explosion/spaCy
1
1
Fork 0
mirror of https://github.com/explosion/spaCy.git synced 2025-04-27 12:23:42 +03:00
Code Issues Packages Projects Releases Wiki Activity

Fix serialization of pretrained_dims property

Browse Source
This commit is contained in:
Matthew Honnibal 2017-09-19 23:42:27 +02:00
parent 2489dcaccf
commit b36a38f63d
1 changed files with 3 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

5
spacy/pipeline.pyx
View File

@ -214,6 +214,7 @@ class TokenVectorEncoder(BaseThincComponent):
self.vocab = vocab self.vocab = vocab
self.model = model self.model = model
self.cfg = dict(cfg) self.cfg = dict(cfg)
self.cfg['pretrained_dims'] = self.vocab.vectors.data.shape[1]
def __call__(self, doc): def __call__(self, doc):
"""Add context-sensitive vectors to a `Doc`, e.g. from a CNN or LSTM """Add context-sensitive vectors to a `Doc`, e.g. from a CNN or LSTM
@ -458,7 +459,7 @@ class NeuralTagger(BaseThincComponent):
token_vector_width = util.env_opt('token_vector_width', token_vector_width = util.env_opt('token_vector_width',
self.cfg.get('token_vector_width', 128)) self.cfg.get('token_vector_width', 128))
self.model = self.Model(self.vocab.morphology.n_tags, token_vector_width, self.model = self.Model(self.vocab.morphology.n_tags, token_vector_width,
pretrained_dims=self.vocab.vectors_length) **self.cfg)
self.model.from_bytes(p.open('rb').read()) self.model.from_bytes(p.open('rb').read())
def load_tag_map(p): def load_tag_map(p):
@ -470,10 +471,10 @@ class NeuralTagger(BaseThincComponent):
exc=self.vocab.morphology.exc) exc=self.vocab.morphology.exc)
deserialize = OrderedDict(( deserialize = OrderedDict((
('cfg', lambda p: self.cfg.update(_load_cfg(p))),
('vocab', lambda p: self.vocab.from_disk(p)), ('vocab', lambda p: self.vocab.from_disk(p)),
('tag_map', load_tag_map), ('tag_map', load_tag_map),
('model', load_model), ('model', load_model),
('cfg', lambda p: self.cfg.update(_load_cfg(p)))
)) ))
util.from_disk(path, deserialize, exclude) util.from_disk(path, deserialize, exclude)
return self return self