explosion/spaCy
1
1
Fork 0
mirror of https://github.com/explosion/spaCy.git synced 2024-12-26 01:46:28 +03:00
Code Issues Packages Projects Releases Wiki Activity

it's only oversized if the tolerance level is also exceeded

Browse Source
This commit is contained in:
svlandeg 2020-06-02 19:59:04 +02:00
parent ef834b4cd7
commit f2e162fc60
1 changed files with 1 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
spacy/util.py
View File

@ -678,7 +678,7 @@ def minibatch_by_words(examples, size, count_words=len, tolerance=0.2, discard_o
n_words = count_words(example.doc) n_words = count_words(example.doc)
# if the current example exceeds the batch size, it is returned separately # if the current example exceeds the batch size, it is returned separately
# but only if discard_oversize=False. # but only if discard_oversize=False.
if n_words > target_size: if n_words > target_size + tol_size:
if not discard_oversize: if not discard_oversize:
yield [example] yield [example]