matlab特征点代码-LearningWithoutForgetting:ECCV2016的“不忘学习”资料库

上传者: 38499732 | 上传时间: 2023-05-04 13:48:38 | 文件大小: 86KB | 文件类型: ZIP
matlab特征点代码不忘学习 由伊利诺伊大学厄巴纳-香槟分校和在此创建。 项目 。 有关此存储库的任何问题,请联系。 注意:此存储库是使用MatConvNet实现的。 对于PyTorch版本,我的同事Arun Mallya的存储库中有一个。 如果您决定改用他的代码,请同时引用两篇论文。 介绍 永不忘记的学习旨在向现有的卷积神经网络添加新功能(新任务),与原始功能(旧任务)共享表示,同时允许调整共享表示以适应两项任务,而无需使用原始训练数据。 由此产生的网络仅对新任务进行完全微调,表现出比广泛使用的方法更好的实践。 它也胜过特征提取,但仅在新任务性能上。 可以在中找到更详细的摘要。 该软件旨在复制我们的方法。 我们使用图书馆。 用法 该代码已在Linux(64位Arch Linux 4.4.5-1-ARCH)上进行了测试 先决条件 Matlab(已针对R2015b测试) MatConvNet v1.0-beta13 为了支持GPU,我们使用TITAN X和CUDA 7.5。 安装 使用其安装指南相应地编译MatConvNet。 下载要在其上进行实验的数据集,并进行适当放置。 (请参见数

文件下载

资源详情

[{"title":"( 45 个子文件 86KB ) matlab特征点代码-LearningWithoutForgetting:ECCV2016的“不忘学习”资料库","children":[{"title":"LearningWithoutForgetting-release","children":[{"title":"getBatchWrapper.m <span style='color:#111;'> 5.77KB </span>","children":null,"spread":false},{"title":".gitignore <span style='color:#111;'> 17B </span>","children":null,"spread":false},{"title":"convertcaffe","children":[{"title":"deploy_edited.prototxt <span style='color:#111;'> 3.74KB </span>","children":null,"spread":false},{"title":"genmat.sh <span style='color:#111;'> 415B </span>","children":null,"spread":false},{"title":"export_matconvnet.m <span style='color:#111;'> 2.09KB </span>","children":null,"spread":false},{"title":"README <span style='color:#111;'> 289B </span>","children":null,"spread":false}],"spread":true},{"title":"clsCnt2ClsWeight.m <span style='color:#111;'> 478B </span>","children":null,"spread":false},{"title":"resetNetMomentum.m <span style='color:#111;'> 1.34KB </span>","children":null,"spread":false},{"title":"IMDBAddVOCPerson.m <span style='color:#111;'> 3.38KB </span>","children":null,"spread":false},{"title":"IMDBAddMNIST.m <span style='color:#111;'> 4.42KB </span>","children":null,"spread":false},{"title":"IMDBAddVOCtrval.m <span style='color:#111;'> 701B </span>","children":null,"spread":false},{"title":"getConfMat.m <span style='color:#111;'> 1.99KB </span>","children":null,"spread":false},{"title":"forkAlexNet.m <span style='color:#111;'> 9.88KB </span>","children":null,"spread":false},{"title":"cnn_customtrain.m <span style='color:#111;'> 42.30KB </span>","children":null,"spread":false},{"title":"IMDBAddPlaces2.m <span style='color:#111;'> 2.58KB </span>","children":null,"spread":false},{"title":"vl_customnn_move.m <span style='color:#111;'> 1.39KB </span>","children":null,"spread":false},{"title":"VOCAveragePrecision.m <span style='color:#111;'> 1.84KB </span>","children":null,"spread":false},{"title":"LICENSE <span style='color:#111;'> 1.92KB </span>","children":null,"spread":false},{"title":"vl_nnsoftmaxdiff.m <span style='color:#111;'> 5.32KB </span>","children":null,"spread":false},{"title":"Pushme.m <span style='color:#111;'> 1.35KB </span>","children":null,"spread":false},{"title":"README.md <span style='color:#111;'> 6.67KB </span>","children":null,"spread":false},{"title":"chkmkdir.m <span style='color:#111;'> 305B </span>","children":null,"spread":false},{"title":"getPath.m <span style='color:#111;'> 4.36KB </span>","children":null,"spread":false},{"title":"constructNewLayer.m <span style='color:#111;'> 1.21KB </span>","children":null,"spread":false},{"title":"trimIMDBforBatch.m <span style='color:#111;'> 1.59KB </span>","children":null,"spread":false},{"title":"vl_nnlogregloss.m <span style='color:#111;'> 2.11KB </span>","children":null,"spread":false},{"title":"IMDBAddMIT67.m <span style='color:#111;'> 2.93KB </span>","children":null,"spread":false},{"title":"IMDBAddImageNet.m <span style='color:#111;'> 4.25KB </span>","children":null,"spread":false},{"title":"expandAlexNet.m <span style='color:#111;'> 9.84KB </span>","children":null,"spread":false},{"title":"dimensionalizeLabel.m <span style='color:#111;'> 720B </span>","children":null,"spread":false},{"title":"IMDBAddCUB.m <span style='color:#111;'> 2.68KB </span>","children":null,"spread":false},{"title":"snippets","children":[{"title":"convert_CUB_old.py <span style='color:#111;'> 730B </span>","children":null,"spread":false},{"title":"visualizeTest.m <span style='color:#111;'> 7.44KB </span>","children":null,"spread":false},{"title":"savePDF.m <span style='color:#111;'> 318B </span>","children":null,"spread":false},{"title":"gridSearchPASCAL.m <span style='color:#111;'> 27.84KB </span>","children":null,"spread":false},{"title":"paperFigures.m <span style='color:#111;'> 8.88KB </span>","children":null,"spread":false},{"title":"slidesFigures.m <span style='color:#111;'> 6.58KB </span>","children":null,"spread":false},{"title":"evalNet.m <span style='color:#111;'> 8.50KB </span>","children":null,"spread":false},{"title":"MIT_wrongformat.txt <span style='color:#111;'> 1.05KB </span>","children":null,"spread":false},{"title":"reverseTableNewOld.py <span style='color:#111;'> 830B </span>","children":null,"spread":false},{"title":"testLayer.m <span style='color:#111;'> 4.73KB </span>","children":null,"spread":false},{"title":"PASCALkeeporig.m <span style='color:#111;'> 27.22KB </span>","children":null,"spread":false},{"title":"figureArrow.m <span style='color:#111;'> 738B </span>","children":null,"spread":false}],"spread":false},{"title":"vl_graphnn.m <span style='color:#111;'> 18.27KB </span>","children":null,"spread":false},{"title":"vl_nnloss_future.m <span style='color:#111;'> 10.18KB </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