explosion/spaCy
1
1
Fork 0
mirror of https://github.com/explosion/spaCy.git synced 2024-09-21 11:29:13 +03:00
Code Issues Packages Projects Releases Wiki Activity

Default to former TextCategorizer model

Browse Source 
* Keep TextCategorizer default model same as v2.0
* Add option 'architecture' that allows "simple_cnn" to switch to
simpler model.
* Add option exclusive_classes, defaulting to False. If set to True,
the model treats classes as mutually exclusive, i.e. only one class can
be true per instance.
This commit is contained in:
Matthew Honnibal 2019-02-23 11:55:16 +01:00
parent 829c9091a4
commit ce1e4eace2
1 changed files with 7 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

10
spacy/pipeline/pipes.pyx
View File

@ -24,7 +24,8 @@ from ..vocab cimport Vocab
from ..syntax import nonproj
from ..attrs import POS, ID
from ..parts_of_speech import X
from .._ml import Tok2Vec, build_tagger_model, build_simple_cnn_text_classifier
from .._ml import Tok2Vec, build_tagger_model
from .._ml import build_text_classifier, build_simple_cnn_text_classifier
from .._ml import link_vectors_to_models, zero_init, flatten
from .._ml import masked_language_model, create_default_optimizer
from ..errors import Errors, TempErrors
@ -862,8 +863,11 @@ class TextCategorizer(Pipe):
token_vector_width = cfg["token_vector_width"]
else:
token_vector_width = util.env_opt("token_vector_width", 96)
tok2vec = Tok2Vec(token_vector_width, embed_size, **cfg)
return build_simple_cnn_text_classifier(tok2vec, nr_class, **cfg)
if cfg.get('architecture') == 'simple_cnn':
tok2vec = Tok2Vec(token_vector_width, embed_size, **cfg)
return build_simple_cnn_text_classifier(tok2vec, nr_class, **cfg)
else:
return build_text_classifier(nr_class, **cfg)
@property
def tok2vec(self):