README 未给出具体安装步骤，需参考官方安装文档，注意 PyTorch 与 CUDA 版本匹配；预训练模型需从 Model Zoo 单独下载；部分功能依赖编译 CUDA 扩展，环境不匹配时安装易失败
detectron2
facebookresearchApache-2.0活跃维护Detectron2 是 Facebook 开源的目标检测与分割平台，提供模块化架构和丰富预训练模型，方便快速搭建和训练视觉识别任务。
Detectron2 is a platform for object detection, segmentation and other visual recognition tasks.
v0.6发布于 2021-11-15 22:08 UTC34,980star +5 / 7 天7,937fork同步于 2026-11-10 11:20 UTC
pip install 'git+https://github.com/facebookresearch/detectron2.git' 硬件要求按 README 说明
README 未说明
Facebook 出品的模块化目标检测与分割库，提供 SOTA 算法和预训练模型
Detectron2 是 Facebook 开源的目标检测与分割平台，提供模块化架构和丰富预训练模型，方便快速搭建和训练视觉识别任务。
核心能力
- 覆盖检测、分割、全景分割、DensePose 等视觉任务
- 内置 Cascade R-CNN、PointRend、DeepLab、ViTDet 等模型
- 支持将模型导出为 TorchScript 或 Caffe2 格式部署
- 提供 Model Zoo 中的基线结果与预训练权重下载
- 可作为库在其上搭建自定义研究项目
容易踩的坑
内容由模型根据 README 生成，可能不完整或不准确，以官方文档为准。看原文 README
- v0.6最新正式版2021-11-15 · 2021-11-15 22:08 UTC
Pre-built Linux binaries are available for the following environment:
- v0.52021-07-23 · 2021-07-23 18:55 UTC
查看更新说明
- Add “LazyConfig” system, an alternative python-based config system with more flexible syntax and no predefined structures.
- Add improved Mask R-CNN baselines to model zoo using large scale jittering and longer training. See blog and configs.
- Add backbone wrapper and detector wrapper for models in mmdetection. This allows training and evaluation of these models in detectron2. See an example config that trains a mmdet’s Mask R-CNN
- Code release for Implicit PointRend & PointSup.
- Code release for Rethinking Batch in BatchNorm.
- Add support for RegNet backbones. Example.
- Integration of fvcore’s tracing-based advanced flop counter.
- New features in DensePose CSE: see its release notes for more details.
Pre-built Linux binaries are available for the following environment:
- v0.42021-03-13 · 2021-03-13 01:36 UTC
查看更新说明
New Features
- All common models can be converted to TorchScript format by tracing or scripting (tutorial). Requires pytorch≥1.8.
- Support fvcore parameter schedulers (originally from ClassyVision) that are composable, scale-invariant, and can be used on parameters other than learning rate.
- Refactor PointRend as a mask head (instead of an ROIHead).
- New export and C++ deployment examples.
- Release d2go which provides end-to-end production pipeline.
New Features in DensePose:
Release DensePose CSE (a framework to extend DensePose to various categories using 3D models) and DensePose Evolution (a framework to bootstrap DensePose on unlabeled data). See here for more details.
Deprecations:
- Deprecate cfg argument from COCO/LVIS evaluator; Deprecate num_classes and ignore_label argument from
SemSegEvaluator - Deprecate
WarmupMultiStepLR,WarmupCosineLRin favor of fvcore schedulers - Deprecated features will be removed in future releases
Pre-built Linux binaries are available for the following environment:
- v0.32020-11-06 · 2020-11-06 03:20 UTC
查看更新说明
Features & Improvements:
- Support constructing RetinaNet, data loader, optimizer, COCOEvaluator without configs, in addition to Mask R-CNN.
- Add DeepLab & PanopticDeepLab in
projects/. - Support importing 3 projects (
point_rend,deeplab,panoptic_deeplab) directly withimport detectron2.projects.xxx. - Support mixed precision in training (using
cfg.SOLVER.AMP.ENABLED) and inference. - Support ADE20k semantic segmentation dataset (named
ade20k_sem_seg_train,ade20k_sem_seg_val). - Continuous build on Windows.
Pre-built Linux binaries are provided for the following environment:
- v0.2.12020-08-04 · 2020-08-04 23:11 UTC
查看更新说明
- Added pre-built binary for PyTorch 1.6
用户点评
登录用户的真实使用记录，可按版本和硬件筛选共 0 条
还没有人点评。第一个说出真实体验的人最有价值。
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 and 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 on top of it.
- Models can be exported to TorchScript format or Caffe2 format for deployment.
- It trains much faster.
See our blog post to see more demos. See this interview to learn more about the stories behind detectron2.
Installation
See installation instructions.
Getting Started
See Getting Started with Detectron2, and the Colab Notebook to learn about basic usage.
Learn more at our documentation. And see 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.
License
Detectron2 is released under the Apache 2.0 license.
Citing Detectron2
If you use Detectron2 in your research or wish to refer to the baseline results published in the Model Zoo, please use the following BibTeX entry.
@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}
}
ultralytics
ultralytics·Python
YOLO 系列官方实现库，一套 PyTorch 代码覆盖目标检测、实例与语义分割、图像分类、姿态估计和目标跟踪，训练到部署全流程打通。
目标检测+4检测 / 分割
63270+8712kv8.4.2082026-11-10 09:31 UTC
yolov5
ultralytics·Python
基于 PyTorch 的目标检测全家桶，覆盖训练、推理、实例分割、图像分类和模型导出，开箱即用，适合快速落地视觉任务。
目标检测+4检测 / 分割
58258+517kv7.02026-11-07 16:59 UTC
pytorch-image-models
huggingface·Python
收录最全的 PyTorch 图像骨干网络合集，涵盖 ResNet、ViT、ConvNeXt 等主流模型，自带训练、评估、推理和导出脚本及预训练权重，省去自己搭网络和找权重的麻烦。
图像分类+4检测 / 分割
37272+75.2kv1.0.312026-11-07 23:22 UTC
mmdetection
open-mmlab·Python
基于 PyTorch 的目标检测工具箱与基准库，集成了 Faster R-CNN、DETR、Grounding DINO 等主流模型，方便训练、评测和复现检测与分割算法。
目标检测+4检测 / 分割
33032+69.8kv3.3.02024-08-21 02:01 UTC