This repository has been archived by the owner on Nov 3, 2023. It is now read-only.
faster ranking at prediction time #1498
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
|
Not sure why the tests aren't starting (and fail) |
emilydinan
approved these changes
Mar 5, 2019
parlai/core/torch_ranker_agent.py
Outdated
| @@ -190,6 +194,8 @@ def eval_step(self, batch): | |||
| rank = (ranks[b] == label_inds[b]).nonzero().item() | |||
| self.metrics['rank'] += 1 + rank | |||
|
|
|||
| ranks = ranks.cpu() | |||
| max_preds = self.opt["cap_num_predictions"] | |||
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Outdated suggestions cannot be applied.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.
In the case of doing predictions with 100k candidates, this part was a bit slow. This modification makes a single prediction with 100k candidates going from 2.6 sec to < 0.1 sec.