explosion/spaCy
1
1
Fork 0
mirror of https://github.com/explosion/spaCy.git synced 2025-02-04 21:50:35 +03:00
Code Issues Packages Projects Releases Wiki Activity

Pass values for CNN maxout pieces option

Browse Source
This commit is contained in:
Matthew Honnibal 2017-09-20 19:15:49 -05:00
parent b832f89ff8
commit 24e85c2048
2 changed files with 6 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

8
spacy/pipeline.pyx
View File

@ -215,6 +215,7 @@ class TokenVectorEncoder(BaseThincComponent):
self.model = model self.model = model
self.cfg = dict(cfg) self.cfg = dict(cfg)
self.cfg['pretrained_dims'] = self.vocab.vectors.data.shape[1] self.cfg['pretrained_dims'] = self.vocab.vectors.data.shape[1]
self.cfg.setdefault('cnn_maxout_pieces', 2)
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
@ -286,9 +287,7 @@ class TokenVectorEncoder(BaseThincComponent):
pipeline (list): The pipeline the model is part of. pipeline (list): The pipeline the model is part of.
""" """
if self.model is True: if self.model is True:
self.model = self.Model( self.model = self.Model(**self.cfg)
pretrained_dims=self.vocab.vectors_length,
**self.cfg)
class NeuralTagger(BaseThincComponent): class NeuralTagger(BaseThincComponent):
@ -297,6 +296,7 @@ class NeuralTagger(BaseThincComponent):
self.vocab = vocab self.vocab = vocab
self.model = model self.model = model
self.cfg = dict(cfg) self.cfg = dict(cfg)
self.cfg.setdefault('cnn_maxout_pieces', 2)
def __call__(self, doc): def __call__(self, doc):
tags = self.predict(([doc], [doc.tensor])) tags = self.predict(([doc], [doc.tensor]))
@ -442,6 +442,7 @@ class NeuralTagger(BaseThincComponent):
return self return self
def to_disk(self, path, **exclude): def to_disk(self, path, **exclude):
self.cfg['pretrained_dims'] = self.vocab.vectors.data.shape[1]
serialize = OrderedDict(( serialize = OrderedDict((
('vocab', lambda p: self.vocab.to_disk(p)), ('vocab', lambda p: self.vocab.to_disk(p)),
('tag_map', lambda p: p.open('wb').write(msgpack.dumps( ('tag_map', lambda p: p.open('wb').write(msgpack.dumps(
@ -486,6 +487,7 @@ class NeuralLabeller(NeuralTagger):
self.vocab = vocab self.vocab = vocab
self.model = model self.model = model
self.cfg = dict(cfg) self.cfg = dict(cfg)
self.cfg.setdefault('cnn_maxout_pieces', 2)
@property @property
def labels(self): def labels(self):

1
spacy/syntax/nn_parser.pyx
View File

@ -309,6 +309,7 @@ cdef class Parser:
cfg['beam_density'] = util.env_opt('beam_density', 0.0) cfg['beam_density'] = util.env_opt('beam_density', 0.0)
if 'pretrained_dims' not in cfg: if 'pretrained_dims' not in cfg:
cfg['pretrained_dims'] = self.vocab.vectors.data.shape[1] cfg['pretrained_dims'] = self.vocab.vectors.data.shape[1]
cfg.setdefault('cnn_maxout_pieces', 2)
self.cfg = cfg self.cfg = cfg
if 'actions' in self.cfg: if 'actions' in self.cfg:
for action, labels in self.cfg.get('actions', {}).items(): for action, labels in self.cfg.get('actions', {}).items():