Pytorch_Retinaface:使用mobilenet0.25,Retinaface在宽面硬值中获得80.99%

上传者: 42144366 | 上传时间: 2022-05-19 21:26:54 | 文件大小: 2.22MB | 文件类型: ZIP
PyTorch中的RetinaFace 实现:。 当Retinaface使用mobilenet0.25作为骨干网时,模型大小仅为1.7M。 我们还提供resnet50作为骨干网以获得更好的结果。 Mxnet中的官方代码可以在找到。 移动或边缘设备部署 从python培训到C ++推理,我们还在为边缘设备提供了一套面部检测器。 使用Resnet50作为骨干网时,单规模的WiderFaceVal性能。 风格 简单的 中等的 难的 Pytorch(与Mxnet相同的参数) 94.82% 93.84% 89.60% pytorch(原始图像比例) 95.48% 94.04% 84.43% 网际网路 94.86% 93.87% 88.33% Mxnet(原始图像比例) 94.97% 93.89% 82.27% 使用Mobilenet0.25作为骨干网时,单规模的Wi

文件下载

资源详情

[{"title":"( 36 个子文件 2.22MB ) Pytorch_Retinaface:使用mobilenet0.25,Retinaface在宽面硬值中获得80.99%","children":[{"title":"Pytorch_Retinaface-master","children":[{"title":"data","children":[{"title":"__init__.py <span style='color:#111;'> 112B </span>","children":null,"spread":false},{"title":"config.py <span style='color:#111;'> 928B </span>","children":null,"spread":false},{"title":"FDDB","children":[{"title":"img_list.txt <span style='color:#111;'> 64.70KB </span>","children":null,"spread":false}],"spread":true},{"title":"wider_face.py <span style='color:#111;'> 3.32KB </span>","children":null,"spread":false},{"title":"data_augment.py <span style='color:#111;'> 6.91KB </span>","children":null,"spread":false}],"spread":true},{"title":"widerface_evaluate","children":[{"title":"setup.py <span style='color:#111;'> 328B </span>","children":null,"spread":false},{"title":"box_overlaps.pyx <span style='color:#111;'> 1.71KB </span>","children":null,"spread":false},{"title":"ground_truth","children":[{"title":"wider_face_val.mat <span style='color:#111;'> 388.45KB </span>","children":null,"spread":false},{"title":"wider_easy_val.mat <span style='color:#111;'> 399.45KB </span>","children":null,"spread":false},{"title":"wider_hard_val.mat <span style='color:#111;'> 414.15KB </span>","children":null,"spread":false},{"title":"wider_medium_val.mat <span style='color:#111;'> 403.05KB </span>","children":null,"spread":false}],"spread":true},{"title":"README.md <span style='color:#111;'> 507B </span>","children":null,"spread":false},{"title":"evaluation.py <span style='color:#111;'> 8.81KB </span>","children":null,"spread":false}],"spread":true},{"title":"layers","children":[{"title":"functions","children":[{"title":"prior_box.py <span style='color:#111;'> 1.30KB </span>","children":null,"spread":false}],"spread":true},{"title":"__init__.py <span style='color:#111;'> 48B </span>","children":null,"spread":false},{"title":"modules","children":[{"title":"__init__.py <span style='color:#111;'> 68B </span>","children":null,"spread":false},{"title":"multibox_loss.py <span style='color:#111;'> 5.15KB </span>","children":null,"spread":false}],"spread":true}],"spread":true},{"title":"models","children":[{"title":"__init__.py <span style='color:#111;'> 0B </span>","children":null,"spread":false},{"title":"net.py <span style='color:#111;'> 4.49KB </span>","children":null,"spread":false},{"title":"retinaface.py <span style='color:#111;'> 4.75KB </span>","children":null,"spread":false}],"spread":true},{"title":"convert_to_onnx.py <span style='color:#111;'> 3.48KB </span>","children":null,"spread":false},{"title":"test_widerface.py <span style='color:#111;'> 8.99KB </span>","children":null,"spread":false},{"title":"utils","children":[{"title":"nms","children":[{"title":"__init__.py <span style='color:#111;'> 0B </span>","children":null,"spread":false},{"title":"py_cpu_nms.py <span style='color:#111;'> 1.03KB </span>","children":null,"spread":false}],"spread":true},{"title":"__init__.py <span style='color:#111;'> 0B </span>","children":null,"spread":false},{"title":"timer.py <span style='color:#111;'> 1.08KB </span>","children":null,"spread":false},{"title":"box_utils.py <span style='color:#111;'> 12.95KB </span>","children":null,"spread":false}],"spread":true},{"title":"README.md <span style='color:#111;'> 5.02KB </span>","children":null,"spread":false},{"title":"curve","children":[{"title":"Widerface.jpg <span style='color:#111;'> 220.71KB </span>","children":null,"spread":false},{"title":"test.jpg <span style='color:#111;'> 108.16KB </span>","children":null,"spread":false},{"title":"FDDB.png <span style='color:#111;'> 83.71KB </span>","children":null,"spread":false},{"title":"1.jpg <span style='color:#111;'> 246.53KB </span>","children":null,"spread":false}],"spread":true},{"title":"test_fddb.py <span style='color:#111;'> 8.37KB </span>","children":null,"spread":false},{"title":"LICENSE.MIT <span style='color:#111;'> 1.03KB </span>","children":null,"spread":false},{"title":"detect.py <span style='color:#111;'> 6.57KB </span>","children":null,"spread":false},{"title":"train.py <span style='color:#111;'> 5.74KB </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