68-Retinaface-Pytorch-version:使用带有MobileNet 0.25的RetinaFace进行6896个地标检测

上传者: 42134143 | 上传时间: 2024-03-14 19:40:41 | 文件大小: 3.29MB | 文件类型: ZIP
视网膜面火炬版 由于机密性,它不是我模型的最佳版本 感谢Alvin Yang( ) 这是68个地标检测的分支,预先训练的模型位于./out中 进行96个地标检测(请参阅其他分支) 该模型还预测了地标的被遮挡部分,如果不希望它们出现,可以将其隐藏。 基于RetinaFace 当前模型 mobileNet V1 + FPN +上下文模块+回归器1.6MB CPU〜10FPS GPU 50FPU 火车:(请参考dataloader.py更改文件位置) python3 train.py -train该模型使用LS3D-W数据集,或将您的数据集更改为demo.pt/ demo.jpg(68 * 2张量)的格式 使用本地摄像头: python3 video_detect.py(需要删除所有'cuda()',并在CPU本地运行) 评估模型: python3 train.py -train错

文件下载

资源详情

[{"title":"( 24 个子文件 3.29MB ) 68-Retinaface-Pytorch-version:使用带有MobileNet 0.25的RetinaFace进行6896个地标检测","children":[{"title":"68-Retinaface-Pytorch-version-master","children":[{"title":"video_detect.py <span style='color:#111;'> 4.04KB </span>","children":null,"spread":false},{"title":"train.py <span style='color:#111;'> 7.53KB </span>","children":null,"spread":false},{"title":"dataloader.py <span style='color:#111;'> 22.85KB </span>","children":null,"spread":false},{"title":"test_argu.py <span style='color:#111;'> 3.91KB </span>","children":null,"spread":false},{"title":"network.torch <span style='color:#111;'> 1.71MB </span>","children":null,"spread":false},{"title":"anchors.py <span style='color:#111;'> 3.00KB </span>","children":null,"spread":false},{"title":"detect.py <span style='color:#111;'> 3.42KB </span>","children":null,"spread":false},{"title":"utils.py <span style='color:#111;'> 13.05KB </span>","children":null,"spread":false},{"title":"model.py <span style='color:#111;'> 16.67KB </span>","children":null,"spread":false},{"title":"mobile_testing.py <span style='color:#111;'> 17.40KB </span>","children":null,"spread":false},{"title":"requirements.txt <span style='color:#111;'> 171B </span>","children":null,"spread":false},{"title":"mnas.py <span style='color:#111;'> 7.12KB </span>","children":null,"spread":false},{"title":"mobile.py <span style='color:#111;'> 9.09KB </span>","children":null,"spread":false},{"title":"assets","children":[{"title":"2.jpg <span style='color:#111;'> 66.88KB </span>","children":null,"spread":false},{"title":"1.jpg <span style='color:#111;'> 96.11KB </span>","children":null,"spread":false},{"title":"3.jpg <span style='color:#111;'> 115.01KB </span>","children":null,"spread":false}],"spread":false},{"title":"losses.py <span style='color:#111;'> 10.94KB </span>","children":null,"spread":false},{"title":"README.md <span style='color:#111;'> 1.21KB </span>","children":null,"spread":false},{"title":"eval_widerface.py <span style='color:#111;'> 5.32KB </span>","children":null,"spread":false},{"title":"down.py <span style='color:#111;'> 706B </span>","children":null,"spread":false},{"title":"img_tester.py <span style='color:#111;'> 4.27KB </span>","children":null,"spread":false},{"title":"magic_convert.py <span style='color:#111;'> 8.23KB </span>","children":null,"spread":false},{"title":"torchvision_model.py <span style='color:#111;'> 19.06KB </span>","children":null,"spread":false},{"title":"out","children":[{"title":"stage_5_68_full_model_epoch_121.pt <span style='color:#111;'> 1.59MB </span>","children":null,"spread":false}],"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