feat(inference): add average_samples flag to auto_regressive_inference#321
Open
moscowmule2240 wants to merge 1 commit into
Open
feat(inference): add average_samples flag to auto_regressive_inference#321moscowmule2240 wants to merge 1 commit into
moscowmule2240 wants to merge 1 commit into
Conversation
By default (average_samples=True) behavior is unchanged: predictions are averaged over the sample dimension. With average_samples=False the per-sample paths are returned with shape (batch, sample_count, total_seq, n_feat), letting callers obtain the full Monte Carlo distribution (probabilistic forecasting / uncertainty) without re-implementing the autoregressive loop. Backward compatible. Adds a docstring for the flag and tests/test_average_samples.py (fake model, no weight download) covering the shape behavior and mean-over-samples consistency.
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
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
What
Add an
average_samplesflag (default True) toauto_regressive_inference.Why
Obtaining individual sampled paths (probabilistic forecasting / uncertainty / quantile bands) currently requires re-implementing the autoregressive loop, since the function always collapses the sample dimension via np.mean. This is a one-line, fully backward-compatible change.
Tests
tests/test_average_samples.py (fake tokenizer/model, no weight download): shape behavior for both flag values + averaged == mean over samples.