Rooba
/
spaCy
mirror of https://github.com/explosion/spaCy.git
1
1
Fork 0
Code Issues Packages Projects Releases Wiki Activity

Improve tensorizer model

This commit is contained in:
Matthew Honnibal 2017-08-16 18:25:20 -05:00
parent a6d8d7c82e
commit 4b1e7bd6d8
1 changed files with 4 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

7
spacy/_ml.py
View File

@ -9,7 +9,7 @@ import cytoolz
from thinc.neural._classes.convolution import ExtractWindow from thinc.neural._classes.convolution import ExtractWindow
from thinc.neural._classes.static_vectors import StaticVectors from thinc.neural._classes.static_vectors import StaticVectors
from thinc.neural._classes.batchnorm import BatchNorm from thinc.neural._classes.batchnorm import BatchNorm as BN
from thinc.neural._classes.layernorm import LayerNorm as LN from thinc.neural._classes.layernorm import LayerNorm as LN
from thinc.neural._classes.resnet import Residual from thinc.neural._classes.resnet import Residual
from thinc.neural import ReLu from thinc.neural import ReLu
@ -22,6 +22,7 @@ from thinc.neural.pooling import Pooling, max_pool, mean_pool, sum_pool
from thinc.neural._classes.attention import ParametricAttention from thinc.neural._classes.attention import ParametricAttention
from thinc.linear.linear import LinearModel from thinc.linear.linear import LinearModel
from thinc.api import uniqued, wrap, flatten_add_lengths from thinc.api import uniqued, wrap, flatten_add_lengths
from thinc.neural._classes.rnn import BiLSTM
from .attrs import ID, ORTH, LOWER, NORM, PREFIX, SUFFIX, SHAPE, TAG, DEP from .attrs import ID, ORTH, LOWER, NORM, PREFIX, SUFFIX, SHAPE, TAG, DEP
@ -229,14 +230,14 @@ def Tok2Vec(width, embed_size, preprocess=None):
suffix = get_col(cols.index(SUFFIX)) >> HashEmbed(width, embed_size//2, name='embed_suffix') suffix = get_col(cols.index(SUFFIX)) >> HashEmbed(width, embed_size//2, name='embed_suffix')
shape = get_col(cols.index(SHAPE)) >> HashEmbed(width, embed_size//2, name='embed_shape') shape = get_col(cols.index(SHAPE)) >> HashEmbed(width, embed_size//2, name='embed_shape')
embed = (norm | prefix | suffix | shape ) >> Maxout(width, width*4, pieces=3) embed = (norm | prefix | suffix | shape ) >> LN(Maxout(width, width*4, pieces=3))
tok2vec = ( tok2vec = (
with_flatten( with_flatten(
asarray(Model.ops, dtype='uint64') asarray(Model.ops, dtype='uint64')
>> uniqued(embed, column=5) >> uniqued(embed, column=5)
>> drop_layer( >> drop_layer(
Residual( Residual(
(ExtractWindow(nW=1) >> ReLu(width, width*3)) (ExtractWindow(nW=1) >> BN(Maxout(width, width*3)))
) )
) ** 4, pad=4 ) ** 4, pad=4
) )