CompositionalNets:正式执行CVPR2020文件

上传者: 42116794 | 上传时间: 2023-02-27 20:17:14 | 文件大小: 1.92MB | 文件类型: ZIP
组成卷积神经网络:具有对部分遮挡的固有鲁棒性的深度架构[CVPR-2020] Compositional Convolutional Neural Networks: A Deep Architecture with Innate Robustness to Partial Occlusion Adam Kortylewski, Ju He, Qing Liu, Alan Yuille CVPR 2020 发行说明 这是我们原始代码从Tensorflow到PyTorch的移植。 与原始代码库相比,该代码更快,更干净。 结果与本文报道的结果略有不同。 特别是,对于低咬合,性能会稍低一些,而对于较强的咬合,性能会稍高一些。 平均而言,结果比论文中报道的要好。 目前,我们提供了从VGG-16 pool5层进行训练的CompositionalNets的预训练模型。 应当可能为其他骨干和层训练C

文件下载

资源详情

[{"title":"( 41 个子文件 1.92MB ) CompositionalNets:正式执行CVPR2020文件","children":[{"title":"CompositionalNets-master","children":[{"title":"requirements.txt <span style='color:#111;'> 128B </span>","children":null,"spread":false},{"title":"data","children":[{"title":"README.md <span style='color:#111;'> 27B </span>","children":null,"spread":false}],"spread":true},{"title":"models","children":[{"title":"README.md <span style='color:#111;'> 40B </span>","children":null,"spread":false}],"spread":true},{"title":"Code","children":[{"title":"eval_occlusion_localization.py <span style='color:#111;'> 10.75KB </span>","children":null,"spread":false},{"title":"vMFMM.py <span style='color:#111;'> 2.99KB </span>","children":null,"spread":false},{"title":"config.py <span style='color:#111;'> 8.62KB </span>","children":null,"spread":false},{"title":"test.py <span style='color:#111;'> 4.78KB </span>","children":null,"spread":false},{"title":"lib","children":[{"title":"ops_test.py <span style='color:#111;'> 1.38KB </span>","children":null,"spread":false},{"title":"ops.py <span style='color:#111;'> 1.41KB </span>","children":null,"spread":false}],"spread":true},{"title":"demo.py <span style='color:#111;'> 3.57KB </span>","children":null,"spread":false},{"title":"helpers.py <span style='color:#111;'> 10.07KB </span>","children":null,"spread":false},{"title":"model.py <span style='color:#111;'> 17.36KB </span>","children":null,"spread":false},{"title":"losses.py <span style='color:#111;'> 455B </span>","children":null,"spread":false},{"title":"train.py <span style='color:#111;'> 9.10KB </span>","children":null,"spread":false}],"spread":true},{"title":"README.md <span style='color:#111;'> 5.08KB </span>","children":null,"spread":false},{"title":"demo","children":[{"title":"487059_4_train2017.jpg <span style='color:#111;'> 26.66KB </span>","children":null,"spread":false},{"title":"487059_4_train2017_predclass_motorbike_and_occluder_map.jpg <span style='color:#111;'> 32.52KB </span>","children":null,"spread":false},{"title":"81819_0_train2017_predclass_bus_and_occluder_map.jpg <span style='color:#111;'> 72.26KB </span>","children":null,"spread":false},{"title":"17029_0_val2017_predclass_car_and_occluder_map.jpg <span style='color:#111;'> 79.23KB </span>","children":null,"spread":false},{"title":"81819_0_train2017.jpg <span style='color:#111;'> 55.83KB </span>","children":null,"spread":false},{"title":"17029_0_val2017.jpg <span style='color:#111;'> 64.39KB </span>","children":null,"spread":false}],"spread":true},{"title":"background_images","children":[{"title":"nature_general.JPEG <span style='color:#111;'> 86.26KB </span>","children":null,"spread":false},{"title":"nature_noise.JPEG <span style='color:#111;'> 204.04KB </span>","children":null,"spread":false},{"title":"nature_white.JPEG <span style='color:#111;'> 40.54KB </span>","children":null,"spread":false},{"title":"coast_general.JPEG <span style='color:#111;'> 31.72KB </span>","children":null,"spread":false},{"title":"coast_noise.JPEG <span style='color:#111;'> 164.18KB </span>","children":null,"spread":false},{"title":"street_general.JPEG <span style='color:#111;'> 121.54KB </span>","children":null,"spread":false},{"title":"street2_noise.JPEG <span style='color:#111;'> 197.44KB </span>","children":null,"spread":false},{"title":"street2_white.JPEG <span style='color:#111;'> 33.75KB </span>","children":null,"spread":false},{"title":"street_noise.JPEG <span style='color:#111;'> 215.80KB </span>","children":null,"spread":false},{"title":"coast_white.JPEG <span style='color:#111;'> 20.88KB </span>","children":null,"spread":false},{"title":"nature2_noise.JPEG <span style='color:#111;'> 196.19KB </span>","children":null,"spread":false},{"title":"nature2_white.JPEG <span style='color:#111;'> 52.46KB </span>","children":null,"spread":false},{"title":"nature2_general.JPEG <span style='color:#111;'> 122.08KB </span>","children":null,"spread":false},{"title":"street2_general.JPEG <span style='color:#111;'> 82.71KB </span>","children":null,"spread":false},{"title":"street_white.JPEG <span style='color:#111;'> 52.67KB </span>","children":null,"spread":false}],"spread":false},{"title":"Initialization_Code","children":[{"title":"vMF_clustering.py <span style='color:#111;'> 4.36KB </span>","children":null,"spread":false},{"title":"Learn_mix_model_vMF_view.py <span style='color:#111;'> 9.16KB </span>","children":null,"spread":false},{"title":"config_initialization.py <span style='color:#111;'> 1.60KB </span>","children":null,"spread":false},{"title":"vcdist_funcs.py <span style='color:#111;'> 7.62KB </span>","children":null,"spread":false},{"title":"comptSimMat.py <span style='color:#111;'> 4.20KB </span>","children":null,"spread":false}],"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