Mate:基于MatConvNet的MATLAB中面向对象的CPUGPU ConvNets-源码
＃伴侣
Maté是一个用于 ConvNets（卷积神经网络）的 MATLAB 库。 Maté 源自 。 Maté 使用 MatConvNet 例程进行多个时间关键操作，并且可以加载和操作由提供的预。
Maté 是面向对象的，其目标是简化原型设计和实验，特别是尽量减少尝试新的非标准层和新的非标准网络图所需的努力。
Maté 延续了以与咖啡因相关的命名 ConvNet 库的传统。 其他也启发了 Maté 的此类库包括 （Python、CPU）和 （具有接口的 C++、CPU/GPU）。
##Functionality Maté 提供以下功能：
新层的简单定义（只需定义前向过程，如果需要，后向过程；在 MATLAB 中通常需要几行）。
在 MATLAB 代码中轻松定义和训练非链网络（可以使用任何有向无环图）。
轻松加载和操作预训练网络。
借助 MATLAB Parallel Too
文件下载
资源详情
[{"title":"（ 62 个子文件 43KB ） Mate:基于MatConvNet的MATLAB中面向对象的CPUGPU ConvNets-源码","children":[{"title":"Mate-master","children":[{"title":"toolbox","children":[{"title":"MateAllDistLayer.m <span style='color:#111;'> 422B </span>","children":null,"spread":false},{"title":"MateScalarProductLayer.m <span style='color:#111;'> 484B </span>","children":null,"spread":false},{"title":"MateSliceLayer.m <span style='color:#111;'> 750B </span>","children":null,"spread":false},{"title":"MateFlattenLayer.m <span style='color:#111;'> 360B </span>","children":null,"spread":false},{"title":"MateNNAccuracyLayer.m <span style='color:#111;'> 809B </span>","children":null,"spread":false},{"title":"MateDoubleMarginLossLayer.m <span style='color:#111;'> 922B </span>","children":null,"spread":false},{"title":"MateBilinearAllDistLayer.m <span style='color:#111;'> 531B </span>","children":null,"spread":false},{"title":"MateArgmaxCounterLayer.m <span style='color:#111;'> 700B </span>","children":null,"spread":false},{"title":"MateLayer.m <span style='color:#111;'> 4.83KB </span>","children":null,"spread":false},{"title":"extra","children":[{"title":"getPlate.m <span style='color:#111;'> 1.36KB </span>","children":null,"spread":false},{"title":"readMatConvNet.m <span style='color:#111;'> 1.91KB </span>","children":null,"spread":false}],"spread":true},{"title":"MateMetricHingeLossLayer.m <span style='color:#111;'> 1.02KB </span>","children":null,"spread":false},{"title":"MateWeightedLogisticLossLayer.m <span style='color:#111;'> 778B </span>","children":null,"spread":false},{"title":"MateFullLayer.m <span style='color:#111;'> 910B </span>","children":null,"spread":false},{"title":"MateAllProdLayer.m <span style='color:#111;'> 301B </span>","children":null,"spread":false},{"title":"MateBilinearLayer.m <span style='color:#111;'> 978B </span>","children":null,"spread":false},{"title":"MateMaxLayer.m <span style='color:#111;'> 641B </span>","children":null,"spread":false},{"title":"MateSoftmaxLossLayer.m <span style='color:#111;'> 760B </span>","children":null,"spread":false},{"title":"MateSqueezeLayer.m <span style='color:#111;'> 319B </span>","children":null,"spread":false},{"title":"MateFeatureOffsetLayer.m <span style='color:#111;'> 725B </span>","children":null,"spread":false},{"title":"MatePreprocessImageLayer.m <span style='color:#111;'> 869B </span>","children":null,"spread":false},{"title":"MatePairwiseDistLayer.m <span style='color:#111;'> 509B </span>","children":null,"spread":false},{"title":"MateSplitLayer.m <span style='color:#111;'> 567B </span>","children":null,"spread":false},{"title":"MateSoftmaxWithBalancingLayer.m <span style='color:#111;'> 692B </span>","children":null,"spread":false},{"title":"MateL2NormalizeLayer.m <span style='color:#111;'> 755B </span>","children":null,"spread":false},{"title":"MateCatLayer.m <span style='color:#111;'> 846B </span>","children":null,"spread":false},{"title":"MateSumMergeLayer.m <span style='color:#111;'> 606B </span>","children":null,"spread":false},{"title":"MateMultilabelErrorLayer.m <span style='color:#111;'> 494B </span>","children":null,"spread":false},{"title":"MateSoftmaxLayer.m <span style='color:#111;'> 539B </span>","children":null,"spread":false},{"title":"@MateNet","children":[{"title":"init.m <span style='color:#111;'> 5.66KB </span>","children":null,"spread":false},{"title":"getBlob.m <span style='color:#111;'> 178B </span>","children":null,"spread":false},{"title":"disp.m <span style='color:#111;'> 199B </span>","children":null,"spread":false},{"title":"dispBlob.m <span style='color:#111;'> 905B </span>","children":null,"spread":false},{"title":"dispLayer.m <span style='color:#111;'> 170B </span>","children":null,"spread":false},{"title":"dispTimes.m <span style='color:#111;'> 722B </span>","children":null,"spread":false},{"title":"makePass.m <span style='color:#111;'> 2.79KB </span>","children":null,"spread":false},{"title":"getLayer.m <span style='color:#111;'> 120B </span>","children":null,"spread":false},{"title":"trainNet.m <span style='color:#111;'> 6.09KB </span>","children":null,"spread":false},{"title":"MateNet.m <span style='color:#111;'> 2.02KB </span>","children":null,"spread":false},{"title":"move.m <span style='color:#111;'> 578B </span>","children":null,"spread":false}],"spread":false},{"title":"MateParams.m <span style='color:#111;'> 281B </span>","children":null,"spread":false},{"title":"MateFeatureNormLayer.m <span style='color:#111;'> 617B </span>","children":null,"spread":false},{"title":"MateRankErrorLayer.m <span style='color:#111;'> 927B </span>","children":null,"spread":false},{"title":"MateReluLayer.m <span style='color:#111;'> 331B </span>","children":null,"spread":false},{"title":"MateArgmaxLayer.m <span style='color:#111;'> 712B </span>","children":null,"spread":false},{"title":"MateLogisticLossLayer.m <span style='color:#111;'> 740B </span>","children":null,"spread":false},{"title":"MatePoolLayer.m <span style='color:#111;'> 641B </span>","children":null,"spread":false},{"title":"MateConvLayer.m <span style='color:#111;'> 814B </span>","children":null,"spread":false},{"title":"MateDropoutLayer.m <span style='color:#111;'> 1010B </span>","children":null,"spread":false},{"title":"MateLogLossLayer.m <span style='color:#111;'> 707B </span>","children":null,"spread":false}],"spread":false},{"title":"docs","children":[{"title":"network.md <span style='color:#111;'> 6.36KB </span>","children":null,"spread":false},{"title":"training.md <span style='color:#111;'> 3.73KB </span>","children":null,"spread":false},{"title":"pretrained.md <span style='color:#111;'> 1.44KB </span>","children":null,"spread":false},{"title":"catalog.md <span style='color:#111;'> 80B </span>","children":null,"spread":false},{"title":"layer.md <span style='color:#111;'> 3.50KB </span>","children":null,"spread":false}],"spread":true},{"title":"examples","children":[{"title":"MateUsePretrained.m <span style='color:#111;'> 1.31KB </span>","children":null,"spread":false},{"title":"MateMnistSiamese.m <span style='color:#111;'> 5.29KB </span>","children":null,"spread":false},{"title":"MateMnistClassify.m <span style='color:#111;'> 2.63KB </span>","children":null,"spread":false},{"title":"getMnistImdb.m <span style='color:#111;'> 1.32KB </span>","children":null,"spread":false},{"title":"MateMnistAllDist.m <span style='color:#111;'> 3.25KB </span>","children":null,"spread":false}],"spread":true},{"title":"README.md <span style='color:#111;'> 2.06KB </span>","children":null,"spread":false},{"title":"setup.m <span style='color:#111;'> 131B </span>","children":null,"spread":false}],"spread":true}],"spread":true}]
评论信息
其他资源
- The NURBS Book 2nd.pdf
- PLC通用读写HslCommunication DEMO
- secoclient-win-64-7.0.2.33.rar
- UCI经典分类二分类数据集
- 死锁环路判定的系统资源分配图约简算法的设计与实现
- 载荷谱雨流处理
- 南大 南京大学计算机软件复试面试常问问题.rar
- mfc 串口数据绘曲线图
- (Multisim数电仿真指导）与非门逻辑功能测试及组成其它门电路
- 焓熵值计算软件
- 基于web数据库图书管理信息系统设计与实现(源程序)
- VC远程桌面监控(C/S客户端和服务端)
- webmagic修复HTTPS下无法抓取只支持TLSv1.2的站点的bug重新打包jar
- 新型超高速全息照相
- (亲测首发)新版漫画小程序可二开
- 校内实习管理系统
- 易通无线对讲机写频软件
- 基于web的毕业设计管理系统的设计与开发
- Android来电防火墙
- 个人博客系统项目源码
- 恒模滤波算法针对4QAM
- Spire.XLS 8.8.1 去水印
- 基于云计算环境的蚁群优化计算资源分配算法
- 基于C语言STC89C52单片机电子密码锁的设计与仿真
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
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