OpenMMLab is an organization on GitHub that focuses on computer vision and machine learning frameworks. It hosts a wide range of repositories primarily written in Python, with notable projects such as mmdetection and mmsegmentation. The organization's work supports various applications, including audio generation and pose estimation, reflecting its significant public footprint.
Top languages
Public repositories
mmdetection
OpenMMLab Detection Toolbox and Benchmark
mmsegmentation
OpenMMLab Semantic Segmentation Toolbox and Benchmark.
Amphion
Amphion (/æmˈfaɪən/) is a toolkit for Audio, Music, and Speech Generation. Its purpose is to support reproducible research and help junior researchers and engineers get started in the field of audio, music, and speech generation research and development.
mmpose
OpenMMLab Pose Estimation Toolbox and Benchmark.
mmagic
OpenMMLab Multimodal Advanced, Generative, and Intelligent Creation Toolbox. Unlock the magic 🪄: Generative-AI (AIGC), easy-to-use APIs, awsome model zoo, diffusion models, for text-to-image generation, image/video restoration/enhancement, etc.
mmcv
OpenMMLab Computer Vision Foundation
mmdetection3d
OpenMMLab's next-generation platform for general 3D object detection.
OpenPCDet
OpenPCDet Toolbox for LiDAR-based 3D Object Detection.
mmaction2
OpenMMLab's Next Generation Video Understanding Toolbox and Benchmark
mmocr
OpenMMLab Text Detection, Recognition and Understanding Toolbox
mmtracking
OpenMMLab Video Perception Toolbox. It supports Video Object Detection (VID), Multiple Object Tracking (MOT), Single Object Tracking (SOT), Video Instance Segmentation (VIS) with a unified framework.
mmpretrain
OpenMMLab Pre-training Toolbox and Benchmark
mmyolo
OpenMMLab YOLO series toolbox and benchmark. Implemented RTMDet, RTMDet-Rotated,YOLOv5, YOLOv6, YOLOv7, YOLOv8,YOLOX, PPYOLOE, etc.
mmselfsup
OpenMMLab Self-Supervised Learning Toolbox and Benchmark
mmdeploy
OpenMMLab Model Deployment Framework
mmskeleton
A OpenMMLAB toolbox for human pose estimation, skeleton-based action recognition, and action synthesis.
mmrotate
OpenMMLab Rotated Object Detection Toolbox and Benchmark
mmgeneration
MMGeneration is a powerful toolkit for generative models, based on PyTorch and MMCV.
mmaction
An open-source toolbox for action understanding based on PyTorch
mmrazor
OpenMMLab Model Compression Toolbox and Benchmark.
Multimodal-GPT
Multimodal-GPT
mmengine
OpenMMLab Foundational Library for Training Deep Learning Models
mmhuman3d
OpenMMLab 3D Human Parametric Model Toolbox and Benchmark
mmfashion
Open-source toolbox for visual fashion analysis based on PyTorch
OpenMMLabCourse
OpenMMLab course index and stuff
playground
A central hub for gathering and showcasing amazing projects that extend OpenMMLab with SAM and other exciting features.
PowerPaint
[ECCV 2024] PowerPaint, a versatile image inpainting model that supports text-guided object inpainting, object removal, image outpainting and shape-guided object inpainting with only a single model. 一个高质量多功能的图像修补模型，可以同时支持插入物体、移除物体、图像扩展、形状可控的物体生成，只需要一个模型
mmflow
OpenMMLab optical flow toolbox and benchmark
PIA
[CVPR 2024] PIA, your Personalized Image Animator. Animate your images by text prompt, combing with Dreambooth, achieving stunning videos. PIA，你的个性化图像动画生成器，利用文本提示将图像变为奇妙的动画
mmfewshot
OpenMMLab FewShot Learning Toolbox and Benchmark
FoleyCrafter
[IJCV] FoleyCrafter: Bring Silent Videos to Life with Lifelike and Synchronized Sounds. AI拟音大师，给你的无声视频添加生动而且同步的音效 😝
StyleShot
StyleShot: A SnapShot on Any Style. 一款可以迁移任意风格到任意内容的模型，无需针对图片微调，即能生成高质量的个性风格化图片!
awesome-vit
No description provided for this repository.
OpenUnReID
PyTorch open-source toolbox for unsupervised or domain adaptive object re-ID.
labelbee-client
Out-of-the-box Annotation Toolbox
mim
MIM Installs OpenMMLab Packages
denseflow
Extracting optical flow and frames
labelbee
LabelBee is an annotation Library
mmeval
A unified evaluation library for multiple machine learning libraries
MMGEN-FaceStylor
No description provided for this repository.
Live2Diff
Live2Diff: A Pipeline that processes Live video streams by a uni-directional video Diffusion model.
AnyControl
[ECCV 2024] AnyControl, a multi-control image synthesis model that supports any combination of user provided control signals. 一个支持用户自由输入控制信号的图像生成模型，能够根据多种控制生成自然和谐的结果！
OpenMMLabCamp
No description provided for this repository.
FaceShot
Official repo for FaceShot: Bring Any Character into Life
mim-example
No description provided for this repository.
mmengine-template
No description provided for this repository.
cocoapi
COCO API - Dataset @ http://cocodataset.org/
mmstyles
Latex style file to facilitate writing of technical papers
ecosystem
No description provided for this repository.
mmpose-webcam-demo
No description provided for this repository.
pre-commit-hooks
No description provided for this repository.
pytorch_sphinx_theme
PyTorch Sphinx Theme
mdformat-openmmlab
No description provided for this repository.
.github
No description provided for this repository.
Frequently asked questions
What does open-mmlab build on GitHub?
OpenMMLab builds frameworks and toolkits for computer vision and machine learning. Key repositories include mmdetection for object detection and mmsegmentation for semantic segmentation, among others.
Which programming languages does open-mmlab use?
OpenMMLab predominantly uses Python for its repositories, along with Jupyter Notebook, JavaScript, C++, TypeScript, and TeX, reflecting a diverse approach to software development.
Are open-mmlab's repositories public?
Yes, all of OpenMMLab's repositories are public on GitHub, allowing the community to access and contribute to projects like mmpose and mmagic, which are designed to advance research in their respective fields.
Is this exposure intended?
Monitor OpenMMLab with RepoGuard and get alerted the moment a new public repository appears.
Monitor this account