-
Notifications
You must be signed in to change notification settings - Fork 196
Fix docs #1640
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
Closed
Closed
Fix docs #1640
Conversation
This file contains hidden or 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
…o utils/vector_field_utils.py
- changed net type in ConditionalScoreEstimator and related classes to VectorFieldNet - added embedding_net to ConditionalScoreEstimator for condition embedding
…networks, keeping others as independent
- replaced flowmatcher and score estimator imports with vector field equivalents - introduced new vector field neural network builders for MLP and transformer architectures - enhanced flowmatching_nn and posterior_score_nn functions to support new model types - added custom euler integration method in FlowMatchingEstimator for improved sampling - updated z-score handling and embedding net integration in estimator classes Remaining bugs: - Extra num_samples dim in Zuko sampling function that we need to fix
- increased hidden_features from 50 to 64 in posterior_score_nn to make it divisible by num_heads - added vector_field_fn to FlowMatchingEstimator for better dimension handling during sampling - implemented reshaping logic in ConditionalScoreEstimator to manage sample dimensions during batch processing
- replaced direct condition input with embedded condition in log_prob, sample, and sample_and_log_prob methods - removed commented-out code and print statements for cleaner implementation - updated score estimator import to use posterior_score_nn in tests/score_samplers_test.py
…ialization - removed noise_scale parameter from FlowMatchingEstimator - adjusted vector field calculation in FlowMatchingEstimator for improved accuracy - modified last layer initialization in AdaMLPBlock and DiTBlock to scale weights instead of zeroing - streamlined MLP block processing in GlobalEmbeddingMLP for clarity
…ow_builders_to_current_main
…d be seperate! (as they have different preconditionrs)
Add tests for consistentency of score and flow estimators
…s to test (i.e .use defaults).
This reverts commit 7eeaa7d.
Codecov Report✅ All modified and coverable lines are covered by tests. Additional details and impacted files@@ Coverage Diff @@
## main #1640 +/- ##
=======================================
Coverage ? 82.49%
=======================================
Files ? 134
Lines ? 11136
Branches ? 0
=======================================
Hits ? 9187
Misses ? 1949
Partials ? 0
Flags with carried forward coverage won't be shown. Click here to find out more. |
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.
Some paths in the docs need to be adjusted.