mirror of
https://github.com/explosion/spaCy.git
synced 2024-09-22 03:49:17 +03:00
333b1a308b
* Draft layer for BILUO actions * Fixes to biluo layer * WIP on BILUO layer * Add tests for BILUO layer * Format * Fix transitions * Update test * Link in the simple_ner * Update BILUO tagger * Update __init__ * Import simple_ner * Update test * Import * Add files * Add config * Fix label passing for BILUO and tagger * Fix label handling for simple_ner component * Update simple NER test * Update config * Hack train script * Update BILUO layer * Fix SimpleNER component * Update train_from_config * Add biluo_to_iob helper * Add IOB layer * Add IOBTagger model * Update biluo layer * Update SimpleNER tagger * Update BILUO * Read random seed in train-from-config * Update use of normal_init * Fix normalization of gradient in SimpleNER * Update IOBTagger * Remove print * Tweak masking in BILUO * Add dropout in SimpleNER * Update thinc * Tidy up simple_ner * Fix biluo model * Unhack train-from-config * Update setup.cfg and requirements * Add tb_framework.py for parser model * Try to avoid memory leak in BILUO * Move ParserModel into spacy.ml, avoid need for subclass. * Use updated parser model * Remove incorrect call to model.initializre in PrecomputableAffine * Update parser model * Avoid divide by zero in tagger * Add extra dropout layer in tagger * Refine minibatch_by_words function to avoid oom * Fix parser model after refactor * Try to avoid div-by-zero in SimpleNER * Fix infinite loop in minibatch_by_words * Use SequenceCategoricalCrossentropy in Tagger * Fix parser model when hidden layer * Remove extra dropout from tagger * Add extra nan check in tagger * Fix thinc version * Update tests and imports * Fix test * Update test * Update tests * Fix tests * Fix test Co-authored-by: Ines Montani <ines@ines.io>
137 lines
3.6 KiB
Python
137 lines
3.6 KiB
Python
from thinc.api import Config
|
|
|
|
import spacy
|
|
from spacy import util
|
|
from spacy.lang.en import English
|
|
from spacy.util import registry
|
|
|
|
from ..util import make_tempdir
|
|
from ...ml.models import build_Tok2Vec_model, build_tb_parser_model
|
|
|
|
nlp_config_string = """
|
|
[nlp]
|
|
lang = "en"
|
|
|
|
[nlp.pipeline.tok2vec]
|
|
factory = "tok2vec"
|
|
|
|
[nlp.pipeline.tok2vec.model]
|
|
@architectures = "spacy.HashEmbedCNN.v1"
|
|
pretrained_vectors = null
|
|
width = 342
|
|
depth = 4
|
|
window_size = 1
|
|
embed_size = 2000
|
|
maxout_pieces = 3
|
|
subword_features = true
|
|
|
|
[nlp.pipeline.tagger]
|
|
factory = "tagger"
|
|
|
|
[nlp.pipeline.tagger.model]
|
|
@architectures = "spacy.Tagger.v1"
|
|
|
|
[nlp.pipeline.tagger.model.tok2vec]
|
|
@architectures = "spacy.Tok2VecTensors.v1"
|
|
width = ${nlp.pipeline.tok2vec.model:width}
|
|
"""
|
|
|
|
|
|
parser_config_string = """
|
|
[model]
|
|
@architectures = "spacy.TransitionBasedParser.v1"
|
|
nr_feature_tokens = 99
|
|
hidden_width = 66
|
|
maxout_pieces = 2
|
|
|
|
[model.tok2vec]
|
|
@architectures = "spacy.HashEmbedCNN.v1"
|
|
pretrained_vectors = null
|
|
width = 333
|
|
depth = 4
|
|
embed_size = 5555
|
|
window_size = 1
|
|
maxout_pieces = 7
|
|
subword_features = false
|
|
"""
|
|
|
|
|
|
@registry.architectures.register("my_test_parser")
|
|
def my_parser():
|
|
tok2vec = build_Tok2Vec_model(
|
|
width=321,
|
|
embed_size=5432,
|
|
pretrained_vectors=None,
|
|
window_size=3,
|
|
maxout_pieces=4,
|
|
subword_features=True,
|
|
char_embed=True,
|
|
nM=64,
|
|
nC=8,
|
|
conv_depth=2,
|
|
bilstm_depth=0,
|
|
)
|
|
parser = build_tb_parser_model(
|
|
tok2vec=tok2vec, nr_feature_tokens=7, hidden_width=65, maxout_pieces=5
|
|
)
|
|
return parser
|
|
|
|
|
|
def test_serialize_nlp():
|
|
""" Create a custom nlp pipeline from config and ensure it serializes it correctly """
|
|
nlp_config = Config().from_str(nlp_config_string)
|
|
nlp = util.load_model_from_config(nlp_config["nlp"])
|
|
nlp.begin_training()
|
|
assert "tok2vec" in nlp.pipe_names
|
|
assert "tagger" in nlp.pipe_names
|
|
assert "parser" not in nlp.pipe_names
|
|
assert nlp.get_pipe("tagger").model.get_ref("tok2vec").get_dim("nO") == 342
|
|
|
|
with make_tempdir() as d:
|
|
nlp.to_disk(d)
|
|
nlp2 = spacy.load(d)
|
|
assert "tok2vec" in nlp2.pipe_names
|
|
assert "tagger" in nlp2.pipe_names
|
|
assert "parser" not in nlp2.pipe_names
|
|
assert nlp2.get_pipe("tagger").model.get_ref("tok2vec").get_dim("nO") == 342
|
|
|
|
|
|
def test_serialize_custom_nlp():
|
|
""" Create a custom nlp pipeline and ensure it serializes it correctly"""
|
|
nlp = English()
|
|
parser_cfg = dict()
|
|
parser_cfg["model"] = {"@architectures": "my_test_parser"}
|
|
parser = nlp.create_pipe("parser", parser_cfg)
|
|
nlp.add_pipe(parser)
|
|
nlp.begin_training()
|
|
|
|
with make_tempdir() as d:
|
|
nlp.to_disk(d)
|
|
nlp2 = spacy.load(d)
|
|
model = nlp2.get_pipe("parser").model
|
|
tok2vec = model.get_ref("tok2vec")
|
|
upper = model.get_ref("upper")
|
|
|
|
# check that we have the correct settings, not the default ones
|
|
assert upper.get_dim("nI") == 65
|
|
|
|
|
|
def test_serialize_parser():
|
|
""" Create a non-default parser config to check nlp serializes it correctly """
|
|
nlp = English()
|
|
model_config = Config().from_str(parser_config_string)
|
|
parser = nlp.create_pipe("parser", config=model_config)
|
|
parser.add_label("nsubj")
|
|
nlp.add_pipe(parser)
|
|
nlp.begin_training()
|
|
|
|
with make_tempdir() as d:
|
|
nlp.to_disk(d)
|
|
nlp2 = spacy.load(d)
|
|
model = nlp2.get_pipe("parser").model
|
|
tok2vec = model.get_ref("tok2vec")
|
|
upper = model.get_ref("upper")
|
|
|
|
# check that we have the correct settings, not the default ones
|
|
assert upper.get_dim("nI") == 66
|