mirror of
https://github.com/explosion/spaCy.git
synced 2024-09-21 11:29:13 +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>
91 lines
2.0 KiB
Python
91 lines
2.0 KiB
Python
import pytest
|
|
from spacy.ml.models.defaults import default_parser, default_tok2vec
|
|
from spacy.vocab import Vocab
|
|
from spacy.syntax.arc_eager import ArcEager
|
|
from spacy.syntax.nn_parser import Parser
|
|
from spacy.tokens.doc import Doc
|
|
from spacy.gold import GoldParse
|
|
from thinc.api import Model
|
|
|
|
|
|
@pytest.fixture
|
|
def vocab():
|
|
return Vocab()
|
|
|
|
|
|
@pytest.fixture
|
|
def arc_eager(vocab):
|
|
actions = ArcEager.get_actions(left_labels=["L"], right_labels=["R"])
|
|
return ArcEager(vocab.strings, actions)
|
|
|
|
|
|
@pytest.fixture
|
|
def tok2vec():
|
|
tok2vec = default_tok2vec()
|
|
tok2vec.initialize()
|
|
return tok2vec
|
|
|
|
|
|
@pytest.fixture
|
|
def parser(vocab, arc_eager):
|
|
return Parser(vocab, model=default_parser(), moves=arc_eager)
|
|
|
|
|
|
@pytest.fixture
|
|
def model(arc_eager, tok2vec, vocab):
|
|
model = default_parser()
|
|
model.attrs["resize_output"](model, arc_eager.n_moves)
|
|
model.initialize()
|
|
return model
|
|
|
|
|
|
@pytest.fixture
|
|
def doc(vocab):
|
|
return Doc(vocab, words=["a", "b", "c"])
|
|
|
|
|
|
@pytest.fixture
|
|
def gold(doc):
|
|
return GoldParse(doc, heads=[1, 1, 1], deps=["L", "ROOT", "R"])
|
|
|
|
|
|
def test_can_init_nn_parser(parser):
|
|
assert isinstance(parser.model, Model)
|
|
|
|
|
|
def test_build_model(parser, vocab):
|
|
parser.model = Parser(vocab, model=default_parser(), moves=parser.moves).model
|
|
assert parser.model is not None
|
|
|
|
|
|
def test_predict_doc(parser, tok2vec, model, doc):
|
|
doc.tensor = tok2vec.predict([doc])[0]
|
|
parser.model = model
|
|
parser(doc)
|
|
|
|
|
|
def test_update_doc(parser, model, doc, gold):
|
|
parser.model = model
|
|
|
|
def optimize(key, weights, gradient):
|
|
weights -= 0.001 * gradient
|
|
return weights, gradient
|
|
|
|
parser.update((doc, gold), sgd=optimize)
|
|
|
|
|
|
@pytest.mark.xfail
|
|
def test_predict_doc_beam(parser, model, doc):
|
|
parser.model = model
|
|
parser(doc, beam_width=32, beam_density=0.001)
|
|
|
|
|
|
@pytest.mark.xfail
|
|
def test_update_doc_beam(parser, model, doc, gold):
|
|
parser.model = model
|
|
|
|
def optimize(weights, gradient, key=None):
|
|
weights -= 0.001 * gradient
|
|
|
|
parser.update_beam((doc, gold), sgd=optimize)
|