Refactor log probability calculations into separate utility functions #216
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
…into util functions
josephdviviano
requested changes
Nov 14, 2024
There was a problem hiding this comment.
This is an awesome PR, I think having these functions factored out will come in handy down the line as well for novel methods which might calculate these elements slightly differently. I think we should rename the function calls but this is a minor nit. I'll also wait for @younik before approving.
| @@ -78,6 +79,13 @@ def logF_parameters(self): | |||
| ) | |||
| ) | |||
|
|
|||
| def get_pfs_and_pbs( | |||
There was a problem hiding this comment.
sorry, I misunderstood. I quite like this factorization.
| valid_log_pf_actions = self.pf.to_probability_distribution( | ||
| states, module_output | ||
| ).log_prob(actions.tensor) | ||
| log_pf_actions, log_pb_actions = self.get_pfs_and_pbs( |
There was a problem hiding this comment.
ok I really like this.
younik
approved these changes
Nov 15, 2024
src/gfn/gflownet/detailed_balance.py
Outdated
| log_pb_actions = targets.clone() | ||
| targets[~valid_transitions_is_done] += valid_log_F_s_next | ||
| log_F_s_next = torch.zeros_like(log_pb_actions) | ||
| log_F_s_next[~valid_transitions_is_done] += valid_log_F_s_next |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
See the issue #211.
To address the need for calculating log probabilities in
Sampler, we decided to separate the logic for computinglog_probsfrom theGFlowNetclasses and instead create utility functions for these calculations.Naming (of variables, files, etc.) suggestions are welcomed!