Multi-class-Peer-Loss-functions:通过采用对等预测损失功能来学习带有噪声的标签（深度学习和多类版本）-源码
对等丢失功能
此存储库是ICML2020接受的“”的Pytorch Pytorch实现。
所需的包装和环境
支持的操作系统： Windows，Linux，Mac OS X； 的Python：3.6 / 3.7;
深度学习库： PyTorch（需要GPU）
所需软件包： Numpy，Pandas，random，sklearn，tqdm，csv，火炬（如果要估计噪声转换矩阵，则需要Keras）。
实用工具
该存储库包括：
:clipboard: 对等丢失功能的多类实现；
:clipboard: 深度学习中的对等丢失功能；
:clipboard: Peer Loss功能的动态调整策略可进一步提高性能。
运行详细信息（ 每个文件夹的README.md文件中都提到了MNIST，Fashion MNIST，CIFAR-10，CIFAR-100上具有不同噪声设置的对等丢失功能。
的工作流程 加权对等损失函数包括：
决策边界可视化
给定2D合成
文件下载
资源详情
[{"title":"（ 70 个子文件 128.59MB ） Multi-class-Peer-Loss-functions:通过采用对等预测损失功能来学习带有噪声的标签（深度学习和多类版本）-源码","children":[{"title":"Multi-class-Peer-Loss-functions-main","children":[{"title":"peernet.png <span style='color:#111;'> 153.97KB </span>","children":null,"spread":false},{"title":"LICENSE <span style='color:#111;'> 1.04KB </span>","children":null,"spread":false},{"title":"MNIST","children":[{"title":"runner.py <span style='color:#111;'> 6.08KB </span>","children":null,"spread":false},{"title":".DS_Store <span style='color:#111;'> 6.00KB </span>","children":null,"spread":false},{"title":"noise_label","children":[{"title":"MNIST_noise_r0_6.pt <span style='color:#111;'> 469.11KB </span>","children":null,"spread":false},{"title":"MNIST_noise_r0_4.pt <span style='color:#111;'> 469.10KB </span>","children":null,"spread":false},{"title":"MNIST_noise_r0_3.pt <span style='color:#111;'> 469.10KB </span>","children":null,"spread":false},{"title":"MNIST_noise_r0_5.pt <span style='color:#111;'> 469.11KB </span>","children":null,"spread":false},{"title":"MNIST_noise_r0_1.pt <span style='color:#111;'> 469.10KB </span>","children":null,"spread":false},{"title":"test.pt <span style='color:#111;'> 7.55MB </span>","children":null,"spread":false},{"title":"MNIST_noise_r0_2.pt <span style='color:#111;'> 469.10KB </span>","children":null,"spread":false}],"spread":true},{"title":"noise_data_mnist.py <span style='color:#111;'> 9.06KB </span>","children":null,"spread":false},{"title":"README.md <span style='color:#111;'> 634B </span>","children":null,"spread":false},{"title":"datasets","children":[{"title":"raw","children":[{"title":"t10k-images-idx3-ubyte.gz <span style='color:#111;'> 1.57MB </span>","children":null,"spread":false},{"title":"t10k-labels-idx1-ubyte <span style='color:#111;'> 9.77KB </span>","children":null,"spread":false},{"title":"t10k-labels-idx1-ubyte.gz <span style='color:#111;'> 4.44KB </span>","children":null,"spread":false},{"title":"train-labels-idx1-ubyte.gz <span style='color:#111;'> 28.20KB </span>","children":null,"spread":false},{"title":"train-images-idx3-ubyte <span style='color:#111;'> 44.86MB </span>","children":null,"spread":false},{"title":"train-images-idx3-ubyte.gz <span style='color:#111;'> 9.45MB </span>","children":null,"spread":false},{"title":"t10k-images-idx3-ubyte <span style='color:#111;'> 7.48MB </span>","children":null,"spread":false},{"title":"train-labels-idx1-ubyte <span style='color:#111;'> 58.60KB </span>","children":null,"spread":false}],"spread":true},{"title":"processed","children":[{"title":"test.pt <span style='color:#111;'> 7.55MB </span>","children":null,"spread":false},{"title":"training.pt <span style='color:#111;'> 45.32MB </span>","children":null,"spread":false}],"spread":true}],"spread":true}],"spread":true},{"title":"CIFAR-10","children":[{"title":"noise_data_cifar_10.py <span style='color:#111;'> 9.70KB </span>","children":null,"spread":false},{"title":"runner.py <span style='color:#111;'> 6.00KB </span>","children":null,"spread":false},{"title":".DS_Store <span style='color:#111;'> 6.00KB </span>","children":null,"spread":false},{"title":"noise_label","children":[{"title":"CIFAR10_noise_r0_5.pt <span style='color:#111;'> 390.98KB </span>","children":null,"spread":false},{"title":"CIFAR10_noise_r0_1.pt <span style='color:#111;'> 390.98KB </span>","children":null,"spread":false},{"title":"CIFAR10_noise_r0_6.pt <span style='color:#111;'> 390.98KB </span>","children":null,"spread":false},{"title":"CIFAR10_noise_r0_2.pt <span style='color:#111;'> 390.98KB </span>","children":null,"spread":false},{"title":"CIFAR10_noise_r0_3.pt <span style='color:#111;'> 390.97KB </span>","children":null,"spread":false},{"title":"test_label.pt <span style='color:#111;'> 78.46KB </span>","children":null,"spread":false},{"title":"CIFAR10_noise_r0_4.pt <span style='color:#111;'> 390.97KB </span>","children":null,"spread":false}],"spread":true},{"title":"model.py <span style='color:#111;'> 6.41KB </span>","children":null,"spread":false},{"title":"README.md <span style='color:#111;'> 623B </span>","children":null,"spread":false},{"title":"datasets","children":[{"title":".DS_Store <span style='color:#111;'> 6.00KB </span>","children":null,"spread":false}],"spread":true}],"spread":true},{"title":"CIFAR-100","children":[{"title":"runner.py <span style='color:#111;'> 6.88KB </span>","children":null,"spread":false},{"title":".DS_Store <span style='color:#111;'> 6.00KB </span>","children":null,"spread":false},{"title":"noise_label","children":[{"title":"CIFAR100_noise_r0_2.pt <span style='color:#111;'> 390.98KB </span>","children":null,"spread":false},{"title":"CIFAR100_noise_r0_1.pt <span style='color:#111;'> 390.98KB </span>","children":null,"spread":false},{"title":"CIFAR100_noise_r0_3.pt <span style='color:#111;'> 390.98KB </span>","children":null,"spread":false},{"title":"CIFAR100_noise_r0_4.pt <span style='color:#111;'> 390.98KB </span>","children":null,"spread":false},{"title":"test_label.pt <span style='color:#111;'> 78.46KB </span>","children":null,"spread":false}],"spread":true},{"title":"model.py <span style='color:#111;'> 6.41KB </span>","children":null,"spread":false},{"title":"noise_data_cifar_100.py <span style='color:#111;'> 9.38KB </span>","children":null,"spread":false},{"title":"README.md <span style='color:#111;'> 596B </span>","children":null,"spread":false},{"title":"datasets","children":[{"title":".DS_Store <span style='color:#111;'> 6.00KB </span>","children":null,"spread":false}],"spread":true}],"spread":true},{"title":"README.md <span style='color:#111;'> 1.94KB </span>","children":null,"spread":false},{"title":"decision_boundary.png <span style='color:#111;'> 284.55KB </span>","children":null,"spread":false},{"title":"Fashion_MNIST","children":[{"title":"runner.py <span style='color:#111;'> 6.08KB </span>","children":null,"spread":false},{"title":"noise_data_fashion.py <span style='color:#111;'> 8.97KB </span>","children":null,"spread":false},{"title":".DS_Store <span style='color:#111;'> 6.00KB </span>","children":null,"spread":false},{"title":"noise_label","children":[{"title":"Fashion_noise_r0_3.pt <span style='color:#111;'> 469.10KB </span>","children":null,"spread":false},{"title":"Fashion_noise_r0_6.pt <span style='color:#111;'> 469.11KB </span>","children":null,"spread":false},{"title":"Fashion_noise_r0_1.pt <span style='color:#111;'> 469.10KB </span>","children":null,"spread":false},{"title":"test.pt <span style='color:#111;'> 7.55MB </span>","children":null,"spread":false},{"title":"Fashion_noise_r0_2.pt <span style='color:#111;'> 469.10KB </span>","children":null,"spread":false},{"title":"Fashion_noise_r0_5.pt <span style='color:#111;'> 469.11KB </span>","children":null,"spread":false},{"title":"Fashion_noise_r0_4.pt <span style='color:#111;'> 469.10KB </span>","children":null,"spread":false}],"spread":true},{"title":"README.md <span style='color:#111;'> 653B </span>","children":null,"spread":false},{"title":"datasets","children":[{"title":"raw","children":[{"title":"t10k-images-idx3-ubyte.gz <span style='color:#111;'> 4.22MB </span>","children":null,"spread":false},{"title":"t10k-labels-idx1-ubyte <span style='color:#111;'> 9.77KB </span>","children":null,"spread":false},{"title":"t10k-labels-idx1-ubyte.gz <span style='color:#111;'> 5.03KB </span>","children":null,"spread":false},{"title":"train-labels-idx1-ubyte.gz <span style='color:#111;'> 28.82KB </span>","children":null,"spread":false},{"title":"train-images-idx3-ubyte <span style='color:#111;'> 44.86MB </span>","children":null,"spread":false},{"title":"train-images-idx3-ubyte.gz <span style='color:#111;'> 25.20MB </span>","children":null,"spread":false},{"title":"t10k-images-idx3-ubyte <span style='color:#111;'> 7.48MB </span>","children":null,"spread":false},{"title":"train-labels-idx1-ubyte <span style='color:#111;'> 58.60KB </span>","children":null,"spread":false}],"spread":false},{"title":"processed","children":[{"title":"test.pt <span style='color:#111;'> 7.55MB </span>","children":null,"spread":false},{"title":"training.pt <span style='color:#111;'> 45.32MB </span>","children":null,"spread":false}],"spread":false}],"spread":false}],"spread":true}],"spread":true}],"spread":true}]
评论信息
其他资源
- 1037u 小主板备份的bios
- OpenCV之人脸，眼睛，鼻子，嘴巴的识别
- TB67S109AFTG步进驱动板原理图和PCB文件
- RFC3261(SIP协议)中文文字版(带目录)
- 餐饮管理系统（完整可运行)ASP.Net+SqlServer
- linux+QT下基于RTP协议的实时视频传输客户端和服务端
- 基于51单片机全自动洗衣机
- modern robotics.pdf
- 哈工大有限元理论.pdf
- 思侬尚品BP【恩美路演提供】.pdf
- 浮选泡沫图像等效尺寸分布特征提取
- RsaUtils.java
- gin-boilerplate：使用Gin Framework部署结构化项目的默认api的最快方法，该项目默认为PostgreSQL数据库和Redis中存储的JWT身份验证中间件-源码
- pymongo-3.9.0-cp27-cp27m-win_amd64.whl
- 961真题.zip
- ffmpeg安卓课程详解.pdf
- 基于FPGA技术的FIR数字滤波器的设计
- 文件加密软件
- 泛微OA项目实施1000+问 2016版
- 三个动态表白页面
- PMBOK指南项目管理实战工具表格汇总简述-其它文档类资源
- SQL Server 2000一键10秒极速安装.part2
- cocos creator v2.1 api手册
- CA(证书颁发机构)服务器配置原理与图解过程
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