ydume / ednn Goto Github PK
View Code? Open in Web Editor NEWSource code and examples for Evolutional Deep Neural Network (EDNN)
License: MIT License
Source code and examples for Evolutional Deep Neural Network (EDNN)
License: MIT License
# Yifan Du [email protected] # Tamer A. Zaki [email protected] # Johns Hokpins University # US patent submitted 03/08/2021 This main folder containts several realization of EDNN for different time dependent partial differential equations. In each folder there are four files: main.py : The main function for this problem. It contains the problem definition and parameters, the high level initialization, training and marching commands for the EDNN. ednn.py : The EDNN abstract class. It contains the detailed implementation of EDNN structure, training and marching. Because the boundary conditions and constraints for different PDEs are different, the ednn files are slightly different for these cases. rhs.py : The evolutional PDE implementation. It containts The right -hand-side of different PDEs. These nonlinear differential operators are implemented using tensorflow. marching_schemes : The time marching methods for the neural network parameters. The forward Euler and Runge-Kutta are implemented. To run one of these cases, first enter the corresponding directory. To train the network for initial condition, type: python main.py 0 To march the trained network, type: python main.py 1
There are some cache files (in pycache directories) included in the repo. These should be removed. Also, a gitignore file will help avoid adding such files in the future.
The channel flow example doesn't run due to a few typos. In line 115, BNN
should be EDNN
. In lines 119-121, boundary_dir
should be case_name
.
The starting timestep in the marching loop is inconsistent. The value of n
in the first iteration should be nrestart + 1
, but in some examples is nrestart
.
A declarative, efficient, and flexible JavaScript library for building user interfaces.
๐ Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
An Open Source Machine Learning Framework for Everyone
The Web framework for perfectionists with deadlines.
A PHP framework for web artisans
Bring data to life with SVG, Canvas and HTML. ๐๐๐
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
Some thing interesting about web. New door for the world.
A server is a program made to process requests and deliver data to clients.
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Some thing interesting about visualization, use data art
Some thing interesting about game, make everyone happy.
We are working to build community through open source technology. NB: members must have two-factor auth.
Open source projects and samples from Microsoft.
Google โค๏ธ Open Source for everyone.
Alibaba Open Source for everyone
Data-Driven Documents codes.
China tencent open source team.