Standardize recalculate_all_logprobs parameter across PF-based GFlowNets #231
+38
−13
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
younik
reviewed
Jan 22, 2025
src/gfn/gflownet/base.py
Outdated
| @@ -71,17 +71,12 @@ def to_training_samples(self, trajectories: Trajectories) -> TrainingSampleType: | |||
| """Converts trajectories to training samples. The type depends on the GFlowNet.""" | |||
|
|
|||
| @abstractmethod | |||
| def loss(self, env: Env, training_objects: Any): | |||
| def loss(self, env: Env, training_objects: Any, **kwargs: Any): | |||
There was a problem hiding this comment.
Why adding kwargs instead of recalculate_all_logprobs?
src/gfn/gflownet/base.py
Outdated
| env: Env, | ||
| training_objects: Any, | ||
| recalculate_all_logprobs: bool = False, | ||
| **kwargs: Any, |
Quoding
added a commit
to Quoding/torchgfn
that referenced
this pull request
Jan 22, 2025
Add doscrings Add input validation (as proposed by saleml) Add PFBasedGFlowNet verification instead of only TBGFNs (needs merge of GFNOrg#231)
josephdviviano
approved these changes
Jan 24, 2025
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Outdated suggestions cannot be applied.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.
This PR standardizes the handling of
recalculate_all_logprobsparameter across all policy-based GFlowNet implementations (TB, DB, SubTB).Changes:
recalculate_all_logprobsparameter toPFBasedGFlowNet.loss()abstract methodrecalculate_all_logprobs=False)recalculate_all_logprobs=True, force recalculation of logprobs even if they existThis change:
save_logprobs=False(introduced in Default behavior: recalculate logprobs #230)Context:
save_logprobs=Falseas default during sampling to improve memory efficiencyrecalculate_all_logprobsparameter