Fix bug causing beams to not be reordered by log probability. #86
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
Add a reference to cheat some citations.
* saving to and loading from single hdf5 * fixed the indexing * flak8 * fixed paralle * changed function name * updated pre_process_script * fix for type * code cleanup * script added to convert old numpy files into h5 data
… we can directly use the loaded array size to create dataset); remove prepro_process_script.sh
* Update to pytorch4.1 * Refactor
* Update to pytorch4.1 * Refactor * Fix dataloader * Change to item
* Refactor * Fix typo
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Outdated suggestions cannot be applied.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.
Previously, because
beam_logprobs_sum[vix]is a pointer, line 120 would set it equal to -1000, causing the sort on line 126 to be meaningless (since everyx['p']would be -1000). I fix this by turning the tensor pointer into a float.