https://github.com/facebookresearch/detectron2
Detectron2 is a platform for object detection, segmentation and other visual recognition tasks.
https://github.com/facebookresearch/detectron2
Last synced: 7 months ago
JSON representation
Detectron2 is a platform for object detection, segmentation and other visual recognition tasks.
- Host: GitHub
- URL: https://github.com/facebookresearch/detectron2
- Owner: facebookresearch
- License: apache-2.0
- Created: 2019-09-05T21:30:20.000Z (about 6 years ago)
- Default Branch: main
- Last Pushed: 2025-04-24T21:47:42.000Z (7 months ago)
- Last Synced: 2025-05-05T15:54:19.407Z (7 months ago)
- Language: Python
- Homepage: https://detectron2.readthedocs.io/en/latest/
- Size: 6.21 MB
- Stars: 31,889
- Watchers: 391
- Forks: 7,649
- Open Issues: 567
-
Metadata Files:
- Readme: README.md
- Contributing: .github/CONTRIBUTING.md
- License: LICENSE
- Code of conduct: .github/CODE_OF_CONDUCT.md
Awesome Lists containing this project
- awesome-self-driving - Detectron2
- awesome-resources - detectron2 - FAIR's next-generation research platform for object detection and segmentation. It is a ground-up rewrite of the previous version, Detectron, and is powered by the PyTorch deep learning framework. (Uncategorized / Uncategorized)
- Awesome-pytorch-list-CNVersion - detectron2
- awesome-robotic-tooling - detectron2 - is a next-generation research platform for object detection and segmentation. (Sensor Processing / Image Processing)
- awesome-robotic-tooling - detectron2 - A next-generation research platform for object detection and segmentation. (Sensor Processing / Image Processing)
- awesome-list - Detectron2 - A platform for object detection, segmentation and other visual recognition tasks, based on PyTorch. (Computer Vision / Classification & Detection & Tracking)
- Awesome-pytorch-list - detectron2 - generation research platform for object detection and segmentation. (Pytorch & related libraries / CV:)
- awesome-cv - detectron2 - generation platform for object detection, segmentation and other visual recognition tasks | (Repos)
- StarryDivineSky - facebookresearch/detectron2
- awesome-starts - facebookresearch/detectron2 - Detectron2 is FAIR's next-generation platform for object detection, segmentation and other visual recognition tasks. (Python)
- awesome-pytorch-list - detectron2
- awesome-ai-models - facebookresearch/detectron2
- awesome-deep-learning - Detectron2 - A high-performance framework for object detection and segmentation. (Computer Vision)
- awesome-computer-vision - Detectron2 - A high-performance object detection library developed by Facebook AI Research. (Libraries and Frameworks)
- awesome-machine-learning - detectron2 - FAIR's next-generation research platform for object detection and segmentation. It is a ground-up rewrite of the previous version, Detectron, and is powered by the PyTorch deep learning framework. (Python / General-Purpose Machine Learning)
- awesome-machine-learning - detectron2 - FAIR's next-generation research platform for object detection and segmentation. It is a ground-up rewrite of the previous version, Detectron, and is powered by the PyTorch deep learning framework. (Python / General-Purpose Machine Learning)
- AiTreasureBox - facebookresearch/detectron2 - 11-03_33598_0](https://img.shields.io/github/stars/facebookresearch/detectron2.svg)|Detectron2 is a platform for object detection, segmentation and other visual recognition tasks.| (Repos)
- awesome-production-machine-learning - Detectron2 - Detectron2 is Facebook AI Research's next generation library that provides state-of-the-art detection and segmentation algorithms. (Industry Strength Computer Vision)
- awesome-ai - Detectron2 - A high-performance object detection library by Facebook AI Research. (Computer Vision)
- awesome-scientific-image-analysis - Detectron2 - -> (๐ Object detection / Software tools)
- awesome-docker - facebookresearch/detectron2
- awesome-python-machine-learning-resources - GitHub - 7% open ยท โฑ๏ธ 24.08.2022): (ๅพๅๆฐๆฎไธCV)
- awesome-aigc - Detectron2
- Jupyter-Guide - Detectron2 - generation platform for object detection and segmentation. (PyTorch Tools, Libraries, and Frameworks)
- CV-pretrained-model - detectron2 - of-the-art object detection algorithms | `PyTorch` | [Apache License 2.0](https://raw.githubusercontent.com/facebookresearch/detectron2/master/LICENSE) (Model Deployment library / PyTorch <a name="pytorch"/>)
- Awesome-Ai-Tools - Detectron2 - Facebook's detection framework. ๐ (๐๏ธ Computer Vision / ๐ฏ Specialized Vision Tools)
- fucking-awesome-machine-learning - detectron2 - FAIR's next-generation research platform for object detection and segmentation. It is a ground-up rewrite of the previous version, Detectron, and is powered by the PyTorch deep learning framework. (Python / General-Purpose Machine Learning)
- awesome-machine-learning - detectron2 - FAIR's next-generation research platform for object detection and segmentation. It is a ground-up rewrite of the previous version, Detectron, and is powered by the PyTorch deep learning framework. (Python / General-Purpose Machine Learning)
- awesome-ai-papers - [Detectron2 - mmlab/mmdetection)\]\[[MMDetection3D](https://github.com/open-mmlab/mmdetection3d)\]\[[detrex](https://github.com/IDEA-Research/detrex)\]\[[Ultralytics YOLO11](https://github.com/ultralytics/ultralytics)\]\[[AlphaPose](https://github.com/MVIG-SJTU/AlphaPose)\]\[[Anomalib](https://github.com/open-edge-platform/anomalib)\] (CV / 7. Object Detection)
- awesome-google-colab - Detectron2 - Detectron2 is FAIR's next-generation research platform for object detection and segmentation. (Technologies)
- awesome-machine-learning - detectron2 - FAIR's next-generation research platform for object detection and segmentation. It is a ground-up rewrite of the previous version, Detectron, and is powered by the PyTorch deep learning framework. (Python / General-Purpose Machine Learning)
README
Detectron2 is Facebook AI Research's next generation library
that provides state-of-the-art detection and segmentation algorithms.
It is the successor of
[Detectron](https://github.com/facebookresearch/Detectron/)
and [maskrcnn-benchmark](https://github.com/facebookresearch/maskrcnn-benchmark/).
It supports a number of computer vision research projects and production applications in Facebook.
## Learn More about Detectron2
* Includes new capabilities such as panoptic segmentation, Densepose, Cascade R-CNN, rotated bounding boxes, PointRend,
DeepLab, ViTDet, MViTv2 etc.
* Used as a library to support building [research projects](projects/) on top of it.
* Models can be exported to TorchScript format or Caffe2 format for deployment.
* It [trains much faster](https://detectron2.readthedocs.io/notes/benchmarks.html).
See our [blog post](https://ai.meta.com/blog/-detectron2-a-pytorch-based-modular-object-detection-library-/)
to see more demos.
See this [interview](https://ai.meta.com/blog/detectron-everingham-prize/) to learn more about the stories behind detectron2.
## Installation
See [installation instructions](https://detectron2.readthedocs.io/tutorials/install.html).
## Getting Started
See [Getting Started with Detectron2](https://detectron2.readthedocs.io/tutorials/getting_started.html),
and the [Colab Notebook](https://colab.research.google.com/drive/16jcaJoc6bCFAQ96jDe2HwtXj7BMD_-m5)
to learn about basic usage.
Learn more at our [documentation](https://detectron2.readthedocs.org).
And see [projects/](projects/) for some projects that are built on top of detectron2.
## Model Zoo and Baselines
We provide a large set of baseline results and trained models available for download in the [Detectron2 Model Zoo](MODEL_ZOO.md).
## License
Detectron2 is released under the [Apache 2.0 license](LICENSE).
## Citing Detectron2
If you use Detectron2 in your research or wish to refer to the baseline results published in the [Model Zoo](MODEL_ZOO.md), please use the following BibTeX entry.
```BibTeX
@misc{wu2019detectron2,
author = {Yuxin Wu and Alexander Kirillov and Francisco Massa and
Wan-Yen Lo and Ross Girshick},
title = {Detectron2},
howpublished = {\url{https://github.com/facebookresearch/detectron2}},
year = {2019}
}
```