explosion/spaCy
1
1
Fork 0
mirror of https://github.com/explosion/spaCy.git synced 2024-11-11 04:08:09 +03:00
Code Issues Packages Projects Releases Wiki Activity

Fix tensorizer

Browse Source
This commit is contained in:
Matthew Honnibal 2018-11-02 23:51:37 +01:00
parent 0bf14082a4
commit 2527ba68e5
2 changed files with 19 additions and 12 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

6
spacy/_ml.py
View File

@ -532,7 +532,7 @@ def build_text_classifier(nr_class, width=64, **cfg):
vectors = trained_vectors
vectors_width = width
static_vectors = None
cnn_model = (
tok2vec = (
vectors
>> with_flatten(
LN(Maxout(width, vectors_width))
@ -540,6 +540,9 @@ def build_text_classifier(nr_class, width=64, **cfg):
(ExtractWindow(nW=1) >> LN(Maxout(width, width*3)))
) ** depth, pad=depth
)
)
cnn_model = (
tok2vec
>> flatten_add_lengths
>> ParametricAttention(width)
>> Pooling(sum_pool)
@ -556,6 +559,7 @@ def build_text_classifier(nr_class, width=64, **cfg):
>> zero_init(Affine(nr_class, nr_class*2, drop_factor=0.0))
>> logistic
)
model.tok2vec = tok2vec
model.nO = nr_class
model.lsuv = False
return model

19
spacy/pipeline.pyx
View File

@ -434,7 +434,7 @@ class Tensorizer(Pipe):
name = 'tensorizer'
@classmethod
def Model(cls, output_size=300, input_size=384, **cfg):
def Model(cls, output_size=300, input_size=128, **cfg):
"""Create a new statistical model for the class.
width (int): Output size of the model.
@ -442,11 +442,7 @@ class Tensorizer(Pipe):
**cfg: Config parameters.
RETURNS (Model): A `thinc.neural.Model` or similar instance.
"""
model = chain(
SELU(output_size, input_size),
SELU(output_size, output_size),
zero_init(Affine(output_size, output_size)))
return model
return zero_init(Affine(output_size, input_size))
def __init__(self, vocab, model=True, **cfg):
"""Construct a new statistical model. Weights are not allocated on
@ -562,12 +558,11 @@ class Tensorizer(Pipe):
gold_tuples (iterable): Gold-standard training data.
pipeline (list): The pipeline the model is part of.
"""
if pipeline is not None:
for name, model in pipeline:
if getattr(model, 'tok2vec', None):
self.input_models.append(model.tok2vec)
if self.model is True:
self.cfg['input_size'] = 384
self.cfg['output_size'] = 300
self.model = self.Model(**self.cfg)
link_vectors_to_models(self.vocab)
if sgd is None:
@ -1061,6 +1056,14 @@ class TextCategorizer(Pipe):
def Model(cls, nr_class, **cfg):
return build_text_classifier(nr_class, **cfg)
@property
def tok2vec(self):
if self.model in (None, True, False):
return None
else:
return chain(self.model.tok2vec, flatten)
def __init__(self, vocab, model=True, **cfg):
self.vocab = vocab
self.model = model