行人再识别Person-reID的Pytorch实现-python源码

上传者: 42109125 | 上传时间: 2021-08-26 17:32:38 | 文件大小: 271KB | 文件类型: ZIP
行人再识别Person-reID的Pytorch实现 Person_reID_baseline_pytorch 一个小巧、友好、强大的 Person-reID 基线代码(基于 pytorch)。 强的。 它与几个顶级会议工作中的新基线结果一致,例如,用于人员重新识别的联合判别和生成学习(CVPR19)、超越部件模型:具有精细部件池的人员检索(ECCV18)、用于人员的相机风格适应重新识别(CVPR18)。 我们到达 Rank@1=88.24%, mAP=70.68% 仅使用 softmax 损失。 小的。 使用 fp16(由 Nvidia apex 支持),我们的基线可以仅使用 2GB GPU 内存进行训练。 友谊赛。 您可以使用现成的选项在一行中应用许多最先进的技巧。 此外,如果您不熟悉 person re-ID,您可以先查看我们的教程(8 分钟阅读):thumbs_up:。 目录 特性 一些新闻 训练模型先决条件 入门 安装 数据集准备 训练测试评估 使用其他数据集进行训练的技巧 引文 相关存储库功能 现在我们支持: Float16 以节省 GPU 内存,基于 a

文件下载

资源详情

[{"title":"( 36 个子文件 271KB ) 行人再识别Person-reID的Pytorch实现-python源码","children":[{"title":"Person_reID_baseline_pytorch-master","children":[{"title":".gitignore <span style='color:#111;'> 372B </span>","children":null,"spread":false},{"title":"circle_loss.py <span style='color:#111;'> 1.69KB </span>","children":null,"spread":false},{"title":"model","children":[{"title":".gitkeep <span style='color:#111;'> 1B </span>","children":null,"spread":false}],"spread":true},{"title":"show.png <span style='color:#111;'> 213.50KB </span>","children":null,"spread":false},{"title":"leaderboard","children":[{"title":"README.md <span style='color:#111;'> 17.73KB </span>","children":null,"spread":false}],"spread":true},{"title":".travis.yml <span style='color:#111;'> 681B </span>","children":null,"spread":false},{"title":"sitemap.xml <span style='color:#111;'> 79.90KB </span>","children":null,"spread":false},{"title":"LICENSE <span style='color:#111;'> 1.04KB </span>","children":null,"spread":false},{"title":"prepare.py <span style='color:#111;'> 3.58KB </span>","children":null,"spread":false},{"title":"prepare_static.py <span style='color:#111;'> 3.67KB </span>","children":null,"spread":false},{"title":".github","children":[{"title":"ISSUE_TEMPLATE","children":[{"title":"bug_report.md <span style='color:#111;'> 834B </span>","children":null,"spread":false},{"title":"feature_request.md <span style='color:#111;'> 595B </span>","children":null,"spread":false}],"spread":true}],"spread":true},{"title":"README.md <span style='color:#111;'> 14.73KB </span>","children":null,"spread":false},{"title":"prepare_viper.py <span style='color:#111;'> 2.44KB </span>","children":null,"spread":false},{"title":"random_erasing.py <span style='color:#111;'> 1.88KB </span>","children":null,"spread":false},{"title":"test.py <span style='color:#111;'> 8.79KB </span>","children":null,"spread":false},{"title":"tutorial","children":[{"title":"Answers_to_Quick_Questions.md <span style='color:#111;'> 3.02KB </span>","children":null,"spread":false},{"title":"README.md <span style='color:#111;'> 16.52KB </span>","children":null,"spread":false}],"spread":false},{"title":"demo.py <span style='color:#111;'> 3.64KB </span>","children":null,"spread":false},{"title":"evaluate.py <span style='color:#111;'> 3.34KB </span>","children":null,"spread":false},{"title":"evaluate_gpu.py <span style='color:#111;'> 3.64KB </span>","children":null,"spread":false},{"title":"evaluate_rerank.py <span style='color:#111;'> 2.67KB </span>","children":null,"spread":false},{"title":"GPU-Re-Ranking","children":[{"title":"utils.py <span style='color:#111;'> 3.48KB </span>","children":null,"spread":false},{"title":"README.md <span style='color:#111;'> 1.20KB </span>","children":null,"spread":false},{"title":"gnn_reranking.py <span style='color:#111;'> 1.74KB </span>","children":null,"spread":false},{"title":"evaluate_rerank_gpu.py <span style='color:#111;'> 2.10KB </span>","children":null,"spread":false},{"title":"extension","children":[{"title":"adjacency_matrix","children":[{"title":"setup.py <span style='color:#111;'> 1.11KB </span>","children":null,"spread":false},{"title":"build_adjacency_matrix.cpp <span style='color:#111;'> 640B </span>","children":null,"spread":false},{"title":"build_adjacency_matrix_kernel.cu <span style='color:#111;'> 1.16KB </span>","children":null,"spread":false}],"spread":false},{"title":"propagation","children":[{"title":"setup.py <span style='color:#111;'> 1.07KB </span>","children":null,"spread":false},{"title":"gnn_propagate.cpp <span style='color:#111;'> 693B </span>","children":null,"spread":false},{"title":"gnn_propagate_kernel.cu <span style='color:#111;'> 1.37KB </span>","children":null,"spread":false}],"spread":false},{"title":"make.sh <span style='color:#111;'> 85B </span>","children":null,"spread":false}],"spread":false}],"spread":false},{"title":"model.py <span style='color:#111;'> 8.33KB </span>","children":null,"spread":false},{"title":"re_ranking.py <span style='color:#111;'> 4.19KB </span>","children":null,"spread":false},{"title":"train.py <span style='color:#111;'> 15.18KB </span>","children":null,"spread":false}],"spread":false}],"spread":true}]

评论信息

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