-
Notifications
You must be signed in to change notification settings - Fork 762
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Support forward-mode AD #1903
base: master
Are you sure you want to change the base?
Support forward-mode AD #1903
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
deepxde/data/pde_operator.py
Outdated
error = bc.error( | ||
error_f = [fi[:, bcs_start[-1] :] for fi in f] | ||
# Each error has the shape (N1, ~N2) | ||
losses = [loss_fn(bkd.zeros_like(error), error) for error in error_f] |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
The same thing here. For example, if loss_fn
is sum
, then the code is not correct. Need to first compute the loss for each function, then average over functions.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Also this part. What is the speed of the current code vs the correct code?
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Support forward-mode AD and fix a bug when multi-output is needed