matlab微分方程代码-mrst-pytorch:将MRST移植到PyTorch的概念证明
matlab微分方程代码自述文件
GPU加速用于MRST（概念验证）
我今天（12月5日）开始进行评估和概念验证，以移植Matlab油藏模拟器以加速行驶。
部分工作需要SPE论文中的Eclipse数据集进行测试。
MRST。
我已将最重要的数据集上载到其自己的存储库中。
请参阅下面的参考。
由于PyTorch具有与GPU或GPU配合使用的内置功能，因此我们希望证明基于GPU的PyTorch可大大减少油藏模拟中的计算时间。
简而言之，这就是想法。
背景
少数科学家已经将他们的一些工作移植到了这种ML框架上，但是没有专门针对油藏模拟进行研究。
战略
测试构成MRST求解器核心的偏微分方程（PDE）。
使用Matlab和Octave测试求解器的运行时间。
最新书的作者提供了一些性能测试代码（请参阅附录）。
使用PyTorch
for
GPU复制Python中的功能。
将Matlab代码转换为PyTorch;
测量MRST求解器的计算时间。
如果在PyTorch中GPU的计算速度快10到100，则继续将更多的Matlab代码转换为基于PyTorch张量的计算。
感谢您的集思广益。
更新
已经有
文件下载
资源详情
[{"title":"（ 62 个子文件 1.2MB ） matlab微分方程代码-mrst-pytorch:将MRST移植到PyTorch的概念证明","children":[{"title":"mrst-pytorch-master","children":[{"title":".gitignore <span style='color:#111;'> 79B </span>","children":null,"spread":false},{"title":"r-to-matlab","children":[{"title":"read_from_matlab_file.Rmd <span style='color:#111;'> 245B </span>","children":null,"spread":false},{"title":"demo.Rmd <span style='color:#111;'> 856B </span>","children":null,"spread":false},{"title":"demo.nb.html <span style='color:#111;'> 659.21KB </span>","children":null,"spread":false},{"title":"read_from_matlab_file.nb.html <span style='color:#111;'> 662.06KB </span>","children":null,"spread":false},{"title":"r-to-matlab.Rproj <span style='color:#111;'> 205B </span>","children":null,"spread":false},{"title":"notes.md <span style='color:#111;'> 528B </span>","children":null,"spread":false},{"title":"midpoint.m <span style='color:#111;'> 743B </span>","children":null,"spread":false}],"spread":true},{"title":"jacobian-cpu","children":[{"title":"Jacobian-matrix-examples.ipynb <span style='color:#111;'> 19.21KB </span>","children":null,"spread":false},{"title":"tensorflow_pytorch_weights.9001.ipynb <span style='color:#111;'> 39.84KB </span>","children":null,"spread":false},{"title":"README.md <span style='color:#111;'> 1.47KB </span>","children":null,"spread":false},{"title":"tensorflow_pytorch_weights.9000.ipynb <span style='color:#111;'> 58.82KB </span>","children":null,"spread":false},{"title":"Jacobian-matrix-examples-tf.ipynb <span style='color:#111;'> 21.30KB </span>","children":null,"spread":false},{"title":"tensorflow_pytorch_weights.9002.ipynb <span style='color:#111;'> 40.01KB </span>","children":null,"spread":false}],"spread":true},{"title":"README.assets","children":[{"title":"image-20191222110513683.png <span style='color:#111;'> 115.08KB </span>","children":null,"spread":false},{"title":"image-20191222110339257.png <span style='color:#111;'> 180.84KB </span>","children":null,"spread":false},{"title":"image-20191222104821690.png <span style='color:#111;'> 141.62KB </span>","children":null,"spread":false}],"spread":true},{"title":"solving-PDEs","children":[{"title":"solving_PDE.md <span style='color:#111;'> 3.00KB </span>","children":null,"spread":false}],"spread":true},{"title":"README.md <span style='color:#111;'> 3.38KB </span>","children":null,"spread":false},{"title":"tests","children":[{"title":"README.md <span style='color:#111;'> 16B </span>","children":null,"spread":false},{"title":"tensorflow_tests.py <span style='color:#111;'> 737B </span>","children":null,"spread":false}],"spread":true},{"title":"environment.yml <span style='color:#111;'> 823B </span>","children":null,"spread":false},{"title":"lib","children":[{"title":"README.md <span style='color:#111;'> 20B </span>","children":null,"spread":false}],"spread":true},{"title":"dev","children":[{"title":"another_torch_summary.py <span style='color:#111;'> 2.15KB </span>","children":null,"spread":false},{"title":"README.md <span style='color:#111;'> 198B </span>","children":null,"spread":false},{"title":"torchsummary.py <span style='color:#111;'> 4.98KB </span>","children":null,"spread":false}],"spread":true},{"title":"tmp","children":[{"title":"explicit_env.txt <span style='color:#111;'> 10.29KB </span>","children":null,"spread":false},{"title":"environment_newest.yml <span style='color:#111;'> 4.06KB </span>","children":null,"spread":false},{"title":"environment_long.yml <span style='color:#111;'> 4.06KB </span>","children":null,"spread":false}],"spread":true},{"title":"z.sandbox","children":[{"title":"02-PyTorch Autograd.ipynb <span style='color:#111;'> 13.83KB </span>","children":null,"spread":false},{"title":"32-fluidsim.ipynb <span style='color:#111;'> 10.33KB </span>","children":null,"spread":false},{"title":"cuda semantics.ipynb <span style='color:#111;'> 3.76KB </span>","children":null,"spread":false},{"title":"measure_average_time_execution.ipynb <span style='color:#111;'> 7.08KB </span>","children":null,"spread":false},{"title":"Buckley-Leverett-with-autograd.ipynb <span style='color:#111;'> 48.97KB </span>","children":null,"spread":false},{"title":"99-backward_with_indices_on_y.ipynb <span style='color:#111;'> 6.92KB </span>","children":null,"spread":false},{"title":"21-compute Jacobians with PyTorch.ipynb <span style='color:#111;'> 16.17KB </span>","children":null,"spread":false},{"title":"compute_gradients.png <span style='color:#111;'> 74.35KB </span>","children":null,"spread":false},{"title":"jacobian-matrix-pytorch_sequential.ipynb <span style='color:#111;'> 25.39KB </span>","children":null,"spread":false},{"title":"01-backward function in PyTorch.ipynb <span style='color:#111;'> 10.82KB </span>","children":null,"spread":false},{"title":"README.md <span style='color:#111;'> 15B </span>","children":null,"spread":false},{"title":"04-plotting derivatives using PyTorch.ipynb <span style='color:#111;'> 77.99KB </span>","children":null,"spread":false},{"title":"31-plot Autograd error.ipynb <span style='color:#111;'> 6.40KB </span>","children":null,"spread":false},{"title":"30-tests of Jacobians with autograd.ipynb <span style='color:#111;'> 32.06KB </span>","children":null,"spread":false},{"title":"03-why we get errors with simple derivatives - PyTorch.ipynb <span style='color:#111;'> 12.81KB </span>","children":null,"spread":false}],"spread":false},{"title":"jacobian-gpu","children":[{"title":"README.md <span style='color:#111;'> 274B </span>","children":null,"spread":false}],"spread":true},{"title":"jacobians-octave","children":[{"title":"run_complexstep.m <span style='color:#111;'> 1.23KB </span>","children":null,"spread":false},{"title":"run_myjacobian.m <span style='color:#111;'> 439B </span>","children":null,"spread":false},{"title":"run_numerical_jacobian.m <span style='color:#111;'> 595B </span>","children":null,"spread":false},{"title":"run_NumJacob.m <span style='color:#111;'> 517B </span>","children":null,"spread":false},{"title":"run_complexstep_direct.m <span style='color:#111;'> 1.29KB </span>","children":null,"spread":false},{"title":"run_fdjacobian.m <span style='color:#111;'> 477B </span>","children":null,"spread":false},{"title":"README.md <span style='color:#111;'> 1.38KB </span>","children":null,"spread":false},{"title":"jacobian_linear.m <span style='color:#111;'> 245B </span>","children":null,"spread":false},{"title":"NumJacob","children":[{"title":"demo2.m <span style='color:#111;'> 33B </span>","children":null,"spread":false},{"title":"NumJacob.m <span style='color:#111;'> 672B </span>","children":null,"spread":false},{"title":"test_func.m <span style='color:#111;'> 48B </span>","children":null,"spread":false},{"title":"test_func2.m <span style='color:#111;'> 80B </span>","children":null,"spread":false},{"title":"demo.m <span style='color:#111;'> 37B </span>","children":null,"spread":false}],"spread":false},{"title":"notes.assets","children":[{"title":"image-20191208091753167.png <span style='color:#111;'> 26.21KB </span>","children":null,"spread":false},{"title":"image-20191208091905370.png <span style='color:#111;'> 17.33KB </span>","children":null,"spread":false},{"title":"image-20191205133333494.png <span style='color:#111;'> 65.63KB </span>","children":null,"spread":false}],"spread":false},{"title":"simple_jacobian.m <span style='color:#111;'> 134B </span>","children":null,"spread":false}],"spread":false}],"spread":false}],"spread":true}]
评论信息
其他资源
- Matlab R2009b 下载地址+安装全过程
- 硬件架构的艺术PDF
- eigen3.zip
- 基于51单片机的高频函数信号发生器
- IDL界面程序
- 基于Android微博客户端的设计与实现
- C++作业二狼吃羊
- 经典数值分析教材Numerical Analysis Burden Faires 9th 数值分析 非扫描
- VB 读取Excel表格数据并在ListView控件中显示
- STM32F10X固件函数库包 + STM32F103固件函数库用户手册中文版.zip
- mysql-5.7.33-linux-glibc2.12-x86_64.tar.gz
- php自写预订房间
- 教师课堂用语 结束语.pdf
- vxWorks6.8 操作系统下 QT 安装设置.pdf
- 电商广告投放明细_麦包包.xls
- 感激：为我父母的康复之家提供的医疗应用程序。 使患者，应用程序和住房信息井井有条且易于使用-源码
- vb.net图书馆管理系统源码
- 任务书2（一元稀疏多项式计算器）数据结构报告
- toucher.js
- Android 进阶 教你打造 Android 中的 IOC 框架 （下）
- 在modis数据图像上叠加地图
- 《精通GDI+编程》.PDF[含目录]
- 基于matlab gui的图像处理课程实验演示平台的设计与实现
- dlib-19.4.0-cp35-cp35m-win_amd64.whl
- 九宫格日记网
- Teigha.Java 2019.02版本
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