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

Skip duplicate lexeme rank setting (#5401)

Browse Source 
Skip duplicate lexeme rank setting within
`_fix_pretrained_vectors_name()`.
This commit is contained in:
adrianeboyd 2020-05-14 18:26:12 +02:00 committed by GitHub
parent f49e2810e6
commit 908dea3939
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
2 changed files with 8 additions and 7 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

13
spacy/_ml.py
View File

@ -279,18 +279,19 @@ class PrecomputableAffine(Model):
break break
def link_vectors_to_models(vocab): def link_vectors_to_models(vocab, skip_rank=False):
vectors = vocab.vectors vectors = vocab.vectors
if vectors.name is None: if vectors.name is None:
vectors.name = VECTORS_KEY vectors.name = VECTORS_KEY
if vectors.data.size != 0: if vectors.data.size != 0:
warnings.warn(Warnings.W020.format(shape=vectors.data.shape)) warnings.warn(Warnings.W020.format(shape=vectors.data.shape))
ops = Model.ops ops = Model.ops
for word in vocab: if not skip_rank:
if word.orth in vectors.key2row: for word in vocab:
word.rank = vectors.key2row[word.orth] if word.orth in vectors.key2row:
else: word.rank = vectors.key2row[word.orth]
word.rank = util.OOV_RANK else:
word.rank = util.OOV_RANK
data = ops.asarray(vectors.data) data = ops.asarray(vectors.data)
# Set an entry here, so that vectors are accessed by StaticVectors # Set an entry here, so that vectors are accessed by StaticVectors
# (unideal, I know) # (unideal, I know)

2
spacy/language.py
View File

@ -1072,7 +1072,7 @@ def _fix_pretrained_vectors_name(nlp):
else: else:
raise ValueError(Errors.E092) raise ValueError(Errors.E092)
if nlp.vocab.vectors.size != 0: if nlp.vocab.vectors.size != 0:
link_vectors_to_models(nlp.vocab) link_vectors_to_models(nlp.vocab, skip_rank=True)
for name, proc in nlp.pipeline: for name, proc in nlp.pipeline:
if not hasattr(proc, "cfg"): if not hasattr(proc, "cfg"):
continue continue