-
Notifications
You must be signed in to change notification settings - Fork 5
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
add DeepMoD_PC #13
base: main
Are you sure you want to change the base?
add DeepMoD_PC #13
Conversation
…d of importing the numpy module inside ngclearn
refactor importing
|
||
cov_cria = (coeff_track - coeff).mean() | ||
coeff_track = coeff | ||
if jnp.abs(cov_cria) <= 5e-8 or i==n_epochs-1: |
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.
if we have run all the epochs, and cov_cria
has not converged yet, we cannot call it converged. So I think we should remove the i == n_epochs - 1
condition and further optimize the model
self.model.reset() | ||
self.model.clamps(input, target) | ||
|
||
z_codes = self.model._process(jnp.array([[self.dt * i, self.dt] for i in range(self.T)])) |
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.
z_codes
was not used, is this needed?
I think it's fine to leave it there if it serves the ._process
purpose, leaving a comment will clarify for the reader
|
||
coeff_track = 0 | ||
for i in range(n_epochs): | ||
coeff, loss_pred = deepmod.process(ts_scaled, X) |
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 loss in this case is smaller than 0, you then checked if the absolute value of the loss is smaller than some constant (5e-8
), is this behavior desired?
I asked that because normally, the loss is greater than 0, and often converge toward 0.
No description provided.