Using my own Data

[efaillac]

Hello,

I've gotten the training, testing and plotting to work on my own set-up and have recreated your results. I see that the data PDE-Net is trained with is generated in the pdedata.py file. What is the best way to incorporate my own data and how do I feed it to PDE-Net?

Additionally, in PDE-Net 2.0 it is demonstrated that an actual equation can be output. How can I get PDE-Net to output the approximate PDE? Is there code available for PDE-Net 2.0?

[StillerPatrick]

The code for PDE-Net 2.0 is stored in branch PDE_Net 2.0

[ZichaoLong]

What is the best way to incorporate my own data and how do I feed it to PDE-Net?

Insead of applying PDE-Net (2.0) directly to your own problems, I recommand you to build your own codes upon the basic extension library aTEAM for further reseach.

Additionally, in PDE-Net 2.0 it is demonstrated that an actual equation can be output. How can I get PDE-Net to output the approximate PDE? Is there code available for PDE-Net 2.0?

See burgersdebug.py. We create(or load) a model, and print the analytic form of the learned PDE from the learned model. For example: for poly in model.polys: termsym,coeffssym = poly.coeffs(calprec=8) print(termsym[:8]) print(coeffssym[:8])

[yangheart]

Dear Zichao Long,

I tried to run burgersdebug.py. But the error I got like below: FileNotFoundError: [Errno 2] No such file or directory: 'checkpoint/burgers-frozen-upwind-sparse0.005-noise0.001/params/block-9-xopt-final'

How can I fix it? Is it the wrong file I run in the beginning? if this file should not be the first one, which file should I start to get the same plots about burgers from the paper?

Thank you so much!