[WIP] Introduce sentence weighting #1438
Closed
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
francoishernandez
force-pushed
the
sentence_weighting
branch
from
c816158 to
f6846f6
Compare
| if maybe_weights is not None: | ||
| weight_shards = split_corpus(maybe_weights, opt.shard_size) | ||
| else: | ||
| weight_shards = cycle(iter([cycle(iter([1]))])) |
There was a problem hiding this comment.
could be replaced by: repeat(cycle(iter([1])))
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Outdated suggestions cannot be applied.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.
Basic idea: give an additional file when preprocessing, containing sentence weights.
These weights will be stored in the torchtext
Examples and will be used to weight the loss in_compute_loss.I introduce the
-sentence_weightsopt, to which we are supposed to pass some text file(s) containing the weights for each sentence / example. If several corpora are passed according to #1413 upgrades, such weight files should be passed as well. If we want/have weights for only some of the corpora in the list, we can passNone/noneinstead of the filename and it will be cast to pythonNoneby argparse, and weights of 1 will be assigned.I did some tests on basic translation / speech / image runs, and it seems to be running without any issue.