TorchLRP:分层明智相关性传播(LRP)的PyTorch 1.6实施-源码

上传者: 42102933 | 上传时间: 2021-06-22 11:18:34 | 文件大小: 58.52MB | 文件类型: ZIP
pytorch LRP的实现 PyTorch对线性层和卷积层的一些层明智相关性传播(LRP)规则[1、2、3]的实现。 这些模块装饰了torch.nn.Sequential , torch.nn.Linear和torch.nn.Conv2d ,以便能够使用autograd算法来计算说明。 安装 要安装需求,请参阅文件。 如果使用conda ,则可以通过执行以下命令来安装称为torchlrp的环境: > conda env create -f requirements.yml 为了能够如下所示导入lrp ,请确保路径中包含TorchLRP目录。 用法 该代码可以按如下方式使用: import torch import lrp model = Sequential ( lrp . Conv2d ( 1 , 32 , 3 , 1 , 1 ), torch . nn

文件下载

资源详情

[{"title":"( 28 个子文件 58.52MB ) TorchLRP:分层明智相关性传播(LRP)的PyTorch 1.6实施-源码","children":[{"title":"TorchLRP-master","children":[{"title":"lrp","children":[{"title":"functional","children":[{"title":"linear.py <span style='color:#111;'> 5.25KB </span>","children":null,"spread":false},{"title":"utils.py <span style='color:#111;'> 981B </span>","children":null,"spread":false},{"title":"__init__.py <span style='color:#111;'> 170B </span>","children":null,"spread":false},{"title":"maxpool.py <span style='color:#111;'> 1.37KB </span>","children":null,"spread":false},{"title":"conv.py <span style='color:#111;'> 6.38KB </span>","children":null,"spread":false}],"spread":true},{"title":"trace.py <span style='color:#111;'> 500B </span>","children":null,"spread":false},{"title":"linear.py <span style='color:#111;'> 641B </span>","children":null,"spread":false},{"title":"__init__.py <span style='color:#111;'> 305B </span>","children":null,"spread":false},{"title":"maxpool.py <span style='color:#111;'> 308B </span>","children":null,"spread":false},{"title":"conv.py <span style='color:#111;'> 1.33KB </span>","children":null,"spread":false},{"title":"patterns.py <span style='color:#111;'> 4.47KB </span>","children":null,"spread":false},{"title":"converter.py <span style='color:#111;'> 1.40KB </span>","children":null,"spread":false},{"title":"sequential.py <span style='color:#111;'> 1.70KB </span>","children":null,"spread":false}],"spread":true},{"title":"requirements.yml <span style='color:#111;'> 255B </span>","children":null,"spread":false},{"title":"LICENSE <span style='color:#111;'> 1.05KB </span>","children":null,"spread":false},{"title":"__init__.py <span style='color:#111;'> 0B </span>","children":null,"spread":false},{"title":"examples","children":[{"title":"models","children":[{"title":"mnist_model.pth <span style='color:#111;'> 24.60MB </span>","children":null,"spread":false}],"spread":true},{"title":"utils.py <span style='color:#111;'> 2.90KB </span>","children":null,"spread":false},{"title":"explain_vgg.py <span style='color:#111;'> 4.47KB </span>","children":null,"spread":false},{"title":"plots","children":[{"title":"mnist_explanations.png <span style='color:#111;'> 190.90KB </span>","children":null,"spread":false},{"title":"vgg19_explanations.png <span style='color:#111;'> 1.31MB </span>","children":null,"spread":false},{"title":"vgg16_explanations.png <span style='color:#111;'> 7.63MB </span>","children":null,"spread":false}],"spread":true},{"title":"visualization.py <span style='color:#111;'> 1.96KB </span>","children":null,"spread":false},{"title":"explain_mnist.py <span style='color:#111;'> 5.37KB </span>","children":null,"spread":false},{"title":"patterns","children":[{"title":"mnist_pattern_all.pkl <span style='color:#111;'> 24.59MB </span>","children":null,"spread":false},{"title":"mnist_pattern_pos.pkl <span style='color:#111;'> 24.59MB </span>","children":null,"spread":false}],"spread":true}],"spread":true},{"title":".gitignore <span style='color:#111;'> 2.71KB </span>","children":null,"spread":false},{"title":"README.md <span style='color:#111;'> 5.58KB </span>","children":null,"spread":false}],"spread":true}],"spread":true}]

评论信息

  • ForloveZED :
    用户下载后在一定时间内未进行评价,系统默认好评。
    2021-08-06

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