This repository has been archived by the owner on Dec 16, 2022. It is now read-only.
fix constraint bug in beam search, clean up tests #5328
Merged
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
epwalsh
commented
Jul 22, 2021
tests/nn/beam_search_test.py
Outdated
Comment on lines
763
to
773
| step_function = get_step_function(repeated_ngram_transition_probabilities_1) | ||
| self.beam_search.max_steps = 5 | ||
| expected_top_k = np.array([[1, 2, 3, 4, 5], [1, 2, 4, 3, 5]]) | ||
| expected_log_probs = np.log( | ||
| np.array([0.4 * 0.3 * 0.3 * 0.2 * 0.1, 0.4 * 0.3 * 0.2 * 0.3 * 0.1]) | ||
| ) | ||
| self._check_results( | ||
| expected_top_k=expected_top_k, | ||
| expected_log_probs=expected_log_probs, | ||
| take_step=step_function, | ||
| ) |
There was a problem hiding this comment.
This part fails before the fix.
There was a problem hiding this comment.
The rest of the changes to this file are just refactoring.
epwalsh
commented
Jul 22, 2021
Comment on lines
+1088
to
+1090
| backpointer = torch.divide( | ||
| restricted_beam_indices, self.per_node_beam_size, rounding_mode="trunc" | ||
| ) |
There was a problem hiding this comment.
This avoids a deprecation warning.
dirkgr
approved these changes
Jul 22, 2021
Comment on lines
+85
to
+87
| for last_token in last_predictions: | ||
| log_probs = torch.log(transition_matrix[last_token.item()]) | ||
| log_probs_list.append(log_probs) |
There was a problem hiding this comment.
It seems to me that there should be a way to do this without a for loop? Not that it really matters, but something like Tensor.index_select(...)?
Sign up for free
to subscribe to this conversation on GitHub.
Already have an account?
Sign in.
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Outdated suggestions cannot be applied.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 #5216 (comment) for context. @JohnGiorgi @danieldeutsch