Skip to content
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

Exposed Deepset #170

Conversation

Chase-Grajeda
Copy link

  • Added summary_networks folder in experimental for future additions. Added __init__ file for exposed summary networks.
  • Added deepset implementation to summary network class hierarchy.

Added summary_networks folder in experimental for future additions.
Added __init__ file for exposed summary networks.
Added deepset implementation to summary network class hierarchy.
@stefanradev93
Copy link
Contributor

Nice! As discussed:

  • Add self-contained invariant / equivariant networks into own deepset module (folder with init.py)
  • Ensure everything works

Moved deep_set into networks folder.
Exposed the InvariantModule class.
Exposed the EquivariantModule class.
Added relevant imports to networks __init__.
@stefanradev93
Copy link
Contributor

Almost there! The new files should go into their own new folder (deepset) which will sit at the same level as set_transformer, coupling_flow, etc. and the new summary_networks folder should be removed.

Moved new classes to respective deep_set folder.
Removed summary_networks folder.
@stefanradev93 stefanradev93 merged commit e59f077 into bayesflow-org:streamlined-backend Jun 4, 2024
0 of 16 checks passed
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.

2 participants