SparseCoding:基于L1的字典学习,用于稀疏编码

上传者: 42132325 | 上传时间: 2023-07-01 19:40:41 | 文件大小: 2.4MB | 文件类型: ZIP
2020年9月9日更新: 我尝试拉动并运行它,以发现它与最新的pytorch和Windows不兼容。 我将在下周更新它-现在不会运行。 -本 用法 该演示需要 。 首先,使用--help执行python run_demo.py来查看可选参数。 默认实验是带有MNIST的字典学习演示。 目的 该存储库的最终目标是提供一个稀疏的编码库,该库可实现用于(1)词典学习,(2)传统/凸代码推断(例如ISTA,SALSA)和(3)“展开”可学习编码器(例如,)。 现在,字典学习正在不断发展。 特别是,我正在构建结合了(2)和(3)的编码器类。 然后,我将概括用于形态学成分分析(MCA)的类,这是一种用于源分离的稀疏编码方法。 稀疏编码背景 用信号或图像的基本组成部分来表示通常很有用。 例如,笑脸可以有效地描述为“圆,两个点和曲线”。 至少,这比“像素1:值0.1。像素2:值1”更有效,以此类推。

文件下载

资源详情

[{"title":"( 44 个子文件 2.4MB ) SparseCoding:基于L1的字典学习,用于稀疏编码","children":[{"title":"SparseCoding-master","children":[{"title":".gitignore <span style='color:#111;'> 1.17KB </span>","children":null,"spread":false},{"title":"README.md <span style='color:#111;'> 10.19KB </span>","children":null,"spread":false},{"title":"loadImDat.py <span style='color:#111;'> 8.96KB </span>","children":null,"spread":false},{"title":"paramSearchResults","children":[{"title":"reconErrHist.png <span style='color:#111;'> 19.75KB </span>","children":null,"spread":false},{"title":"MNIST32_0000.png <span style='color:#111;'> 635.03KB </span>","children":null,"spread":false},{"title":"CIFAR1010_0210.png <span style='color:#111;'> 16.23KB </span>","children":null,"spread":false},{"title":"lossHist.png <span style='color:#111;'> 23.19KB </span>","children":null,"spread":false},{"title":"ASIRRA16_0000.png <span style='color:#111;'> 79.53KB </span>","children":null,"spread":false},{"title":"FashionMNIST10_0220.png <span style='color:#111;'> 13.15KB </span>","children":null,"spread":false},{"title":"sparsityHist.png <span style='color:#111;'> 24.01KB </span>","children":null,"spread":false}],"spread":true},{"title":"sanity_ims","children":[{"title":"fixedEncoders","children":[{"title":"ista_loss.png <span style='color:#111;'> 20.69KB </span>","children":null,"spread":false},{"title":"salsa_loss.png <span style='color:#111;'> 21.81KB </span>","children":null,"spread":false},{"title":"salsa_x.png <span style='color:#111;'> 11.09KB </span>","children":null,"spread":false},{"title":"ista_x.png <span style='color:#111;'> 11.09KB </span>","children":null,"spread":false},{"title":"fista_loss.png <span style='color:#111;'> 16.80KB </span>","children":null,"spread":false},{"title":"fista_x.png <span style='color:#111;'> 11.83KB </span>","children":null,"spread":false}],"spread":true},{"title":"trainedEncoders","children":[{"title":"ista_loss.png <span style='color:#111;'> 16.88KB </span>","children":null,"spread":false},{"title":"salsa_loss.png <span style='color:#111;'> 17.12KB </span>","children":null,"spread":false},{"title":"salsa_x.png <span style='color:#111;'> 13.30KB </span>","children":null,"spread":false},{"title":"ista_x.png <span style='color:#111;'> 13.09KB </span>","children":null,"spread":false},{"title":"fista_loss.png <span style='color:#111;'> 20.97KB </span>","children":null,"spread":false},{"title":"fista_x.png <span style='color:#111;'> 13.00KB </span>","children":null,"spread":false}],"spread":true}],"spread":true},{"title":"LICENSE <span style='color:#111;'> 1.04KB </span>","children":null,"spread":false},{"title":"getParams.py <span style='color:#111;'> 669B </span>","children":null,"spread":false},{"title":"tests.py <span style='color:#111;'> 2.70KB </span>","children":null,"spread":false},{"title":"run_demo.py <span style='color:#111;'> 9.92KB </span>","children":null,"spread":false},{"title":"UTILS","children":[{"title":"writeProgressFigs.py <span style='color:#111;'> 1.78KB </span>","children":null,"spread":false},{"title":"matlab_type_demo.py <span style='color:#111;'> 2.92KB </span>","children":null,"spread":false},{"title":"FISTA.py <span style='color:#111;'> 2.06KB </span>","children":null,"spread":false},{"title":"utils.py <span style='color:#111;'> 7.54KB </span>","children":null,"spread":false},{"title":"class_dict.py <span style='color:#111;'> 3.01KB </span>","children":null,"spread":false},{"title":"class_nonlinearity.py <span style='color:#111;'> 3.23KB </span>","children":null,"spread":false},{"title":"fcn_patchExtract.py <span style='color:#111;'> 547B </span>","children":null,"spread":false},{"title":"DictionaryTraining.py <span style='color:#111;'> 8.34KB </span>","children":null,"spread":false},{"title":"class_encoder.py <span style='color:#111;'> 13.07KB </span>","children":null,"spread":false}],"spread":true},{"title":"pSearch.py <span style='color:#111;'> 2.89KB </span>","children":null,"spread":false},{"title":"results","children":[{"title":"reconErrHist.png <span style='color:#111;'> 28.15KB </span>","children":null,"spread":false},{"title":"MNIST32dictAtoms.png <span style='color:#111;'> 801.10KB </span>","children":null,"spread":false},{"title":"data_atoms_comparison.pdf <span style='color:#111;'> 565.16KB </span>","children":null,"spread":false},{"title":"MNIST10dictAtoms.png <span style='color:#111;'> 28.85KB </span>","children":null,"spread":false},{"title":"lossHist.png <span style='color:#111;'> 31.94KB </span>","children":null,"spread":false},{"title":"npl1.png <span style='color:#111;'> 14.28KB </span>","children":null,"spread":false},{"title":"tmp","children":[{"title":"no-name.pt <span style='color:#111;'> 943B </span>","children":null,"spread":false}],"spread":false},{"title":"sparsityHist.png <span style='color:#111;'> 13.19KB </span>","children":null,"spread":false}],"spread":true}],"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