xalanjava源码-KekeHu_DTLDP:客客呼_DTLDP
xalan
java源码客客呼_DTLDP
摘要：软件缺陷预测旨在自动定位有缺陷的代码模块，以更好地集中测试资源和人力。
通常，软件缺陷预测管道由两部分组成：第一部分通过使用外部工具提取程序特征，如抽象语法树，第二部分将基于机器学习的分类模型应用于这些特征以预测有缺陷的模块。
由于此类方法依赖于特定的特征提取工具，因此必须定制机器学习分类器以有效构建最准确的模型。
为了弥合深度学习和缺陷预测之间的差距，我们提出了一个端到端框架，该框架可以在不使用特征提取工具的情况下直接获得程序的预测结果。
为此，我们首先将程序可视化为图像，应用自注意力机制来提取图像特征，使用迁移学习来减少项目之间样本分布的差异，最后将图像文件输入到预先训练的深度学习模型中进行缺陷预测.
对来自
PROMISE
数据集的
10
个开源项目的实验表明，我们的方法可以改进跨项目和项目内缺陷预测。
实验
我们进行了实验以评估
DTL-DP
的性能，并将其与现有的基于深度学习的缺陷预测方法进行比较，用于项目内、WPDP
和跨项目、CPDP、缺陷预测。
我们在配备
3
个
Titan
XP
GPU
的
Linux
服务器上进行了
文件下载
资源详情
[{"title":"（ 56 个子文件 538KB ） xalanjava源码-KekeHu_DTLDP:客客呼_DTLDP","children":[{"title":"KekeHu_DTLDP-master","children":[{"title":".gitignore <span style='color:#111;'> 1.76KB </span>","children":null,"spread":false},{"title":"README.md <span style='color:#111;'> 4.62KB </span>","children":null,"spread":false},{"title":"code","children":[{"title":"run.sh <span style='color:#111;'> 125B </span>","children":null,"spread":false},{"title":"lr_schedule.py <span style='color:#111;'> 393B </span>","children":null,"spread":false},{"title":"train.py <span style='color:#111;'> 18.72KB </span>","children":null,"spread":false},{"title":"pre_process.py <span style='color:#111;'> 4.91KB </span>","children":null,"spread":false},{"title":"colorMap.py <span style='color:#111;'> 2.75KB </span>","children":null,"spread":false},{"title":"__pycache__","children":[{"title":"data_list.cpython-36.pyc <span style='color:#111;'> 6.41KB </span>","children":null,"spread":false},{"title":"loss.cpython-36.pyc <span style='color:#111;'> 2.52KB </span>","children":null,"spread":false},{"title":"network.cpython-36.pyc <span style='color:#111;'> 11.53KB </span>","children":null,"spread":false},{"title":"pre_process.cpython-36.pyc <span style='color:#111;'> 3.83KB </span>","children":null,"spread":false},{"title":"lr_schedule.cpython-36.pyc <span style='color:#111;'> 523B </span>","children":null,"spread":false}],"spread":true},{"title":"codeVis.py <span style='color:#111;'> 3.73KB </span>","children":null,"spread":false},{"title":"loss.py <span style='color:#111;'> 2.71KB </span>","children":null,"spread":false},{"title":"network.py <span style='color:#111;'> 12.67KB </span>","children":null,"spread":false},{"title":"data_list.py <span style='color:#111;'> 7.93KB </span>","children":null,"spread":false}],"spread":true},{"title":"LICENSE <span style='color:#111;'> 11.09KB </span>","children":null,"spread":false},{"title":"temp","children":[{"title":"readme.md <span style='color:#111;'> 75B </span>","children":null,"spread":false}],"spread":true},{"title":"data","children":[{"title":"ant-1.6.csv <span style='color:#111;'> 67.45KB </span>","children":null,"spread":false},{"title":"camel-1.4.csv <span style='color:#111;'> 146.13KB </span>","children":null,"spread":false},{"title":"velocity-1.5.csv <span style='color:#111;'> 33.88KB </span>","children":null,"spread":false},{"title":"xalan-2.5.csv <span style='color:#111;'> 124.67KB </span>","children":null,"spread":false},{"title":"poi-2.0.csv <span style='color:#111;'> 49.40KB </span>","children":null,"spread":false},{"title":"xalan-2.4.csv <span style='color:#111;'> 113.44KB </span>","children":null,"spread":false},{"title":"lucene-2.2.csv <span style='color:#111;'> 49.38KB </span>","children":null,"spread":false},{"title":"xerces-1.4.csv <span style='color:#111;'> 85.63KB </span>","children":null,"spread":false},{"title":"poi-3.0.csv <span style='color:#111;'> 67.92KB </span>","children":null,"spread":false},{"title":"xerces-1.3.csv <span style='color:#111;'> 69.17KB </span>","children":null,"spread":false},{"title":"log4j-1.0.csv <span style='color:#111;'> 18.50KB </span>","children":null,"spread":false},{"title":"ivy-2.0.csv <span style='color:#111;'> 61.94KB </span>","children":null,"spread":false},{"title":"synapse-1.0.csv <span style='color:#111;'> 22.83KB </span>","children":null,"spread":false},{"title":"xalan-2.7.csv <span style='color:#111;'> 157.26KB </span>","children":null,"spread":false},{"title":"archives","children":[{"title":"readme.md <span style='color:#111;'> 128B </span>","children":null,"spread":false}],"spread":false},{"title":"lucene-2.0.csv <span style='color:#111;'> 36.63KB </span>","children":null,"spread":false},{"title":"velocity-1.6.csv <span style='color:#111;'> 36.30KB </span>","children":null,"spread":false},{"title":"xerces-1.2.csv <span style='color:#111;'> 65.43KB </span>","children":null,"spread":false},{"title":"log4j-1.2.csv <span style='color:#111;'> 35.26KB </span>","children":null,"spread":false},{"title":"ant-1.7.csv <span style='color:#111;'> 143.74KB </span>","children":null,"spread":false},{"title":"synapse-1.2.csv <span style='color:#111;'> 37.14KB </span>","children":null,"spread":false},{"title":"camel-1.2.csv <span style='color:#111;'> 98.76KB </span>","children":null,"spread":false},{"title":"synapse-1.1.csv <span style='color:#111;'> 31.77KB </span>","children":null,"spread":false},{"title":"camel-1.0.csv <span style='color:#111;'> 55.48KB </span>","children":null,"spread":false},{"title":"camel-1.6.csv <span style='color:#111;'> 163.36KB </span>","children":null,"spread":false},{"title":"img","children":[{"title":"readme.md <span style='color:#111;'> 120B </span>","children":null,"spread":false}],"spread":false},{"title":"readme.md <span style='color:#111;'> 93B </span>","children":null,"spread":false},{"title":"poi-1.5.csv <span style='color:#111;'> 38.37KB </span>","children":null,"spread":false},{"title":"ivy-1.4.csv <span style='color:#111;'> 39.62KB </span>","children":null,"spread":false},{"title":"log4j-1.1.csv <span style='color:#111;'> 14.95KB </span>","children":null,"spread":false},{"title":"ant-1.4.csv <span style='color:#111;'> 33.23KB </span>","children":null,"spread":false},{"title":"velocity-1.4.csv <span style='color:#111;'> 30.12KB </span>","children":null,"spread":false},{"title":"poi-2.5.csv <span style='color:#111;'> 60.56KB </span>","children":null,"spread":false},{"title":"lucene-2.4.csv <span style='color:#111;'> 70.29KB </span>","children":null,"spread":false},{"title":"txt","children":[{"title":"readme.md <span style='color:#111;'> 164B </span>","children":null,"spread":false}],"spread":false},{"title":"ant-1.5.csv <span style='color:#111;'> 51.37KB </span>","children":null,"spread":false},{"title":"xalan-2.6.csv <span style='color:#111;'> 22.42KB </span>","children":null,"spread":false},{"title":"ant-1.3.csv <span style='color:#111;'> 23.40KB </span>","children":null,"spread":false}],"spread":false}],"spread":true}],"spread":true}]
评论信息
其他资源
- 魔术公式轮胎模型参数高精度拟合：基于MATLAB的CarSim数据辨识与文档详解, 魔术公式轮胎模型参数拟合MATLAB 本产品可根据CarSim数据辨识魔术公式轮胎模型的纵向轮胎力、侧向轮胎力、回正
- 汉字内码扩展规范(GBK)_按编码顺序排列.txt
- STM32F103脉搏血压测量硬件设计与Keil工程源码
- 第九课-垃圾分类-图像版.sb3
- Ubuntu 22.04 安装NVIDIA Container Toolkit
- ubuntu22.04的Docker离线包
- The First Snap-fit Handbook
- 魔术公式轮胎模型参数高精度拟合系统：基于MATLAB的数据辨识与CarSim集成应用,魔术公式轮胎模型参数高精度拟合系统-基于MATLAB对CarSim数据的识别与精准建模, 魔术公式轮胎模型参数拟
- docker mysql5.7 镜像
- CCleaner Pro
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