mirror of
https://github.com/explosion/spaCy.git
synced 2024-09-21 19:39:13 +03:00
06f0a8daa0
* fix grad_clip naming * cleaning up pretrained_vectors out of cfg * further refactoring Model init's * move Model building out of pipes * further refactor to require a model config when creating a pipe * small fixes * making cfg in nn_parser more consistent * fixing nr_class for parser * fixing nn_parser's nO * fix printing of loss * architectures in own file per type, consistent naming * convenience methods default_tagger_config and default_tok2vec_config * let create_pipe access default config if available for that component * default_parser_config * move defaults to separate folder * allow reading nlp from package or dir with argument 'name' * architecture spacy.VocabVectors.v1 to read static vectors from file * cleanup * default configs for nel, textcat, morphologizer, tensorizer * fix imports * fixing unit tests * fixes and clean up * fixing defaults, nO, fix unit tests * restore parser IO * fix IO * 'fix' serialization test * add *.cfg to manifest * fix example configs with additional arguments * replace Morpohologizer with Tagger * add IO bit when testing overfitting of tagger (currently failing) * fix IO - don't initialize when reading from disk * expand overfitting tests to also check IO goes OK * remove dropout from HashEmbed to fix Tagger performance * add defaults for sentrec * update thinc * always pass a Model instance to a Pipe * fix piped_added statement * remove obsolete W029 * remove obsolete errors * restore byte checking tests (work again) * clean up test * further test cleanup * convert from config to Model in create_pipe * bring back error when component is not initialized * cleanup * remove calls for nlp2.begin_training * use thinc.api in imports * allow setting charembed's nM and nC * fix for hardcoded nM/nC + unit test * formatting fixes * trigger build
127 lines
3.6 KiB
Python
127 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.upper
|
|
|
|
# check that we have the correct settings, not the default ones
|
|
assert tok2vec.get_dim("nO") == 321
|
|
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.upper
|
|
|
|
# check that we have the correct settings, not the default ones
|
|
assert upper.get_dim("nI") == 66
|
|
assert tok2vec.get_dim("nO") == 333
|