision-transformer

Scientific Fields

Engineering Computer Science - 40% confidence

Last synced: 6 months ago · JSON representation ·

Repository

OpenMMLab Pre-training Toolbox and Benchmark

Basic Info

Host: GitHub
Owner: open-mmlab
License: apache-2.0
Language: Python
Default Branch: main
Homepage: https://mmpretrain.readthedocs.io/en/latest/
Size: 13.5 MB

Statistics

Stars: 3,737
Watchers: 29
Forks: 1,103
Open Issues: 267
Releases: 36

Topics

Created over 5 years ago · Last pushed over 1 year ago

Metadata Files

Readme Contributing License Citation

README.md

OpenMMLab website ^HOT OpenMMLab platform ^{TRY IT OUT}

[![PyPI](https://img.shields.io/pypi/v/mmpretrain)](https://pypi.org/project/mmpretrain) [![Docs](https://img.shields.io/badge/docs-latest-blue)](https://mmpretrain.readthedocs.io/en/latest/) [![Build Status](https://github.com/open-mmlab/mmpretrain/workflows/build/badge.svg)](https://github.com/open-mmlab/mmpretrain/actions) [![codecov](https://codecov.io/gh/open-mmlab/mmpretrain/branch/main/graph/badge.svg)](https://codecov.io/gh/open-mmlab/mmpretrain) [![license](https://img.shields.io/github/license/open-mmlab/mmpretrain.svg)](https://github.com/open-mmlab/mmpretrain/blob/main/LICENSE) [![open issues](https://isitmaintained.com/badge/open/open-mmlab/mmpretrain.svg)](https://github.com/open-mmlab/mmpretrain/issues) [![issue resolution](https://isitmaintained.com/badge/resolution/open-mmlab/mmpretrain.svg)](https://github.com/open-mmlab/mmpretrain/issues) [📘 Documentation](https://mmpretrain.readthedocs.io/en/latest/) | [🛠️ Installation](https://mmpretrain.readthedocs.io/en/latest/get_started.html#installation) | [👀 Model Zoo](https://mmpretrain.readthedocs.io/en/latest/modelzoo_statistics.html) | [🆕 Update News](https://mmpretrain.readthedocs.io/en/latest/notes/changelog.html) | [🤔 Reporting Issues](https://github.com/open-mmlab/mmpretrain/issues/new/choose)

English | [简体中文](/README_zh-CN.md)

Introduction

MMPreTrain is an open source pre-training toolbox based on PyTorch. It is a part of the OpenMMLab project.

The main branch works with PyTorch 1.8+.

Major features

Various backbones and pretrained models
Rich training strategies (supervised learning, self-supervised learning, multi-modality learning etc.)
Bag of training tricks
Large-scale training configs
High efficiency and extensibility
Powerful toolkits for model analysis and experiments
Various out-of-box inference tasks.
- Image Classification
- Image Caption
- Visual Question Answering
- Visual Grounding
- Retrieval (Image-To-Image, Text-To-Image, Image-To-Text)

https://github.com/open-mmlab/mmpretrain/assets/26739999/e4dcd3a2-f895-4d1b-a351-fbc74a04e904

What's new

🌟 v1.2.0 was released in 04/01/2023

Support LLaVA 1.5.
Implement of RAM with a gradio interface.

🌟 v1.1.0 was released in 12/10/2023

Support Mini-GPT4 training and provide a Chinese model (based on Baichuan-7B)
Support zero-shot classification based on CLIP.

🌟 v1.0.0 was released in 04/07/2023

Support inference of more multi-modal algorithms, such as LLaVA, MiniGPT-4, Otter, etc.
Support around 10 multi-modal datasets!
Add iTPN, SparK self-supervised learning algorithms.
Provide examples of New Config and DeepSpeed/FSDP with FlexibleRunner. Here are the documentation links of New Config and DeepSpeed/FSDP with FlexibleRunner.

🌟 Upgrade from MMClassification to MMPreTrain

Integrated Self-supervised learning algorithms from MMSelfSup, such as MAE, BEiT, etc.
Support RIFormer, a simple but effective vision backbone by removing token mixer.
Refactor dataset pipeline visualization.
Support LeViT, XCiT, ViG, ConvNeXt-V2, EVA, RevViT, EfficientnetV2, CLIP, TinyViT and MixMIM backbones.

This release introduced a brand new and flexible training & test engine, but it's still in progress. Welcome to try according to the documentation.

And there are some BC-breaking changes. Please check the migration tutorial.

Please refer to changelog for more details and other release history.

Installation

Below are quick steps for installation:

shell conda create -n open-mmlab python=3.8 pytorch==1.10.1 torchvision==0.11.2 cudatoolkit=11.3 -c pytorch -y conda activate open-mmlab pip install openmim git clone https://github.com/open-mmlab/mmpretrain.git cd mmpretrain mim install -e .

Please refer to installation documentation for more detailed installation and dataset preparation.

For multi-modality models support, please install the extra dependencies by:

shell mim install -e ".[multimodal]"

User Guides

We provided a series of tutorials about the basic usage of MMPreTrain for new users:

For more information, please refer to our documentation.

Model zoo

Results and models are available in the model zoo.

Overview

Supported Backbones

Self-supervised Learning

Multi-Modality Algorithms

Others

Image Retrieval Task:

ArcFace (CVPR'2019)

Training&Test Tips:

Contributing

We appreciate all contributions to improve MMPreTrain. Please refer to CONTRUBUTING for the contributing guideline.

Acknowledgement

MMPreTrain is an open source project that is contributed by researchers and engineers from various colleges and companies. We appreciate all the contributors who implement their methods or add new features, as well as users who give valuable feedbacks. We wish that the toolbox and benchmark could serve the growing research community by providing a flexible toolkit to reimplement existing methods and supporting their own academic research.

Citation

If you find this project useful in your research, please consider cite:

BibTeX @misc{2023mmpretrain, title={OpenMMLab's Pre-training Toolbox and Benchmark}, author={MMPreTrain Contributors}, howpublished = {\url{https://github.com/open-mmlab/mmpretrain}}, year={2023} }

License

This project is released under the Apache 2.0 license.

Projects in OpenMMLab

MMEngine: OpenMMLab foundational library for training deep learning models.
MMCV: OpenMMLab foundational library for computer vision.
MIM: MIM installs OpenMMLab packages.
MMEval: A unified evaluation library for multiple machine learning libraries.
MMPreTrain: OpenMMLab pre-training 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.
MMYOLO: OpenMMLab YOLO series 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.
MMagic: OpenMMLab Advanced, Generative and Intelligent Creation toolbox.
MMGeneration: OpenMMLab image and video generative models toolbox.
MMDeploy: OpenMMLab model deployment framework.
Playground: A central hub for gathering and showcasing amazing projects built upon OpenMMLab.

Owner

Name: OpenMMLab
Login: open-mmlab
Kind: organization
Location: China

Website: https://openmmlab.com
Twitter: OpenMMLab
Repositories: 53
Profile: https://github.com/open-mmlab

Citation (CITATION.cff)

cff-version: 1.2.0
message: "If you use this software, please cite it as below."
title: "OpenMMLab's Pre-training Toolbox and Benchmark"
authors:
  - name: "MMPreTrain Contributors"
version: 0.15.0
date-released: 2023-04-06
repository-code: "https://github.com/open-mmlab/mmpretrain"
license: Apache-2.0

GitHub Events

Total

Commit comment event: 1
Issues event: 17
Watch event: 306
Member event: 1
Issue comment event: 36
Push event: 1
Pull request event: 4
Pull request review event: 3
Fork event: 67

Last Year

Commit comment event: 1
Issues event: 17
Watch event: 306
Member event: 1
Issue comment event: 36
Push event: 1
Pull request event: 4
Pull request review event: 3
Fork event: 67

Committers

Last synced: 9 months ago

All Time

Total Commits: 916
Total Committers: 129
Avg Commits per committer: 7.101
Development Distribution Score (DDS): 0.681

Past Year

Commits: 3
Committers: 2
Avg Commits per committer: 1.5
Development Distribution Score (DDS): 0.333

Top Committers

Name	Email	Commits
Ma Zerun	m**6@1**m	292
Ezra-Yu	1**6@q**m	87
LXXXXR	7****R	82
lixiaojie	l**e@s**m	52
Yixiao Fang	3****8	46
Hubert	4****u	26
yanglei	y**i@s**m	25
Lei Yang	y**v@g**m	24
whcao	4****h	19
takuoko	t**0@g**m	19
Yuan Liu	3****u	13
techmonsterwang	2**0@q**m	13
zzc98	4****8	10
Songyang Zhang	t****y	9
Zhicheng Chen	c**2@f**m	8
David de la Iglesia Castro	d**o@g**m	7
chenkai	c**i@s**m	6
John	g**p@f**m	6
fanqiNO1	7****1	6
louzan	l**n@s**m	5
Wangbo Zhao(黑色枷锁)	5****o	5
Y. Xiong	x**y@g**m	5
xiefeifeihu	x**u@q**m	4
WRH	1****i	4
Yike Yuan	3****w	4
kitecats	9****s	4
QingChuanWS	b**5@1**m	4
imyhxy	i**y@g**m	4
Wenwei Zhang	4****e	3
Yiqin Wang 王逸钦	w**7@o**m	3
and 99 more...

Committer Domains (Top 20 + Academic)

qq.com: 13 sensetime.com: 6 163.com: 6 intel.com: 3 foxmail.com: 3 sjtu.edu.cn: 2 mails.tsinghua.edu.cn: 1 pku.edu.cn: 1 stu.xidian.edu.cn: 1 yeah.net: 1 stu.pku.edu.cn: 1 126.com: 1

Issues and Pull Requests

Last synced: 6 months ago

All Time

Total issues: 204
Total pull requests: 188
Average time to close issues: about 2 months
Average time to close pull requests: about 2 months
Total issue authors: 173
Total pull request authors: 98
Average comments per issue: 2.24
Average comments per pull request: 1.76
Merged pull requests: 91
Bot issues: 0
Bot pull requests: 0

Past Year

Issues: 18
Pull requests: 7
Average time to close issues: 3 days
Average time to close pull requests: 1 minute
Issue authors: 17
Pull request authors: 4
Average comments per issue: 0.0
Average comments per pull request: 0.71
Merged pull requests: 0
Bot issues: 0
Bot pull requests: 0

View more stats

Top Authors

Issue Authors

alaa-shubbak (7)
HaoLiuHust (6)
crypdick (4)
goldwater668 (3)
baiguosummer (3)
guneetmutreja (3)
bobo0810 (3)
sibet-lb (2)
Ezra-Yu (2)
zbzbzbb95 (2)
felipe-parodi (2)
FDInSky (2)
fangyixiao18 (2)
wangzhaoyang-508 (1)
lyp-liuyipeng (1)

Pull Request Authors

fangyixiao18 (16)
Ezra-Yu (11)
zzc98 (10)
mzr1996 (7)
fanqiNO1 (6)
Lazy-coder-9527 (6)
YuanLiuuuuuu (5)
okotaku (5)
Ginray (5)
MGAMZ (5)
bear-coder-9527 (4)
asas1asas200 (4)
wemoveon2 (4)
wangruohui (3)
alexwangxiang (3)

Top Labels

Issue Labels

help wanted (9)

Pull Request Labels

1.0rc (4) Bug:P2 (1)

Packages

Total packages: 2
Total downloads:
- pypi 20,783 last-month
Total docker downloads: 308

Total dependent packages: 1
(may contain duplicates)
Total dependent repositories: 60
(may contain duplicates)
Total versions: 40
Total maintainers: 1

pypi.org: mmpretrain

OpenMMLab Model Pretraining Toolbox and Benchmark

Homepage: https://github.com/open-mmlab/mmpretrain
Documentation: https://mmpretrain.readthedocs.io/
License: Apache License 2.0
Latest release: 1.2.0
published about 2 years ago

Versions: 9
Dependent Packages: 1
Dependent Repositories: 60
Downloads: 20,783 Last month
Docker Downloads: 308

Rankings

Forks count: 1.3%

Stargazers count: 1.4%

Dependent repos count: 1.9%

Average: 2.8%

Downloads: 2.9%

Docker downloads count: 4.3%

Dependent packages count: 4.8%

Maintainers (1)

openmmlab

Last synced: 6 months ago

proxy.golang.org: github.com/open-mmlab/mmpretrain

Documentation: https://pkg.go.dev/github.com/open-mmlab/mmpretrain#section-documentation
License: apache-2.0
Latest release: v1.2.0
published about 2 years ago

Versions: 31
Dependent Packages: 0
Dependent Repositories: 0

Rankings

Dependent packages count: 6.5%

Average: 6.7%

Dependent repos count: 7.0%

Last synced: 6 months ago

Dependencies

.github/workflows/lint.yml actions

actions/checkout v3 composite
actions/setup-python v4 composite

.github/workflows/pr_stage_test.yml actions

actions/checkout v3 composite
actions/setup-python v4 composite
codecov/codecov-action v1.0.14 composite

.github/workflows/publish-to-pypi.yml actions

actions/checkout v3 composite
actions/setup-python v4 composite

.github/workflows/test_mim.yml actions

actions/checkout v3 composite
actions/setup-python v4 composite

tests/data/meta.yml cpan

.circleci/docker/Dockerfile docker

pytorch/pytorch ${PYTORCH}-cuda${CUDA}-cudnn${CUDNN}-devel build

docker/Dockerfile docker

pytorch/pytorch ${PYTORCH}-cuda${CUDA}-cudnn${CUDNN}-devel build

docker/serve/Dockerfile docker

pytorch/torchserve latest-gpu build

projects/internimage_classification/ops_dcnv3/setup.py pypi

requirements/docs.txt pypi

docutils ==0.18.1
modelindex *
myst-parser *
pytorch_sphinx_theme *
sphinx ==6.1.3
sphinx-copybutton *
sphinx-notfound-page *
sphinx-tabs *
sphinxcontrib-jquery *
tabulate *

requirements/mminstall.txt pypi

mmcv >=2.0.0,<2.1.0
mmengine >=0.8.3,<1.0.0

requirements/multimodal.txt pypi

pycocotools *
transformers >=4.28.0

requirements/optional.txt pypi

albumentations >=0.3.2
grad-cam >=1.3.7
requests *
scikit-learn *

requirements/readthedocs.txt pypi

mmcv-lite >=2.0.0rc4
mmengine *
pycocotools *
torch *
torchvision *
transformers *

requirements/runtime.txt pypi

einops *
importlib-metadata *
mat4py *
matplotlib *
modelindex *
numpy *
rich *

requirements/tests.txt pypi

coverage * test
interrogate * test
pytest * test

requirements.txt pypi

setup.py pypi