dde.gradients support 3D outputs #1928
Conversation
Update example of heat equation (lululxvi#706)
Add document for Lorenz inverse with exogenous input (lululxvi#709)
OperatorPredictor supports backends tensorflow.compat.v1, tensorflow,…
… method of Lr decay in Pytorch
update to latest version
|
You need to test all backends. |
The only case where the output is 3D is shown to be supported only by tensorflow v2 and pytorch https://github.com/lululxvi/deepxde/blob/master/examples/operator/stokes_aligned_pideeponet.py |
|
Not necessary testing PI-DeepONet. You can manually construct a function, and jus test if dde.gradients works correctly. |
I have tested pytorch, tf v2, paddle, jax. I don't have access to the environment for tf v1 |
| @@ -21,11 +21,11 @@ def __call__(self, i=None, j=None): | |||
| # Compute J[i, :] | |||
| if i not in self.J: | |||
| if backend_name in ["tensorflow.compat.v1", "tensorflow"]: | |||
| y = self.ys[:, i : i + 1] if self.dim_y > 1 else self.ys | |||
| y = self.ys[..., i : i + 1] if self.dim_y > 1 else self.ys | |||
There was a problem hiding this comment.
Since reverse mode doesn't support 3D anyway, we don't need to modify this file.
deepxde/gradients/gradients.py
Outdated
| """ | ||
| if config.autodiff == "reverse": | ||
| if bkd.ndim(ys) == 3: |
There was a problem hiding this comment.
Raise this error in gradients_reverse.py
No description provided.