Skip to content

Conversation

khushant2001
Copy link
Collaborator

Adding EDMD implementation to the latent space dynamics. Updated codebase allows user to choose standard/extended DMD through the .yml file.

fd = None
fd_oper = None

def __init__(self, dim, high_order_terms, rand_functions, nt, config):
Copy link
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Based on the usage shown below, high_order_terms and rand_functions can be parsed from config and need not be passed as input arguments. Can we parse them from config and reduce the number of input arguments?

Copy link
Collaborator Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

They could be. But updating the workflow maintains the original structure of defining trainers/latent space/latent physics. Can update it your way through if necessary!


# Updating the dynamics callback to account for the higher order terms and other non linear functions from the .yml file.

latent_dynamics = ld_dict[ld_type](latent_space.n_z, config['latent_dynamics'][ld_type]['higher_order_terms'], config['latent_dynamics'][ld_type]['extra_functions'], physics.nt, config['latent_dynamics'])
Copy link
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

As I mentioned above, high_order_terms and rand_functions can be parsed from config and need not be passed as input arguments. That way we wouldn't have to change this line.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

3 participants