[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"project-1693":3},{"id":4,"name":5,"fullName":6,"owner":7,"repo":5,"description":8,"homepage":9,"htmlUrl":10,"language":11,"languages":10,"totalLinesOfCode":10,"stars":12,"forks":13,"watchers":14,"openIssues":15,"contributorsCount":16,"subscribersCount":16,"size":16,"stars1d":17,"stars7d":18,"stars30d":19,"stars90d":16,"forks30d":16,"starsTrendScore":20,"compositeScore":21,"rankGlobal":10,"rankLanguage":10,"license":22,"archived":23,"fork":23,"defaultBranch":24,"hasWiki":23,"hasPages":23,"topics":25,"createdAt":10,"pushedAt":10,"updatedAt":26,"readmeContent":27,"aiSummary":28,"trendingCount":16,"starSnapshotCount":16,"syncStatus":29,"lastSyncTime":30,"discoverSource":31},1693,"detectron2","facebookresearch\u002Fdetectron2","facebookresearch","Detectron2 is a platform for object detection, segmentation and other visual recognition tasks.","https:\u002F\u002Fdetectron2.readthedocs.io\u002Fen\u002Flatest\u002F",null,"Python",34544,7947,392,472,0,4,20,86,19,45,"Apache License 2.0",false,"main",[],"2026-06-12 02:00:31","\u003Cimg src=\".github\u002FDetectron2-Logo-Horz.svg\" width=\"300\" >\n\nDetectron2 is Facebook AI Research's next generation library\nthat provides state-of-the-art detection and segmentation algorithms.\nIt is the successor of\n[Detectron](https:\u002F\u002Fgithub.com\u002Ffacebookresearch\u002FDetectron\u002F)\nand [maskrcnn-benchmark](https:\u002F\u002Fgithub.com\u002Ffacebookresearch\u002Fmaskrcnn-benchmark\u002F).\nIt supports a number of computer vision research projects and production applications in Facebook.\n\n\u003Cdiv align=\"center\">\n  \u003Cimg src=\"https:\u002F\u002Fuser-images.githubusercontent.com\u002F1381301\u002F66535560-d3422200-eace-11e9-9123-5535d469db19.png\"\u002F>\n\u003C\u002Fdiv>\n\u003Cbr>\n\n## Learn More about Detectron2\n\n* Includes new capabilities such as panoptic segmentation, Densepose, Cascade R-CNN, rotated bounding boxes, PointRend,\n  DeepLab, ViTDet, MViTv2 etc.\n* Used as a library to support building [research projects](projects\u002F) on top of it.\n* Models can be exported to TorchScript format or Caffe2 format for deployment.\n* It [trains much faster](https:\u002F\u002Fdetectron2.readthedocs.io\u002Fnotes\u002Fbenchmarks.html).\n\nSee our [blog post](https:\u002F\u002Fai.meta.com\u002Fblog\u002F-detectron2-a-pytorch-based-modular-object-detection-library-\u002F)\nto see more demos.\nSee this [interview](https:\u002F\u002Fai.meta.com\u002Fblog\u002Fdetectron-everingham-prize\u002F) to learn more about the stories behind detectron2.\n\n## Installation\n\nSee [installation instructions](https:\u002F\u002Fdetectron2.readthedocs.io\u002Ftutorials\u002Finstall.html).\n\n## Getting Started\n\nSee [Getting Started with Detectron2](https:\u002F\u002Fdetectron2.readthedocs.io\u002Ftutorials\u002Fgetting_started.html),\nand the [Colab Notebook](https:\u002F\u002Fcolab.research.google.com\u002Fdrive\u002F16jcaJoc6bCFAQ96jDe2HwtXj7BMD_-m5)\nto learn about basic usage.\n\nLearn more at our [documentation](https:\u002F\u002Fdetectron2.readthedocs.org).\nAnd see [projects\u002F](projects\u002F) for some projects that are built on top of detectron2.\n\n## Model Zoo and Baselines\n\nWe provide a large set of baseline results and trained models available for download in the [Detectron2 Model Zoo](MODEL_ZOO.md).\n\n## License\n\nDetectron2 is released under the [Apache 2.0 license](LICENSE).\n\n## Citing Detectron2\n\nIf 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.\n\n```BibTeX\n@misc{wu2019detectron2,\n  author =       {Yuxin Wu and Alexander Kirillov and Francisco Massa and\n                  Wan-Yen Lo and Ross Girshick},\n  title =        {Detectron2},\n  howpublished = {\\url{https:\u002F\u002Fgithub.com\u002Ffacebookresearch\u002Fdetectron2}},\n  year =         {2019}\n}\n```\n","Detectron2 是一个用于物体检测、分割及其他视觉识别任务的平台。它由 Facebook AI Research 开发，提供了包括全景分割、Densepose、Cascade R-CNN 等在内的多种先进算法，并且支持旋转边界框、PointRend、DeepLab 和 ViTDet 等功能。Detectron2 既可作为研究项目的库来构建更复杂的应用，也能将模型导出为 TorchScript 或 Caffe2 格式以便于部署，同时训练速度显著提升。该工具非常适合需要进行图像分析与理解的研究者及开发者使用，特别是在计算机视觉领域内追求高性能解决方案时。",2,"2026-06-11 02:45:29","top_all"]