重新实现RetinaFace使用C ++和TensorRT-C/C++开发

上传者: 42113754 | 上传时间: 2024-01-17 00:21:28 | 文件大小: 6.66MB | 文件类型: ZIP
RetinaFace C ++重新实现源参考资源RetinaFace带有python代码。 模型转换工具MXNet2Caffe您需要自己添加一些层,并且在caffe中没有upsam RetinaFace C ++重新实现源参考资源RetinaFace用python代码提供在Insightface中。 模型转换工具MXNet2Caffe您需要自己添加一些图层,并且在caffe中没有上采样,您可以用反卷积代替,并且可能会有一点精度损失。 来自mobilenet25的原始模型参考,我已经对其进行了重新培训。 演示$ mkdir build $ cd build / $ cmake ../ $使您需要修改CmakeList文件中的依赖路径。 测速硬件:1080Ti test1:mod

文件下载

资源详情

[{"title":"( 66 个子文件 6.66MB ) 重新实现RetinaFace使用C ++和TensorRT-C/C++开发","children":[{"title":"retinaface-master","children":[{"title":"INT8-Calibration-Tool","children":[{"title":"common","children":[{"title":"logger.h <span style='color:#111;'> 340B </span>","children":null,"spread":false},{"title":"helpercuda.h <span style='color:#111;'> 461B </span>","children":null,"spread":false},{"title":"aescrypto.h <span style='color:#111;'> 888B </span>","children":null,"spread":false},{"title":"logging.h <span style='color:#111;'> 14.83KB </span>","children":null,"spread":false},{"title":"aescrypto.cpp <span style='color:#111;'> 6.13KB </span>","children":null,"spread":false},{"title":"calcprelu.cu <span style='color:#111;'> 872B </span>","children":null,"spread":false},{"title":"logger.cpp <span style='color:#111;'> 1.41KB </span>","children":null,"spread":false}],"spread":true},{"title":"calibra.pro.user <span style='color:#111;'> 18.35KB </span>","children":null,"spread":false},{"title":"calibrationtable.cpp <span style='color:#111;'> 17.20KB </span>","children":null,"spread":false},{"title":"CalibrationTableImpl.h <span style='color:#111;'> 393B </span>","children":null,"spread":false},{"title":"CalibrationTableImpl.cpp <span style='color:#111;'> 1018B </span>","children":null,"spread":false},{"title":"CMakeLists.txt <span style='color:#111;'> 1.62KB </span>","children":null,"spread":false},{"title":"main.cpp <span style='color:#111;'> 523B </span>","children":null,"spread":false},{"title":"README.md <span style='color:#111;'> 2.01KB </span>","children":null,"spread":false},{"title":"calibra.pro <span style='color:#111;'> 2.22KB </span>","children":null,"spread":false},{"title":"calibrationtable.h <span style='color:#111;'> 10.60KB </span>","children":null,"spread":false}],"spread":true},{"title":"model","children":[{"title":"mnet-deconv-0517.table.int8 <span style='color:#111;'> 7.39KB </span>","children":null,"spread":false},{"title":"mnet25.caffemodel <span style='color:#111;'> 1.69MB </span>","children":null,"spread":false},{"title":"mnet-deconv-0517.caffemodel <span style='color:#111;'> 1.69MB </span>","children":null,"spread":false},{"title":"mnet-deconv-0517.prototxt <span style='color:#111;'> 41.39KB </span>","children":null,"spread":false},{"title":"mnet25.prototxt <span style='color:#111;'> 40.90KB </span>","children":null,"spread":false},{"title":"plot.gv.pdf <span style='color:#111;'> 28.93KB </span>","children":null,"spread":false}],"spread":true},{"title":".vscode","children":[{"title":"c_cpp_properties.json <span style='color:#111;'> 367B </span>","children":null,"spread":false},{"title":"settings.json <span style='color:#111;'> 1.31KB </span>","children":null,"spread":false}],"spread":true},{"title":"retinaface","children":[{"title":"RetinaFace.h <span style='color:#111;'> 2.57KB </span>","children":null,"spread":false},{"title":"tensorrt","children":[{"title":"trtretinafacenet.cpp <span style='color:#111;'> 7.24KB </span>","children":null,"spread":false},{"title":"trtnetbase.h <span style='color:#111;'> 6.08KB </span>","children":null,"spread":false},{"title":"trtutility.h <span style='color:#111;'> 1.39KB </span>","children":null,"spread":false},{"title":"trtretinafacenet.h <span style='color:#111;'> 1.87KB </span>","children":null,"spread":false},{"title":"trtnetbase.cpp <span style='color:#111;'> 8.61KB </span>","children":null,"spread":false}],"spread":true},{"title":"resizeconvertion.cu <span style='color:#111;'> 14.25KB </span>","children":null,"spread":false},{"title":"retinaface.pro <span style='color:#111;'> 2.17KB </span>","children":null,"spread":false},{"title":"main.cpp <span style='color:#111;'> 1.56KB </span>","children":null,"spread":false},{"title":"retinaface.pro.user <span style='color:#111;'> 18.35KB </span>","children":null,"spread":false},{"title":"timer.h <span style='color:#111;'> 1.51KB </span>","children":null,"spread":false},{"title":"RetinaFace.cpp <span style='color:#111;'> 38.50KB </span>","children":null,"spread":false}],"spread":true},{"title":"CMakeLists.txt <span style='color:#111;'> 3.79KB </span>","children":null,"spread":false},{"title":"LICENSE <span style='color:#111;'> 1.04KB </span>","children":null,"spread":false},{"title":"README.md <span style='color:#111;'> 4.59KB </span>","children":null,"spread":false},{"title":"data","children":[{"title":"retinaface-widerface测试.png <span style='color:#111;'> 220.85KB </span>","children":null,"spread":false},{"title":"img.jpg <span style='color:#111;'> 125.80KB </span>","children":null,"spread":false}],"spread":true},{"title":"MXNet2Caffe","children":[{"title":"predictor_caffe.py <span style='color:#111;'> 437B </span>","children":null,"spread":false},{"title":"check_results.py <span style='color:#111;'> 1.76KB </span>","children":null,"spread":false},{"title":"json2prototxt.py <span style='color:#111;'> 1.46KB </span>","children":null,"spread":false},{"title":"find_caffe.pyc <span style='color:#111;'> 422B </span>","children":null,"spread":false},{"title":"mxnet2caffe.py <span style='color:#111;'> 4.62KB </span>","children":null,"spread":false},{"title":"predictor_mxnet.py <span style='color:#111;'> 1.10KB </span>","children":null,"spread":false},{"title":"prototxt_basic.pyc <span style='color:#111;'> 6.58KB </span>","children":null,"spread":false},{"title":"model_mxnet","children":[{"title":"mnet.25-0000.params <span style='color:#111;'> 1.68MB </span>","children":null,"spread":false},{"title":"mnet.25-symbol.json <span style='color:#111;'> 119.69KB </span>","children":null,"spread":false}],"spread":false},{"title":"find_mxnet.pyc <span style='color:#111;'> 496B </span>","children":null,"spread":false},{"title":"LICENSE <span style='color:#111;'> 1.04KB </span>","children":null,"spread":false},{"title":"predictor_mxnet.pyc <span style='color:#111;'> 1.71KB </span>","children":null,"spread":false},{"title":"README.md <span style='color:#111;'> 310B </span>","children":null,"spread":false},{"title":"show_mxnet_graph.py <span style='color:#111;'> 573B </span>","children":null,"spread":false},{"title":"predictor_caffe.pyc <span style='color:#111;'> 1.19KB </span>","children":null,"spread":false},{"title":"__pycache__","children":[{"title":"find_caffe.cpython-35.pyc <span style='color:#111;'> 369B </span>","children":null,"spread":false},{"title":"predictor_caffe.cpython-35.pyc <span style='color:#111;'> 967B </span>","children":null,"spread":false},{"title":"prototxt_basic.cpython-35.pyc <span style='color:#111;'> 9.88KB </span>","children":null,"spread":false},{"title":"find_mxnet.cpython-35.pyc <span style='color:#111;'> 437B </span>","children":null,"spread":false},{"title":"predictor_mxnet.cpython-35.pyc <span style='color:#111;'> 1.39KB </span>","children":null,"spread":false}],"spread":false},{"title":"find_mxnet.py <span style='color:#111;'> 264B </span>","children":null,"spread":false},{"title":"prototxt_basic.py <span style='color:#111;'> 10.86KB </span>","children":null,"spread":false},{"title":"model_caffe","children":[{"title":"mnet.25.caffemodel1 <span style='color:#111;'> 1.69MB </span>","children":null,"spread":false},{"title":"mnet.25.prototxt1 <span style='color:#111;'> 40.90KB </span>","children":null,"spread":false}],"spread":false},{"title":"find_caffe.py <span style='color:#111;'> 185B </span>","children":null,"spread":false}],"spread":false}],"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