Python-PCBofpaper行人重识别

上传者: 39841856 | 上传时间: 2021-05-28 12:01:25 | 文件大小: 432KB | 文件类型: ZIP
来自清华大学,文章贡献在于无需使用格外的处理,例如姿态估计、ROI区域的检测等等,简单方便。针对因检测到的行人图像存在遮挡、不完整、分辨率低等问题而导致重识别精度差,本文提出了如下解决思路:1. 通过基模型的特征提取部分,来提取行人图像的特征图,将特征图水平切成六部分,每部分单独全局平均池化(GAP),再利用1*1的卷积核降维,分别输入到对应的全连接层进行预测。

文件下载

资源详情

[{"title":"( 44 个子文件 432KB ) Python-PCBofpaper行人重识别","children":[{"title":"beyond-part-models-master","children":[{"title":".gitignore <span style='color:#111;'> 22B </span>","children":null,"spread":false},{"title":"requirements.txt <span style='color:#111;'> 127B </span>","children":null,"spread":false},{"title":"bpm","children":[{"title":"model","children":[{"title":"__init__.py <span style='color:#111;'> 0B </span>","children":null,"spread":false},{"title":"PCBModel.py <span style='color:#111;'> 1.96KB </span>","children":null,"spread":false},{"title":"resnet.py <span style='color:#111;'> 6.27KB </span>","children":null,"spread":false}],"spread":true},{"title":"dataset","children":[{"title":"TrainSet.py <span style='color:#111;'> 1.76KB </span>","children":null,"spread":false},{"title":"__init__.py <span style='color:#111;'> 3.23KB </span>","children":null,"spread":false},{"title":"Prefetcher.py <span style='color:#111;'> 6.65KB </span>","children":null,"spread":false},{"title":"TestSet.py <span style='color:#111;'> 9.08KB </span>","children":null,"spread":false},{"title":"Dataset.py <span style='color:#111;'> 1.49KB </span>","children":null,"spread":false},{"title":"PreProcessImage.py <span style='color:#111;'> 4.09KB </span>","children":null,"spread":false}],"spread":true},{"title":"__init__.py <span style='color:#111;'> 0B </span>","children":null,"spread":false},{"title":"utils","children":[{"title":"visualization.py <span style='color:#111;'> 4.17KB </span>","children":null,"spread":false},{"title":"__init__.py <span style='color:#111;'> 0B </span>","children":null,"spread":false},{"title":"dataset_utils.py <span style='color:#111;'> 4.08KB </span>","children":null,"spread":false},{"title":"utils.py <span style='color:#111;'> 16.89KB </span>","children":null,"spread":false},{"title":"metric.py <span style='color:#111;'> 6.18KB </span>","children":null,"spread":false},{"title":"re_ranking.py <span style='color:#111;'> 4.10KB </span>","children":null,"spread":false},{"title":"distance.py <span style='color:#111;'> 1.21KB </span>","children":null,"spread":false}],"spread":true}],"spread":true},{"title":"example_rank_lists_on_Market1501","children":[{"title":"00001199_0001_00000008.jpg <span style='color:#111;'> 25.96KB </span>","children":null,"spread":false},{"title":"00000920_0003_00000002.jpg <span style='color:#111;'> 24.50KB </span>","children":null,"spread":false},{"title":"00001009_0001_00000004.jpg <span style='color:#111;'> 23.00KB </span>","children":null,"spread":false},{"title":"00001299_0001_00000004.jpg <span style='color:#111;'> 24.61KB </span>","children":null,"spread":false},{"title":"00001399_0003_00000006.jpg <span style='color:#111;'> 24.53KB </span>","children":null,"spread":false},{"title":"00000881_0002_00000006.jpg <span style='color:#111;'> 24.75KB </span>","children":null,"spread":false},{"title":"00000492_0005_00000001.jpg <span style='color:#111;'> 23.35KB </span>","children":null,"spread":false},{"title":"00000305_0001_00000001.jpg <span style='color:#111;'> 24.49KB </span>","children":null,"spread":false},{"title":"00001494_0003_00000002.jpg <span style='color:#111;'> 23.95KB </span>","children":null,"spread":false},{"title":"00001035_0005_00000001.jpg <span style='color:#111;'> 24.55KB </span>","children":null,"spread":false},{"title":"00001399_0005_00000002.jpg <span style='color:#111;'> 24.87KB </span>","children":null,"spread":false},{"title":"00000156_0003_00000009.jpg <span style='color:#111;'> 25.10KB </span>","children":null,"spread":false},{"title":"00001494_0006_00000001.jpg <span style='color:#111;'> 23.77KB </span>","children":null,"spread":false},{"title":"00001046_0002_00000002.jpg <span style='color:#111;'> 20.64KB </span>","children":null,"spread":false},{"title":"00001090_0006_00000004.jpg <span style='color:#111;'> 27.02KB </span>","children":null,"spread":false},{"title":"00001131_0003_00000005.jpg <span style='color:#111;'> 22.52KB </span>","children":null,"spread":false}],"spread":false},{"title":"README.md <span style='color:#111;'> 13.88KB </span>","children":null,"spread":false},{"title":"script","children":[{"title":"dataset","children":[{"title":"mapping_im_names_duke.py <span style='color:#111;'> 3.32KB </span>","children":null,"spread":false},{"title":"transform_market1501.py <span style='color:#111;'> 6.24KB </span>","children":null,"spread":false},{"title":"mapping_im_names_market1501.py <span style='color:#111;'> 4.80KB </span>","children":null,"spread":false},{"title":"combine_trainval_sets.py <span style='color:#111;'> 3.77KB </span>","children":null,"spread":false},{"title":"transform_cuhk03.py <span style='color:#111;'> 5.90KB </span>","children":null,"spread":false},{"title":"transform_duke.py <span style='color:#111;'> 4.90KB </span>","children":null,"spread":false}],"spread":true},{"title":"experiment","children":[{"title":"visualize_rank_list.py <span style='color:#111;'> 7.72KB </span>","children":null,"spread":false},{"title":"train_pcb.py <span style='color:#111;'> 14.70KB </span>","children":null,"spread":false}],"spread":true}],"spread":true}],"spread":true}],"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