explosion/spaCy
1
1
Fork 0
mirror of https://github.com/explosion/spaCy.git synced 2024-09-21 11:29:13 +03:00
Code Issues Packages Projects Releases Wiki Activity

Update thinc dependency to 9.0.0.dev4

Browse Source
This commit is contained in:
Daniël de Kok 2024-01-16 14:54:26 +01:00
parent 7718886fa3
commit 7351f6bbeb
8 changed files with 16 additions and 22 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
pyproject.toml
View File

@ -5,7 +5,7 @@ requires = [
"cymem>=2.0.2,<2.1.0", "cymem>=2.0.2,<2.1.0",
"preshed>=3.0.2,<3.1.0", "preshed>=3.0.2,<3.1.0",
"murmurhash>=0.28.0,<1.1.0", "murmurhash>=0.28.0,<1.1.0",
"thinc>=9.0.0.dev2,<9.1.0", "thinc>=9.0.0.dev4,<9.1.0",
"numpy>=1.15.0", "numpy>=1.15.0",
] ]
build-backend = "setuptools.build_meta" build-backend = "setuptools.build_meta"

2
requirements.txt
View File

@ -3,7 +3,7 @@ spacy-legacy>=4.0.0.dev0,<4.1.0
spacy-loggers>=1.0.0,<2.0.0 spacy-loggers>=1.0.0,<2.0.0
cymem>=2.0.2,<2.1.0 cymem>=2.0.2,<2.1.0
preshed>=3.0.2,<3.1.0 preshed>=3.0.2,<3.1.0
thinc>=9.0.0.dev2,<9.1.0 thinc>=9.0.0.dev4,<9.1.0
ml_datasets>=0.2.0,<0.3.0 ml_datasets>=0.2.0,<0.3.0
murmurhash>=0.28.0,<1.1.0 murmurhash>=0.28.0,<1.1.0
wasabi>=0.9.1,<1.2.0 wasabi>=0.9.1,<1.2.0

4
setup.cfg
View File

@ -37,7 +37,7 @@ setup_requires =
cymem>=2.0.2,<2.1.0 cymem>=2.0.2,<2.1.0
preshed>=3.0.2,<3.1.0 preshed>=3.0.2,<3.1.0
murmurhash>=0.28.0,<1.1.0 murmurhash>=0.28.0,<1.1.0
thinc>=9.0.0.dev2,<9.1.0 thinc>=9.0.0.dev4,<9.1.0
install_requires = install_requires =
# Our libraries # Our libraries
spacy-legacy>=4.0.0.dev0,<4.1.0 spacy-legacy>=4.0.0.dev0,<4.1.0
@ -45,7 +45,7 @@ install_requires =
murmurhash>=0.28.0,<1.1.0 murmurhash>=0.28.0,<1.1.0
cymem>=2.0.2,<2.1.0 cymem>=2.0.2,<2.1.0
preshed>=3.0.2,<3.1.0 preshed>=3.0.2,<3.1.0
thinc>=9.0.0.dev2,<9.1.0 thinc>=9.0.0.dev4,<9.1.0
wasabi>=0.9.1,<1.2.0 wasabi>=0.9.1,<1.2.0
srsly>=2.4.3,<3.0.0 srsly>=2.4.3,<3.0.0
catalogue>=2.0.6,<2.1.0 catalogue>=2.0.6,<2.1.0

7
spacy/pipeline/edit_tree_lemmatizer.py
View File

@ -5,7 +5,6 @@ from typing import Any, Callable, Dict, Iterable, List, Optional, Tuple, Union,
import numpy as np import numpy as np
import srsly import srsly
from thinc.api import Config, Model, NumpyOps, SequenceCategoricalCrossentropy from thinc.api import Config, Model, NumpyOps, SequenceCategoricalCrossentropy
from thinc.legacy import LegacySequenceCategoricalCrossentropy
from thinc.types import ArrayXd, Floats2d, Ints1d from thinc.types import ArrayXd, Floats2d, Ints1d
from .. import util from .. import util
@ -131,9 +130,7 @@ class EditTreeLemmatizer(TrainablePipe):
self, examples: Iterable[Example], scores: List[Floats2d] self, examples: Iterable[Example], scores: List[Floats2d]
) -> Tuple[float, List[Floats2d]]: ) -> Tuple[float, List[Floats2d]]:
validate_examples(examples, "EditTreeLemmatizer.get_loss") validate_examples(examples, "EditTreeLemmatizer.get_loss")
loss_func = LegacySequenceCategoricalCrossentropy( loss_func = SequenceCategoricalCrossentropy(normalize=False, missing_value=-1)
normalize=False, missing_value=-1
)
truths = [] truths = []
for eg in examples: for eg in examples:
@ -169,7 +166,7 @@ class EditTreeLemmatizer(TrainablePipe):
DOCS: https://spacy.io/api/edittreelemmatizer#get_teacher_student_loss DOCS: https://spacy.io/api/edittreelemmatizer#get_teacher_student_loss
""" """
loss_func = LegacySequenceCategoricalCrossentropy(normalize=False) loss_func = SequenceCategoricalCrossentropy(normalize=False)
d_scores, loss = loss_func(student_scores, teacher_scores) d_scores, loss = loss_func(student_scores, teacher_scores)
if self.model.ops.xp.isnan(loss): if self.model.ops.xp.isnan(loss):
raise ValueError(Errors.E910.format(name=self.name)) raise ValueError(Errors.E910.format(name=self.name))

7
spacy/pipeline/morphologizer.pyx
View File

@ -2,8 +2,7 @@
from itertools import islice from itertools import islice
from typing import Callable, Dict, Iterable, Optional, Union from typing import Callable, Dict, Iterable, Optional, Union
from thinc.api import Config, Model from thinc.api import Config, Model, SequenceCategoricalCrossentropy
from thinc.legacy import LegacySequenceCategoricalCrossentropy
from ..morphology cimport Morphology from ..morphology cimport Morphology
from ..tokens.doc cimport Doc from ..tokens.doc cimport Doc
@ -296,8 +295,8 @@ class Morphologizer(Tagger):
DOCS: https://spacy.io/api/morphologizer#get_loss DOCS: https://spacy.io/api/morphologizer#get_loss
""" """
validate_examples(examples, "Morphologizer.get_loss") validate_examples(examples, "Morphologizer.get_loss")
loss_func = LegacySequenceCategoricalCrossentropy(names=self.labels, normalize=False, loss_func = SequenceCategoricalCrossentropy(names=self.labels, normalize=False,
label_smoothing=self.cfg["label_smoothing"]) label_smoothing=self.cfg["label_smoothing"])
truths = [] truths = []
for eg in examples: for eg in examples:
eg_truths = [] eg_truths = []

5
spacy/pipeline/senter.pyx
View File

@ -2,8 +2,7 @@
from itertools import islice from itertools import islice
from typing import Callable, Iterable, Optional from typing import Callable, Iterable, Optional
from thinc.api import Config, Model from thinc.api import Config, Model, SequenceCategoricalCrossentropy
from thinc.legacy import LegacySequenceCategoricalCrossentropy
from ..tokens.doc cimport Doc from ..tokens.doc cimport Doc
@ -158,7 +157,7 @@ class SentenceRecognizer(Tagger):
""" """
validate_examples(examples, "SentenceRecognizer.get_loss") validate_examples(examples, "SentenceRecognizer.get_loss")
labels = self.labels labels = self.labels
loss_func = LegacySequenceCategoricalCrossentropy(names=labels, normalize=False) loss_func = SequenceCategoricalCrossentropy(names=labels, normalize=False)
truths = [] truths = []
for eg in examples: for eg in examples:
eg_truth = [] eg_truth = []

7
spacy/pipeline/tagger.pyx
View File

@ -3,8 +3,7 @@ from itertools import islice
from typing import Callable, Dict, Iterable, List, Optional, Tuple, Union from typing import Callable, Dict, Iterable, List, Optional, Tuple, Union
import numpy import numpy
from thinc.api import Config, Model, set_dropout_rate from thinc.api import Config, Model, SequenceCategoricalCrossentropy, set_dropout_rate
from thinc.legacy import LegacySequenceCategoricalCrossentropy
from thinc.types import Floats2d, Ints1d from thinc.types import Floats2d, Ints1d
from ..tokens.doc cimport Doc from ..tokens.doc cimport Doc
@ -276,7 +275,7 @@ class Tagger(TrainablePipe):
DOCS: https://spacy.io/api/tagger#get_teacher_student_loss DOCS: https://spacy.io/api/tagger#get_teacher_student_loss
""" """
loss_func = LegacySequenceCategoricalCrossentropy(normalize=False) loss_func = SequenceCategoricalCrossentropy(normalize=False)
d_scores, loss = loss_func(student_scores, teacher_scores) d_scores, loss = loss_func(student_scores, teacher_scores)
if self.model.ops.xp.isnan(loss): if self.model.ops.xp.isnan(loss):
raise ValueError(Errors.E910.format(name=self.name)) raise ValueError(Errors.E910.format(name=self.name))
@ -293,7 +292,7 @@ class Tagger(TrainablePipe):
DOCS: https://spacy.io/api/tagger#get_loss DOCS: https://spacy.io/api/tagger#get_loss
""" """
validate_examples(examples, "Tagger.get_loss") validate_examples(examples, "Tagger.get_loss")
loss_func = LegacySequenceCategoricalCrossentropy( loss_func = SequenceCategoricalCrossentropy(
names=self.labels, names=self.labels,
normalize=False, normalize=False,
neg_prefix=self.cfg["neg_prefix"], neg_prefix=self.cfg["neg_prefix"],

4
spacy/pipeline/transition_parser.pyx
View File

@ -21,13 +21,13 @@ from thinc.api import (
CupyOps, CupyOps,
NumpyOps, NumpyOps,
Optimizer, Optimizer,
SequenceCategoricalCrossentropy,
chain, chain,
get_ops, get_ops,
set_dropout_rate, set_dropout_rate,
softmax_activation, softmax_activation,
use_ops, use_ops,
) )
from thinc.legacy import LegacySequenceCategoricalCrossentropy
from thinc.types import Floats2d from thinc.types import Floats2d
from ..ml.parser_model cimport ( from ..ml.parser_model cimport (
@ -349,7 +349,7 @@ cdef class Parser(TrainablePipe):
DOCS: https://spacy.io/api/dependencyparser#get_teacher_student_loss DOCS: https://spacy.io/api/dependencyparser#get_teacher_student_loss
""" """
loss_func = LegacySequenceCategoricalCrossentropy(normalize=False) loss_func = SequenceCategoricalCrossentropy(normalize=False)
d_scores, loss = loss_func(student_scores, teacher_scores) d_scores, loss = loss_func(student_scores, teacher_scores)
if self.model.ops.xp.isnan(loss): if self.model.ops.xp.isnan(loss):
raise ValueError(Errors.E910.format(name=self.name)) raise ValueError(Errors.E910.format(name=self.name))