PoseforEveryting的github代码
现有的二维姿态估计工作主要集中在某个类别，例如人、动物和车辆。但是，有许多应用场景需要检测看不见的物体类的姿势/关键点。在本文中，我们介绍了与类别无关的姿态估计（CAPE）的任务，该任务旨在创建一个姿态估计模型，该模型能够在仅给定几个具有关键点定义的样本的情况下检测任何类别物体的姿态。为了实现这一目标，我们将姿态估计问题表述为关键点匹配问题，并设计了一种新颖的CAPE框架，称为POse匹配网络（POMNet）。该文提出一种基于变压器的键点交互模块（KIM），用于捕获不同关键点之间的交互以及支持和查询图像之间的关系。我们还介绍了多类别姿势 （MP-100） 数据集，这是一个包含 100 个对象类别的 2D 姿势数据集，包含超过 20K 个实例，专为开发 CAPE 算法而设计。实验表明，我们的方法比其他基线方法大打折扣。
文件下载
资源详情
[{"title":"（ 55 个子文件 4.94MB ） PoseforEveryting的github代码","children":[{"title":"Pose-for-Everything-main","children":[{"title":"pomnet","children":[{"title":"models","children":[{"title":"keypoint_heads","children":[{"title":"matching_head.py <span style='color:#111;'> 15.90KB </span>","children":null,"spread":false},{"title":"transformer_head.py <span style='color:#111;'> 18.92KB </span>","children":null,"spread":false},{"title":"__init__.py <span style='color:#111;'> 133B </span>","children":null,"spread":false}],"spread":true},{"title":"detectors","children":[{"title":"__init__.py <span style='color:#111;'> 142B </span>","children":null,"spread":false},{"title":"transformer_pose.py <span style='color:#111;'> 12.10KB </span>","children":null,"spread":false},{"title":"fewshot_keypoint.py <span style='color:#111;'> 12.22KB </span>","children":null,"spread":false}],"spread":true},{"title":"__init__.py <span style='color:#111;'> 70B </span>","children":null,"spread":false},{"title":"utils","children":[{"title":"positional_encoding.py <span style='color:#111;'> 6.41KB </span>","children":null,"spread":false},{"title":"builder.py <span style='color:#111;'> 1.50KB </span>","children":null,"spread":false},{"title":"__init__.py <span style='color:#111;'> 579B </span>","children":null,"spread":false},{"title":"transformer.py <span style='color:#111;'> 9.68KB </span>","children":null,"spread":false}],"spread":true}],"spread":true},{"title":"core","children":[{"title":"__init__.py <span style='color:#111;'> 1B </span>","children":null,"spread":false},{"title":"custom_hooks","children":[{"title":"shuffle_hooks.py <span style='color:#111;'> 1.11KB </span>","children":null,"spread":false}],"spread":true}],"spread":true},{"title":"__init__.py <span style='color:#111;'> 90B </span>","children":null,"spread":false},{"title":"apis","children":[{"title":"train.py <span style='color:#111;'> 4.55KB </span>","children":null,"spread":false},{"title":"__init__.py <span style='color:#111;'> 64B </span>","children":null,"spread":false}],"spread":true},{"title":"VERSION <span style='color:#111;'> 6B </span>","children":null,"spread":false},{"title":"datasets","children":[{"title":"pipelines","children":[{"title":"post_transforms.py <span style='color:#111;'> 3.58KB </span>","children":null,"spread":false},{"title":"top_down_transform.py <span style='color:#111;'> 15.82KB </span>","children":null,"spread":false},{"title":"__init__.py <span style='color:#111;'> 192B </span>","children":null,"spread":false}],"spread":true},{"title":"builder.py <span style='color:#111;'> 1.83KB </span>","children":null,"spread":false},{"title":"__init__.py <span style='color:#111;'> 96B </span>","children":null,"spread":false},{"title":"datasets","children":[{"title":"mp100","children":[{"title":"transformer_dataset.py <span style='color:#111;'> 10.70KB </span>","children":null,"spread":false},{"title":"fewshot_base_dataset.py <span style='color:#111;'> 7.71KB </span>","children":null,"spread":false},{"title":"fewshot_dataset.py <span style='color:#111;'> 10.48KB </span>","children":null,"spread":false},{"title":"__init__.py <span style='color:#111;'> 345B </span>","children":null,"spread":false},{"title":"transformer_base_dataset.py <span style='color:#111;'> 6.63KB </span>","children":null,"spread":false}],"spread":true},{"title":"__init__.py <span style='color:#111;'> 257B </span>","children":null,"spread":false}],"spread":true}],"spread":true}],"spread":true},{"title":"tools","children":[{"title":"test.py <span style='color:#111;'> 4.67KB </span>","children":null,"spread":false},{"title":"train.py <span style='color:#111;'> 5.99KB </span>","children":null,"spread":false},{"title":"dist_train.sh <span style='color:#111;'> 295B </span>","children":null,"spread":false},{"title":"slurm_test.sh <span style='color:#111;'> 566B </span>","children":null,"spread":false},{"title":"slurm_train.sh <span style='color:#111;'> 574B </span>","children":null,"spread":false},{"title":"dist_test.sh <span style='color:#111;'> 320B </span>","children":null,"spread":false}],"spread":true},{"title":"assets","children":[{"title":"intro.png <span style='color:#111;'> 2.58MB </span>","children":null,"spread":false},{"title":"MP100.png <span style='color:#111;'> 2.37MB </span>","children":null,"spread":false}],"spread":true},{"title":"mp100","children":[{"title":"rename_carfusion_image.py <span style='color:#111;'> 1.04KB </span>","children":null,"spread":false},{"title":"README.md <span style='color:#111;'> 9.25KB </span>","children":null,"spread":false}],"spread":true},{"title":"LICENSE <span style='color:#111;'> 11.14KB </span>","children":null,"spread":false},{"title":"setup.cfg <span style='color:#111;'> 475B </span>","children":null,"spread":false},{"title":"configs","children":[{"title":"mp100","children":[{"title":"pomnet","children":[{"title":"pomnet_mp100_split1_256x256_1shot.py <span style='color:#111;'> 5.38KB </span>","children":null,"spread":false},{"title":"pomnet_mp100_split4_256x256_1shot.py <span style='color:#111;'> 5.38KB </span>","children":null,"spread":false},{"title":"pomnet_mp100_split3_256x256_1shot.py <span style='color:#111;'> 5.38KB </span>","children":null,"spread":false},{"title":"pomnet_mp100_split2_256x256_1shot.py <span style='color:#111;'> 5.38KB </span>","children":null,"spread":false},{"title":"pomnet_mp100_split5_256x256_1shot.py <span style='color:#111;'> 5.38KB </span>","children":null,"spread":false}],"spread":true},{"title":"matching","children":[{"title":"matching_mp100_split5_256x256_1shot.py.py <span style='color:#111;'> 3.76KB </span>","children":null,"spread":false},{"title":"matching_mp100_split3_256x256_1shot.py.py <span style='color:#111;'> 3.76KB </span>","children":null,"spread":false},{"title":"matching_mp100_split2_256x256_1shot.py.py <span style='color:#111;'> 3.76KB </span>","children":null,"spread":false},{"title":"matching_mp100_split1_256x256_1shot.py <span style='color:#111;'> 3.76KB </span>","children":null,"spread":false},{"title":"matching_mp100_split4_256x256_1shot.py.py <span style='color:#111;'> 3.76KB </span>","children":null,"spread":false}],"spread":true}],"spread":true}],"spread":true},{"title":"requirements.txt <span style='color:#111;'> 64B </span>","children":null,"spread":false},{"title":"setup.py <span style='color:#111;'> 3.08KB </span>","children":null,"spread":false},{"title":".gitignore <span style='color:#111;'> 1.32KB </span>","children":null,"spread":false},{"title":"README.md <span style='color:#111;'> 4.55KB </span>","children":null,"spread":false},{"title":".pre-commit-config.yaml <span style='color:#111;'> 953B </span>","children":null,"spread":false}],"spread":false}],"spread":true}]
评论信息
其他资源
- Synchro7中文说明书
- 概率与统计（陈家鼎）电子书
- MVC外文文献
- 算法导论——所有算法和数据结构的C++实现
- cronolog-1.6.2.Linux.zip
- 超简单 Flash 作品/作业
- ABAP开发教程及代码（含SAP各模块实例代码）
- Visual Prolog 初学者指南（中文版)
- SDL_image-1.2.8.tar.tar
- STM32F4 硬件I2C 使用DMA
- 微信电影机器人
- java web房屋出租系统项目
- 2020桂电计算机组成原理课程设计工程文件
- 基于VHDL的程序设计集
- 量子计算和量子信息 Nielsen著 pdf版
- 迁移上云架构设计及解决方案
- nginx离线安装包
- 单相AC-DC变换电路（A题）
- 图书在线销售系统的设计与实现毕业论文
- mingw32-openssl-1.1.1
- sql挂起解决.rar
- Odoo13 企业版 ubuntu 18.04 64安装.pdf
- WPE封包工具
- java 支付宝H5支付Demo
- Android图像数字识别
免责申明
【只为小站】的资源来自网友分享，仅供学习研究，请务必在下载后24小时内给予删除，不得用于其他任何用途，否则后果自负。基于互联网的特殊性，【只为小站】 无法对用户传输的作品、信息、内容的权属或合法性、合规性、真实性、科学性、完整权、有效性等进行实质审查；无论 【只为小站】 经营者是否已进行审查，用户均应自行承担因其传输的作品、信息、内容而可能或已经产生的侵权或权属纠纷等法律责任。
本站所有资源不代表本站的观点或立场，基于网友分享，根据中国法律《信息网络传播权保护条例》第二十二条之规定，若资源存在侵权或相关问题请联系本站客服人员，zhiweidada#qq.com，请把#换成@，本站将给予最大的支持与配合，做到及时反馈和处理。关于更多版权及免责申明参见 版权及免责申明
本站所有资源不代表本站的观点或立场，基于网友分享，根据中国法律《信息网络传播权保护条例》第二十二条之规定，若资源存在侵权或相关问题请联系本站客服人员，zhiweidada#qq.com，请把#换成@，本站将给予最大的支持与配合，做到及时反馈和处理。关于更多版权及免责申明参见 版权及免责申明