- Make equation discovery more transparent and illustrative
- Combine power of pytorch, numerical methods and math overall to conquer and solve ALL XDEs(X={O,P}). There are some examples to provide a little insight to an operator form
- Core features
- Installation
- Examples
- Project Structure
- Documentation
- Getting started
- License
- Contacts
- Citation
- Solve ODE initial- or boundary-value problems
- Solve PDE initial-boundary value problems
- Use variable models and their differentiation methods
- Faster solution using cache
TEDEouS can be installed with pip
:
$ git clone https://github.com/ITMO-NSS-team/torch_DE_solver.git $ cd torch_DE_solver $ pip install -r requirements.txt
After the TEDEouS is installed the user may refer to various examples that are in examples forlder.
$ cd examples
Every example is designed such that the boxplots of the launches are commented and the preliminary results are not shown, but stored in separate folders.
- Legendre polynomial equation
$ python example_ODE_Legendre.py
or
$ python example_ODE_Legendre_autograd.py
- Panleve transcendents (others are placed in 'examples\to_renew' folder due to the architecture change)
$ python example_Painleve_I.py
- Wave equation (non-physical conditions for equation discovery problem)
$ python example_wave_paper_autograd.py
- Wave equation (initial-boundary value problem)
$ python example_wave_physics.py
- Heat equation
$ python example_heat.py
- KdV equation (non-physical conditions for equation discovery problem)
$ python example_KdV.py
- KdV equation (solitary solution with periodic boundary conditions)
$ python example_KdV_periodic.py
- Burgers equation and DeepXDE comparison
$ python example_Burgers_paper.py
Stable version is located in the master branch.
https://torch-de-solver.readthedocs.io/en/docs/index.html
Schroedinger equation example step-by-step https://torch-de-solver.readthedocs.io/en/docs/tedeous/examples/schrodinger.html
TEDEouS is distributed under BSD-3 licence found in LICENCE file
- Feel free to make issues or contact @SuperSashka directly
@article{hvatov2023solver, AUTHOR = {Hvatov, Alexander}, TITLE = {Automated Differential Equation Solver Based on the Parametric Approximation Optimization}, JOURNAL = {Mathematics}, VOLUME = {11}, YEAR = {2023}, NUMBER = {8}, ARTICLE-NUMBER = {1787}, URL = {https://www.mdpi.com/2227-7390/11/8/1787}, ISSN = {2227-7390}, DOI = {10.3390/math11081787} }