Awesome
<div align="center"> <img src="resources/mmdet-logo.png" width="600"/> <div> </div> <div align="center"> <b><font size="5">OpenMMLab website</font></b> <sup> <a href="https://openmmlab.com"> <i><font size="4">HOT</font></i> </a> </sup> <b><font size="5">OpenMMLab platform</font></b> <sup> <a href="https://platform.openmmlab.com"> <i><font size="4">TRY IT OUT</font></i> </a> </sup> </div> <div> </div>📘Documentation | 🛠️Installation | 👀Model Zoo | 🆕Update News | 🚀Ongoing Projects | 🤔Reporting Issues
</div> <div align="center">English | 简体中文
</div> <div align="center"> <a href="https://openmmlab.medium.com/" style="text-decoration:none;"> <img src="https://user-images.githubusercontent.com/25839884/219255827-67c1a27f-f8c5-46a9-811d-5e57448c61d1.png" width="3%" alt="" /></a> <img src="https://user-images.githubusercontent.com/25839884/218346358-56cc8e2f-a2b8-487f-9088-32480cceabcf.png" width="3%" alt="" /> <a href="https://discord.com/channels/1037617289144569886/1046608014234370059" style="text-decoration:none;"> <img src="https://user-images.githubusercontent.com/25839884/218347213-c080267f-cbb6-443e-8532-8e1ed9a58ea9.png" width="3%" alt="" /></a> <img src="https://user-images.githubusercontent.com/25839884/218346358-56cc8e2f-a2b8-487f-9088-32480cceabcf.png" width="3%" alt="" /> <a href="https://twitter.com/OpenMMLab" style="text-decoration:none;"> <img src="https://user-images.githubusercontent.com/25839884/218346637-d30c8a0f-3eba-4699-8131-512fb06d46db.png" width="3%" alt="" /></a> <img src="https://user-images.githubusercontent.com/25839884/218346358-56cc8e2f-a2b8-487f-9088-32480cceabcf.png" width="3%" alt="" /> <a href="https://www.youtube.com/openmmlab" style="text-decoration:none;"> <img src="https://user-images.githubusercontent.com/25839884/218346691-ceb2116a-465a-40af-8424-9f30d2348ca9.png" width="3%" alt="" /></a> <img src="https://user-images.githubusercontent.com/25839884/218346358-56cc8e2f-a2b8-487f-9088-32480cceabcf.png" width="3%" alt="" /> <a href="https://space.bilibili.com/1293512903" style="text-decoration:none;"> <img src="https://user-images.githubusercontent.com/25839884/219026751-d7d14cce-a7c9-4e82-9942-8375fca65b99.png" width="3%" alt="" /></a> <img src="https://user-images.githubusercontent.com/25839884/218346358-56cc8e2f-a2b8-487f-9088-32480cceabcf.png" width="3%" alt="" /> <a href="https://www.zhihu.com/people/openmmlab" style="text-decoration:none;"> <img src="https://user-images.githubusercontent.com/25839884/219026120-ba71e48b-6e94-4bd4-b4e9-b7d175b5e362.png" width="3%" alt="" /></a> </div> <div align="center"> <img src="https://github.com/open-mmlab/mmdetection/assets/17425982/6c29886f-ae7a-4a55-8be4-352ee85b7d3e"/> </div>Introduction
MMDetection is an open source object detection toolbox based on PyTorch. It is a part of the OpenMMLab project.
The main branch works with PyTorch 1.8+.
<img src="https://user-images.githubusercontent.com/12907710/187674113-2074d658-f2fb-42d1-ac15-9c4a695e64d7.png"/> <details open> <summary>Major features</summary>-
Modular Design
We decompose the detection framework into different components and one can easily construct a customized object detection framework by combining different modules.
-
Support of multiple tasks out of box
The toolbox directly supports multiple detection tasks such as object detection, instance segmentation, panoptic segmentation, and semi-supervised object detection.
-
High efficiency
All basic bbox and mask operations run on GPUs. The training speed is faster than or comparable to other codebases, including Detectron2, maskrcnn-benchmark and SimpleDet.
-
State of the art
The toolbox stems from the codebase developed by the MMDet team, who won COCO Detection Challenge in 2018, and we keep pushing it forward. The newly released RTMDet also obtains new state-of-the-art results on real-time instance segmentation and rotated object detection tasks and the best parameter-accuracy trade-off on object detection.
Apart from MMDetection, we also released MMEngine for model training and MMCV for computer vision research, which are heavily depended on by this toolbox.
What's New
💎 We have released the pre-trained weights for MM-Grounding-DINO Swin-B and Swin-L, welcome to try and give feedback.
Highlight
v3.3.0 was released in 5/1/2024:
MM-Grounding-DINO: An Open and Comprehensive Pipeline for Unified Object Grounding and Detection
Grounding DINO is a grounding pre-training model that unifies 2d open vocabulary object detection and phrase grounding, with wide applications. However, its training part has not been open sourced. Therefore, we propose MM-Grounding-DINO, which not only serves as an open source replication version of Grounding DINO, but also achieves significant performance improvement based on reconstructed data types, exploring different dataset combinations and initialization strategies. Moreover, we conduct evaluations from multiple dimensions, including OOD, REC, Phrase Grounding, OVD, and Fine-tune, to fully excavate the advantages and disadvantages of Grounding pre-training, hoping to provide inspiration for future work.
code: mm_grounding_dino/README.md
<div align=center> <img src="https://github.com/open-mmlab/mmdetection/assets/17425982/fb14d1ee-5469-44d2-b865-aac9850c429c"/> </div>We are excited to announce our latest work on real-time object recognition tasks, RTMDet, a family of fully convolutional single-stage detectors. RTMDet not only achieves the best parameter-accuracy trade-off on object detection from tiny to extra-large model sizes but also obtains new state-of-the-art performance on instance segmentation and rotated object detection tasks. Details can be found in the technical report. Pre-trained models are here.
Task | Dataset | AP | FPS(TRT FP16 BS1 3090) |
---|---|---|---|
Object Detection | COCO | 52.8 | 322 |
Instance Segmentation | COCO | 44.6 | 188 |
Rotated Object Detection | DOTA | 78.9(single-scale)/81.3(multi-scale) | 121 |
Installation
Please refer to Installation for installation instructions.
Getting Started
Please see Overview for the general introduction of MMDetection.
For detailed user guides and advanced guides, please refer to our documentation:
-
User Guides
<details>- Train & Test
- Learn about Configs
- Inference with existing models
- Dataset Prepare
- Test existing models on standard datasets
- Train predefined models on standard datasets
- Train with customized datasets
- Train with customized models and standard datasets
- Finetuning Models
- Test Results Submission
- Weight initialization
- Use a single stage detector as RPN
- Semi-supervised Object Detection
- Useful Tools
- Train & Test
-
Advanced Guides
<details> </details>
We also provide object detection colab tutorial and instance segmentation colab tutorial
.
To migrate from MMDetection 2.x, please refer to migration.
Overview of Benchmark and Model Zoo
Results and models are available in the model zoo.
<div align="center"> <b>Architectures</b> </div> <table align="center"> <tbody> <tr align="center" valign="bottom"> <td> <b>Object Detection</b> </td> <td> <b>Instance Segmentation</b> </td> <td> <b>Panoptic Segmentation</b> </td> <td> <b>Other</b> </td> </tr> <tr valign="top"> <td> <ul> <li><a href="configs/fast_rcnn">Fast R-CNN (ICCV'2015)</a></li> <li><a href="configs/faster_rcnn">Faster R-CNN (NeurIPS'2015)</a></li> <li><a href="configs/rpn">RPN (NeurIPS'2015)</a></li> <li><a href="configs/ssd">SSD (ECCV'2016)</a></li> <li><a href="configs/retinanet">RetinaNet (ICCV'2017)</a></li> <li><a href="configs/cascade_rcnn">Cascade R-CNN (CVPR'2018)</a></li> <li><a href="configs/yolo">YOLOv3 (ArXiv'2018)</a></li> <li><a href="configs/cornernet">CornerNet (ECCV'2018)</a></li> <li><a href="configs/grid_rcnn">Grid R-CNN (CVPR'2019)</a></li> <li><a href="configs/guided_anchoring">Guided Anchoring (CVPR'2019)</a></li> <li><a href="configs/fsaf">FSAF (CVPR'2019)</a></li> <li><a href="configs/centernet">CenterNet (CVPR'2019)</a></li> <li><a href="configs/libra_rcnn">Libra R-CNN (CVPR'2019)</a></li> <li><a href="configs/tridentnet">TridentNet (ICCV'2019)</a></li> <li><a href="configs/fcos">FCOS (ICCV'2019)</a></li> <li><a href="configs/reppoints">RepPoints (ICCV'2019)</a></li> <li><a href="configs/free_anchor">FreeAnchor (NeurIPS'2019)</a></li> <li><a href="configs/cascade_rpn">CascadeRPN (NeurIPS'2019)</a></li> <li><a href="configs/foveabox">Foveabox (TIP'2020)</a></li> <li><a href="configs/double_heads">Double-Head R-CNN (CVPR'2020)</a></li> <li><a href="configs/atss">ATSS (CVPR'2020)</a></li> <li><a href="configs/nas_fcos">NAS-FCOS (CVPR'2020)</a></li> <li><a href="configs/centripetalnet">CentripetalNet (CVPR'2020)</a></li> <li><a href="configs/autoassign">AutoAssign (ArXiv'2020)</a></li> <li><a href="configs/sabl">Side-Aware Boundary Localization (ECCV'2020)</a></li> <li><a href="configs/dynamic_rcnn">Dynamic R-CNN (ECCV'2020)</a></li> <li><a href="configs/detr">DETR (ECCV'2020)</a></li> <li><a href="configs/paa">PAA (ECCV'2020)</a></li> <li><a href="configs/vfnet">VarifocalNet (CVPR'2021)</a></li> <li><a href="configs/sparse_rcnn">Sparse R-CNN (CVPR'2021)</a></li> <li><a href="configs/yolof">YOLOF (CVPR'2021)</a></li> <li><a href="configs/yolox">YOLOX (CVPR'2021)</a></li> <li><a href="configs/deformable_detr">Deformable DETR (ICLR'2021)</a></li> <li><a href="configs/tood">TOOD (ICCV'2021)</a></li> <li><a href="configs/ddod">DDOD (ACM MM'2021)</a></li> <li><a href="configs/rtmdet">RTMDet (ArXiv'2022)</a></li> <li><a href="configs/conditional_detr">Conditional DETR (ICCV'2021)</a></li> <li><a href="configs/dab_detr">DAB-DETR (ICLR'2022)</a></li> <li><a href="configs/dino">DINO (ICLR'2023)</a></li> <li><a href="configs/glip">GLIP (CVPR'2022)</a></li> <li><a href="configs/ddq">DDQ (CVPR'2023)</a></li> <li><a href="projects/DiffusionDet">DiffusionDet (ArXiv'2023)</a></li> <li><a href="projects/EfficientDet">EfficientDet (CVPR'2020)</a></li> <li><a href="projects/ViTDet">ViTDet (ECCV'2022)</a></li> <li><a href="projects/Detic">Detic (ECCV'2022)</a></li> <li><a href="projects/CO-DETR">CO-DETR (ICCV'2023)</a></li> </ul> </td> <td> <ul> <li><a href="configs/mask_rcnn">Mask R-CNN (ICCV'2017)</a></li> <li><a href="configs/cascade_rcnn">Cascade Mask R-CNN (CVPR'2018)</a></li> <li><a href="configs/ms_rcnn">Mask Scoring R-CNN (CVPR'2019)</a></li> <li><a href="configs/htc">Hybrid Task Cascade (CVPR'2019)</a></li> <li><a href="configs/yolact">YOLACT (ICCV'2019)</a></li> <li><a href="configs/instaboost">InstaBoost (ICCV'2019)</a></li> <li><a href="configs/solo">SOLO (ECCV'2020)</a></li> <li><a href="configs/point_rend">PointRend (CVPR'2020)</a></li> <li><a href="configs/detectors">DetectoRS (ArXiv'2020)</a></li> <li><a href="configs/solov2">SOLOv2 (NeurIPS'2020)</a></li> <li><a href="configs/scnet">SCNet (AAAI'2021)</a></li> <li><a href="configs/queryinst">QueryInst (ICCV'2021)</a></li> <li><a href="configs/mask2former">Mask2Former (ArXiv'2021)</a></li> <li><a href="configs/condinst">CondInst (ECCV'2020)</a></li> <li><a href="projects/SparseInst">SparseInst (CVPR'2022)</a></li> <li><a href="configs/rtmdet">RTMDet (ArXiv'2022)</a></li> <li><a href="configs/boxinst">BoxInst (CVPR'2021)</a></li> <li><a href="projects/ConvNeXt-V2">ConvNeXt-V2 (Arxiv'2023)</a></li> </ul> </td> <td> <ul> <li><a href="configs/panoptic_fpn">Panoptic FPN (CVPR'2019)</a></li> <li><a href="configs/maskformer">MaskFormer (NeurIPS'2021)</a></li> <li><a href="configs/mask2former">Mask2Former (ArXiv'2021)</a></li> <li><a href="configs/XDecoder">XDecoder (CVPR'2023)</a></li> </ul> </td> <td> </ul> <li><b>Contrastive Learning</b></li> <ul> <ul> <li><a href="configs/selfsup_pretrain">SwAV (NeurIPS'2020)</a></li> <li><a href="configs/selfsup_pretrain">MoCo (CVPR'2020)</a></li> <li><a href="configs/selfsup_pretrain">MoCov2 (ArXiv'2020)</a></li> </ul> </ul> </ul> <li><b>Distillation</b></li> <ul> <ul> <li><a href="configs/ld">Localization Distillation (CVPR'2022)</a></li> <li><a href="configs/lad">Label Assignment Distillation (WACV'2022)</a></li> </ul> </ul> <li><b>Semi-Supervised Object Detection</b></li> <ul> <ul> <li><a href="configs/soft_teacher">Soft Teacher (ICCV'2021)</a></li> </ul> </ul> </ul> </td> </tr> </td> </tr> </tbody> </table> <div align="center"> <b>Components</b> </div> <table align="center"> <tbody> <tr align="center" valign="bottom"> <td> <b>Backbones</b> </td> <td> <b>Necks</b> </td> <td> <b>Loss</b> </td> <td> <b>Common</b> </td> </tr> <tr valign="top"> <td> <ul> <li>VGG (ICLR'2015)</li> <li>ResNet (CVPR'2016)</li> <li>ResNeXt (CVPR'2017)</li> <li>MobileNetV2 (CVPR'2018)</li> <li><a href="configs/hrnet">HRNet (CVPR'2019)</a></li> <li><a href="configs/empirical_attention">Generalized Attention (ICCV'2019)</a></li> <li><a href="configs/gcnet">GCNet (ICCVW'2019)</a></li> <li><a href="configs/res2net">Res2Net (TPAMI'2020)</a></li> <li><a href="configs/regnet">RegNet (CVPR'2020)</a></li> <li><a href="configs/resnest">ResNeSt (ArXiv'2020)</a></li> <li><a href="configs/pvt">PVT (ICCV'2021)</a></li> <li><a href="configs/swin">Swin (CVPR'2021)</a></li> <li><a href="configs/pvt">PVTv2 (ArXiv'2021)</a></li> <li><a href="configs/resnet_strikes_back">ResNet strikes back (ArXiv'2021)</a></li> <li><a href="configs/efficientnet">EfficientNet (ArXiv'2021)</a></li> <li><a href="configs/convnext">ConvNeXt (CVPR'2022)</a></li> <li><a href="projects/ConvNeXt-V2">ConvNeXtv2 (ArXiv'2023)</a></li> </ul> </td> <td> <ul> <li><a href="configs/pafpn">PAFPN (CVPR'2018)</a></li> <li><a href="configs/nas_fpn">NAS-FPN (CVPR'2019)</a></li> <li><a href="configs/carafe">CARAFE (ICCV'2019)</a></li> <li><a href="configs/fpg">FPG (ArXiv'2020)</a></li> <li><a href="configs/groie">GRoIE (ICPR'2020)</a></li> <li><a href="configs/dyhead">DyHead (CVPR'2021)</a></li> </ul> </td> <td> <ul> <li><a href="configs/ghm">GHM (AAAI'2019)</a></li> <li><a href="configs/gfl">Generalized Focal Loss (NeurIPS'2020)</a></li> <li><a href="configs/seesaw_loss">Seasaw Loss (CVPR'2021)</a></li> </ul> </td> <td> <ul> <li><a href="configs/faster_rcnn/faster-rcnn_r50_fpn_ohem_1x_coco.py">OHEM (CVPR'2016)</a></li> <li><a href="configs/gn">Group Normalization (ECCV'2018)</a></li> <li><a href="configs/dcn">DCN (ICCV'2017)</a></li> <li><a href="configs/dcnv2">DCNv2 (CVPR'2019)</a></li> <li><a href="configs/gn+ws">Weight Standardization (ArXiv'2019)</a></li> <li><a href="configs/pisa">Prime Sample Attention (CVPR'2020)</a></li> <li><a href="configs/strong_baselines">Strong Baselines (CVPR'2021)</a></li> <li><a href="configs/resnet_strikes_back">Resnet strikes back (ArXiv'2021)</a></li> </ul> </td> </tr> </td> </tr> </tbody> </table>Some other methods are also supported in projects using MMDetection.
FAQ
Please refer to FAQ for frequently asked questions.
Contributing
We appreciate all contributions to improve MMDetection. Ongoing projects can be found in out GitHub Projects. Welcome community users to participate in these projects. Please refer to CONTRIBUTING.md for the contributing guideline.
Acknowledgement
MMDetection 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 develop their own new detectors.
Citation
If you use this toolbox or benchmark in your research, please cite this project.
@article{mmdetection,
title = {{MMDetection}: Open MMLab Detection Toolbox and Benchmark},
author = {Chen, Kai and Wang, Jiaqi and Pang, Jiangmiao and Cao, Yuhang and
Xiong, Yu and Li, Xiaoxiao and Sun, Shuyang and Feng, Wansen and
Liu, Ziwei and Xu, Jiarui and Zhang, Zheng and Cheng, Dazhi and
Zhu, Chenchen and Cheng, Tianheng and Zhao, Qijie and Li, Buyu and
Lu, Xin and Zhu, Rui and Wu, Yue and Dai, Jifeng and Wang, Jingdong
and Shi, Jianping and Ouyang, Wanli and Loy, Chen Change and Lin, Dahua},
journal= {arXiv preprint arXiv:1906.07155},
year={2019}
}
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.
- MMPreTrain: OpenMMLab pre-training toolbox and benchmark.
- MMagic: OpenMMLab Advanced, Generative and Intelligent Creation toolbox.
- 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.
- MMEditing: OpenMMLab image and video editing toolbox.
- MMGeneration: OpenMMLab image and video generative models toolbox.
- MMDeploy: OpenMMLab model deployment framework.
- MIM: MIM installs OpenMMLab packages.
- MMEval: A unified evaluation library for multiple machine learning libraries.
- Playground: A central hub for gathering and showcasing amazing projects built upon OpenMMLab.