Batch size is not implemented?

[tsarikahin]

Dear LuLu @lululxvi,

I was wondering if the batch_size in the train method is not implemented or if it does not work. It says: "If you solve PDEs via dde.data.PDE or dde.data.TimePDE, do not use batch_size, and instead use dde.callbacks.PDEPointResampler"

Imagine that I must use batch_size.

I would really appreciate it if you could explain why you suggest using the callback PDEPointResampler.

Can you also confirm if batch_size uses train_x_all in case it is implemented?

Best,
Tarik

[lululxvi]

https://deepxde.readthedocs.io/en/latest/modules/deepxde.html#deepxde.callbacks.PDEPointResampler works the same as batch size.