explosion/spaCy
1
1
Fork 0
mirror of https://github.com/explosion/spaCy.git synced 2025-02-10 08:30:34 +03:00
Code Issues Packages Projects Releases Wiki Activity

Merge branch 'develop' of https://github.com/explosion/spaCy into develop

Browse Source
This commit is contained in:
Ines Montani 2020-07-01 15:33:57 +02:00
commit 4f42bcdd13
4 changed files with 20 additions and 13 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
spacy/about.py
View File

@ -1,6 +1,6 @@
# fmt: off # fmt: off
__title__ = "spacy" __title__ = "spacy"
__version__ = "3.0.0.dev13" __version__ = "3.0.0.dev14"
__release__ = True __release__ = True
__download_url__ = "https://github.com/explosion/spacy-models/releases/download" __download_url__ = "https://github.com/explosion/spacy-models/releases/download"
__compatibility__ = "https://raw.githubusercontent.com/explosion/spacy-models/master/compatibility.json" __compatibility__ = "https://raw.githubusercontent.com/explosion/spacy-models/master/compatibility.json"

5
spacy/cli/train.py
View File

@ -332,13 +332,14 @@ def create_evaluation_callback(nlp, optimizer, corpus, cfg):
) )
n_words = sum(len(ex.predicted) for ex in dev_examples) n_words = sum(len(ex.predicted) for ex in dev_examples)
batch_size = cfg.get("evaluation_batch_size", 128)
start_time = timer() start_time = timer()
if optimizer.averages: if optimizer.averages:
with nlp.use_params(optimizer.averages): with nlp.use_params(optimizer.averages):
scorer = nlp.evaluate(dev_examples, batch_size=32) scorer = nlp.evaluate(dev_examples, batch_size=batch_size)
else: else:
scorer = nlp.evaluate(dev_examples, batch_size=32) scorer = nlp.evaluate(dev_examples, batch_size=batch_size)
end_time = timer() end_time = timer()
wps = n_words / (end_time - start_time) wps = n_words / (end_time - start_time)
scores = scorer.scores scores = scorer.scores

24
spacy/gold/corpus.py
View File

@ -45,18 +45,22 @@ class Corpus:
def make_examples(self, nlp, reference_docs, max_length=0): def make_examples(self, nlp, reference_docs, max_length=0):
for reference in reference_docs: for reference in reference_docs:
if len(reference) >= max_length >= 1: if len(reference) == 0:
if reference.is_sentenced: continue
for ref_sent in reference.sents: elif max_length == 0 or len(reference) < max_length:
yield Example(
nlp.make_doc(ref_sent.text),
ref_sent.as_doc()
)
else:
yield Example( yield Example(
nlp.make_doc(reference.text), nlp.make_doc(reference.text),
reference reference
) )
elif reference.is_sentenced:
for ref_sent in reference.sents:
if len(ref_sent) == 0:
continue
elif max_length == 0 or len(ref_sent) < max_length:
yield Example(
nlp.make_doc(ref_sent.text),
ref_sent.as_doc()
)
def make_examples_gold_preproc(self, nlp, reference_docs): def make_examples_gold_preproc(self, nlp, reference_docs):
for reference in reference_docs: for reference in reference_docs:
@ -65,7 +69,7 @@ class Corpus:
else: else:
ref_sents = [reference] ref_sents = [reference]
for ref_sent in ref_sents: for ref_sent in ref_sents:
yield Example( eg = Example(
Doc( Doc(
nlp.vocab, nlp.vocab,
words=[w.text for w in ref_sent], words=[w.text for w in ref_sent],
@ -73,6 +77,8 @@ class Corpus:
), ),
ref_sent ref_sent
) )
if len(eg.x):
yield eg
def read_docbin(self, vocab, locs): def read_docbin(self, vocab, locs):
""" Yield training examples as example dicts """ """ Yield training examples as example dicts """

2
spacy/syntax/nn_parser.pyx
View File

@ -449,7 +449,7 @@ cdef class Parser:
if component is self: if component is self:
break break
if hasattr(component, "pipe"): if hasattr(component, "pipe"):
doc_sample = list(component.pipe(doc_sample)) doc_sample = list(component.pipe(doc_sample, batch_size=8))
else: else:
doc_sample = [component(doc) for doc in doc_sample] doc_sample = [component(doc) for doc in doc_sample]
if doc_sample: if doc_sample: