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

Restore tok2vec function

This commit is contained in:
Matthew Honnibal 2017-05-05 20:12:03 +02:00
parent efe9630e1c
commit fa7c1990b6
1 changed files with 18 additions and 18 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

36
spacy/_ml.py
View File

@ -1,7 +1,11 @@
from thinc.api import layerize, chain, clone from thinc.api import layerize, chain, clone, concatenate
from thinc.neural import Model, Maxout, Softmax from thinc.neural import Model, Maxout, Softmax
from thinc.neural._classes.hash_embed import HashEmbed from thinc.neural._classes.hash_embed import HashEmbed
from .attrs import TAG, DEP
from thinc.neural._classes.convolution import ExtractWindow
from thinc.neural._classes.static_vectors import StaticVectors
from .attrs import ID, PREFIX, SUFFIX, SHAPE, TAG, DEP
def get_col(idx): def get_col(idx):
@ -79,19 +83,15 @@ def _reshape(layer):
model._layers.append(layer) model._layers.append(layer)
return model return model
#from thinc.api import layerize, chain, clone, concatenate, add def build_tok2vec(lang, width, depth, embed_size, cols):
# from thinc.neural._classes.convolution import ExtractWindow with Model.define_operators({'>>': chain, '|': concatenate, '**': clone}):
# from thinc.neural._classes.static_vectors import StaticVectors static = get_col(cols.index(ID)) >> StaticVectors(lang, width)
prefix = get_col(cols.index(PREFIX)) >> HashEmbed(width, embed_size)
#def build_tok2vec(lang, width, depth, embed_size, cols): suffix = get_col(cols.index(SUFFIX)) >> HashEmbed(width, embed_size)
# with Model.define_operators({'>>': chain, '|': concatenate, '**': clone}): shape = get_col(cols.index(SHAPE)) >> HashEmbed(width, embed_size)
# static = get_col(cols.index(ID)) >> StaticVectors(lang, width) tok2vec = (
# prefix = get_col(cols.index(PREFIX)) >> HashEmbed(width, embed_size) (static | prefix | suffix | shape)
# suffix = get_col(cols.index(SUFFIX)) >> HashEmbed(width, embed_size) >> Maxout(width, width*4)
# shape = get_col(cols.index(SHAPE)) >> HashEmbed(width, embed_size) >> (ExtractWindow(nW=1) >> Maxout(width, width*3)) ** depth
# tok2vec = ( )
# (static | prefix | suffix | shape) return tok2vec
# >> Maxout(width, width*4)
# >> (ExtractWindow(nW=1) >> Maxout(width, width*3)) ** depth
# )
# return tok2vec