vl-dud comments

Results 15 comments of


                                            vl-dud

Higher precision

@jottoy check the parameter *decimals* in TableOne class

Tensorflow 1.x backend: define a model multiple times in the same code

If you think it might cause any issues, then let's close this PR. But I spent a lot of time trying to figure out what the problem was with my...

Type mismatch when trying to use L-BFGS

> However, when trying to use this optimizer after setting the default precision to float64 Did you call `deepxde.config.real.set_float64()` right after `import deepxde`? If not, do it.

Type mismatch when trying to use L-BFGS

Can you show all the code?

Separate train_x_all and train_x_bc in PDE

> Check this #1113 These pull requests are certainly related, but in my opinion they are not the same thing. The current PR specifically concerns the duplication of points. The...

PINNs energy method

Could you show the code?

PINNs energy method

It seems that `tf.reduce_sum(dy_xx**2-y,axis=1)` is an incorrect representation of the integral for this problem.

PINNs energy method

I don't think deepxde is suitable for equations with integral. But I could be wrong

Is DeepXDE able to have a terminal condition instead of an initial

Why don't you just add this equation to the PDEs list?

Tensorflow 1.x backend: add dropout to DeepONet

> Do you use dropbox to prevent overfitting? Yes, I'm using dropout_rate right now during hyperparameter tuning. I'll write how useful it is in my case.