![](https://raw.githubusercontent.com/vakker/mmdetection/main/resources/mmdet-logo.png)
📘Documentation | 🛠️Installation | 👀Model Zoo | 🆕Update News | 🚀Ongoing Projects | 🤔Reporting Issues
English | 简体中文
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+.
Major features
-
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.
v3.2.0 was released in 12/10/2023:
1. Detection Transformer SOTA Model Collection
(1) Supported four updated and stronger SOTA Transformer models: DDQ, CO-DETR, AlignDETR, and H-DINO.
(2) Based on CO-DETR, MMDet released a model with a COCO performance of 64.1 mAP.
(3) Algorithms such as DINO support AMP/Checkpoint/FrozenBN
, which can effectively reduce memory usage.
2. Comprehensive Performance Comparison between CNN and Transformer RF100 consists of a dataset collection of 100 real-world datasets, including 7 domains. It can be used to assess the performance differences of Transformer models like DINO and CNN-based algorithms under different scenarios and data volumes. Users can utilize this benchmark to quickly evaluate the robustness of their algorithms in various scenarios.
3. Support for GLIP and Grounding DINO fine-tuning, the only algorithm library that supports Grounding DINO fine-tuning The Grounding DINO algorithm in MMDet is the only library that supports fine-tuning. Its performance is one point higher than the official version, and of course, GLIP also outperforms the official version. We also provide a detailed process for training and evaluating Grounding DINO on custom datasets. Everyone is welcome to give it a try.
Model | Backbone | Style | COCO mAP | Official COCO mAP |
---|---|---|---|---|
Grounding DINO-T | Swin-T | Zero-shot | 48.5 | 48.4 |
Grounding DINO-T | Swin-T | Finetune | 58.1(+0.9) | 57.2 |
Grounding DINO-B | Swin-B | Zero-shot | 56.9 | 56.7 |
Grounding DINO-B | Swin-B | Finetune | 59.7 | |
Grounding DINO-R50 | R50 | Scratch | 48.9(+0.8) | 48.1 |
4. Support for the open-vocabulary detection algorithm Detic and multi-dataset joint training. 5. Training detection models using FSDP and DeepSpeed.
ID | AMP | GC of Backbone | GC of Encoder | FSDP | Peak Mem (GB) | Iter Time (s) |
---|---|---|---|---|---|---|
1 | 49 (A100) | 0.9 | ||||
2 | √ | 39 (A100) | 1.2 | |||
3 | √ | 33 (A100) | 1.1 | |||
4 | √ | √ | 25 (A100) | 1.3 | ||
5 | √ | √ | 18 | 2.2 | ||
6 | √ | √ | √ | 13 | 1.6 | |
7 | √ | √ | √ | 14 | 2.9 | |
8 | √ | √ | √ | √ | 8.5 | 2.4 |
6. Support for the V3Det dataset, a large-scale detection dataset with over 13,000 categories.
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 |
Please refer to Installation for installation instructions.
Please see Overview for the general introduction of MMDetection.
For detailed user guides and advanced guides, please refer to our documentation:
-
User Guides
- 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
We also provide object detection colab tutorial and instance segmentation colab tutorial
.
To migrate from MMDetection 2.x, please refer to migration.
Results and models are available in the model zoo.
Backbones | Necks | Loss | Common |
|
Some other methods are also supported in projects using MMDetection.
Please refer to FAQ for frequently asked questions.
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.
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.
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}
}
This project is released under the Apache 2.0 license.
- 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.