Fix tag map clobbering in spacy train (#6437)

Fix bug from #5768 where the tag map is clobbered if a custom tag map
isn't provided.
This commit is contained in:
Adriane Boyd 2020-11-24 13:13:16 +01:00 committed by GitHub
parent ce18fc6588
commit 573f5c863f
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
1 changed files with 4 additions and 5 deletions

View File

@ -137,9 +137,6 @@ def train(
output_path.mkdir()
msg.good("Created output directory: {}".format(output_path))
tag_map = {}
if tag_map_path is not None:
tag_map = srsly.read_json(tag_map_path)
# Take dropout and batch size as generators of values -- dropout
# starts high and decays sharply, to force the optimizer to explore.
# Batch size starts at 1 and grows, so that we make updates quickly
@ -250,8 +247,10 @@ def train(
pipe_cfg = {}
nlp.add_pipe(nlp.create_pipe(pipe, config=pipe_cfg))
# Replace tag map with provided mapping
nlp.vocab.morphology.load_tag_map(tag_map)
if tag_map_path is not None:
tag_map = srsly.read_json(tag_map_path)
# Replace tag map with provided mapping
nlp.vocab.morphology.load_tag_map(tag_map)
# Create empty extra lexeme tables so the data from spacy-lookups-data
# isn't loaded if these features are accessed