mirror of
https://github.com/explosion/spaCy.git
synced 2024-09-21 11:29:13 +03:00
311133e579
* bring back default build_text_classifier method * remove _set_dims_ hack in favor of proper dim inference * add tok2vec initialize to unit test * small fixes * add unit test for various textcat config settings * logistic output layer does not have nO * fix window_size setting * proper fix * fix W initialization * Update textcat training example * Use ml_datasets * Convert training data to `Example` format * Use `n_texts` to set proportionate dev size * fix _init renaming on latest thinc * avoid setting a non-existing dim * update to thinc==8.0.0a2 * add BOW and CNN defaults for easy testing * various experiments with train_textcat script, fix softmax activation in textcat bow * allow textcat train script to work on other datasets as well * have dataset as a parameter * train textcat from config, with example config * add config for training textcat * formatting * fix exclusive_classes * fixing BOW for GPU * bump thinc to 8.0.0a3 (not published yet so CI will fail) * add in link_vectors_to_models which got deleted Co-authored-by: Adriane Boyd <adrianeboyd@gmail.com>
33 lines
1004 B
Python
33 lines
1004 B
Python
from pydantic import StrictInt
|
|
from thinc.api import Model, chain, list2array, Linear, zero_init, use_ops
|
|
|
|
from ...util import registry
|
|
from .._precomputable_affine import PrecomputableAffine
|
|
from ...syntax._parser_model import ParserModel
|
|
|
|
|
|
@registry.architectures.register("spacy.TransitionBasedParser.v1")
|
|
def build_tb_parser_model(
|
|
tok2vec: Model,
|
|
nr_feature_tokens: StrictInt,
|
|
hidden_width: StrictInt,
|
|
maxout_pieces: StrictInt,
|
|
nO=None,
|
|
):
|
|
token_vector_width = tok2vec.get_dim("nO")
|
|
tok2vec = chain(tok2vec, list2array())
|
|
tok2vec.set_dim("nO", token_vector_width)
|
|
|
|
lower = PrecomputableAffine(
|
|
nO=hidden_width,
|
|
nF=nr_feature_tokens,
|
|
nI=tok2vec.get_dim("nO"),
|
|
nP=maxout_pieces,
|
|
)
|
|
lower.set_dim("nP", maxout_pieces)
|
|
with use_ops("numpy"):
|
|
# Initialize weights at zero, as it's a classification layer.
|
|
upper = Linear(nO=nO, init_W=zero_init)
|
|
model = ParserModel(tok2vec, lower, upper)
|
|
return model
|