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
83 lines
3.6 KiB
Python
83 lines
3.6 KiB
Python
import pytest
|
|
|
|
from spacy.ml.models.tok2vec import build_Tok2Vec_model
|
|
from spacy.vocab import Vocab
|
|
from spacy.tokens import Doc
|
|
|
|
|
|
def get_batch(batch_size):
|
|
vocab = Vocab()
|
|
docs = []
|
|
start = 0
|
|
for size in range(1, batch_size + 1):
|
|
# Make the words numbers, so that they're distinct
|
|
# across the batch, and easy to track.
|
|
numbers = [str(i) for i in range(start, start + size)]
|
|
docs.append(Doc(vocab, words=numbers))
|
|
start += size
|
|
return docs
|
|
|
|
|
|
# This fails in Thinc v7.3.1. Need to push patch
|
|
@pytest.mark.xfail
|
|
def test_empty_doc():
|
|
width = 128
|
|
embed_size = 2000
|
|
vocab = Vocab()
|
|
doc = Doc(vocab, words=[])
|
|
# TODO: fix tok2vec arguments
|
|
tok2vec = build_Tok2Vec_model(width, embed_size)
|
|
vectors, backprop = tok2vec.begin_update([doc])
|
|
assert len(vectors) == 1
|
|
assert vectors[0].shape == (0, width)
|
|
|
|
|
|
@pytest.mark.parametrize(
|
|
"batch_size,width,embed_size", [[1, 128, 2000], [2, 128, 2000], [3, 8, 63]]
|
|
)
|
|
def test_tok2vec_batch_sizes(batch_size, width, embed_size):
|
|
batch = get_batch(batch_size)
|
|
tok2vec = build_Tok2Vec_model(
|
|
width,
|
|
embed_size,
|
|
pretrained_vectors=None,
|
|
conv_depth=4,
|
|
bilstm_depth=0,
|
|
window_size=1,
|
|
maxout_pieces=3,
|
|
subword_features=True,
|
|
char_embed=False,
|
|
nM=64,
|
|
nC=8,
|
|
)
|
|
tok2vec.initialize()
|
|
vectors, backprop = tok2vec.begin_update(batch)
|
|
assert len(vectors) == len(batch)
|
|
for doc_vec, doc in zip(vectors, batch):
|
|
assert doc_vec.shape == (len(doc), width)
|
|
|
|
|
|
# fmt: off
|
|
@pytest.mark.parametrize(
|
|
"tok2vec_config",
|
|
[
|
|
{"width": 8, "embed_size": 100, "char_embed": False, "nM": 64, "nC": 8, "pretrained_vectors": None, "window_size": 1, "conv_depth": 2, "bilstm_depth": 0, "maxout_pieces": 3, "subword_features": True},
|
|
{"width": 8, "embed_size": 100, "char_embed": True, "nM": 64, "nC": 8, "pretrained_vectors": None, "window_size": 1, "conv_depth": 2, "bilstm_depth": 0, "maxout_pieces": 3, "subword_features": True},
|
|
{"width": 8, "embed_size": 100, "char_embed": False, "nM": 64, "nC": 8, "pretrained_vectors": None, "window_size": 1, "conv_depth": 6, "bilstm_depth": 0, "maxout_pieces": 3, "subword_features": True},
|
|
{"width": 8, "embed_size": 100, "char_embed": False, "nM": 64, "nC": 8, "pretrained_vectors": None, "window_size": 1, "conv_depth": 6, "bilstm_depth": 0, "maxout_pieces": 3, "subword_features": True},
|
|
{"width": 8, "embed_size": 100, "char_embed": False, "nM": 64, "nC": 8, "pretrained_vectors": None, "window_size": 1, "conv_depth": 2, "bilstm_depth": 0, "maxout_pieces": 3, "subword_features": False},
|
|
{"width": 8, "embed_size": 100, "char_embed": False, "nM": 64, "nC": 8, "pretrained_vectors": None, "window_size": 3, "conv_depth": 2, "bilstm_depth": 0, "maxout_pieces": 3, "subword_features": False},
|
|
{"width": 8, "embed_size": 100, "char_embed": True, "nM": 81, "nC": 8, "pretrained_vectors": None, "window_size": 3, "conv_depth": 2, "bilstm_depth": 0, "maxout_pieces": 3, "subword_features": False},
|
|
{"width": 8, "embed_size": 100, "char_embed": True, "nM": 81, "nC": 9, "pretrained_vectors": None, "window_size": 3, "conv_depth": 2, "bilstm_depth": 0, "maxout_pieces": 3, "subword_features": False},
|
|
],
|
|
)
|
|
# fmt: on
|
|
def test_tok2vec_configs(tok2vec_config):
|
|
docs = get_batch(3)
|
|
tok2vec = build_Tok2Vec_model(**tok2vec_config)
|
|
tok2vec.initialize()
|
|
vectors, backprop = tok2vec.begin_update(docs)
|
|
assert len(vectors) == len(docs)
|
|
assert vectors[0].shape == (len(docs[0]), tok2vec_config["width"])
|
|
backprop(vectors)
|