explosion/spaCy
1
1
Fork 0
mirror of https://github.com/explosion/spaCy.git synced 2024-12-24 17:06:29 +03:00
Code Issues Packages Projects Releases Wiki Activity

Specify seeds in HashEmbed

Browse Source
This commit is contained in:
Matthw Honnibal 2020-07-04 23:51:49 +02:00
parent 2bd1bf81f1
commit 8870a6ded7
1 changed files with 8 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

12
spacy/ml/models/tok2vec.py
View File

@ -263,17 +263,21 @@ def build_Tok2Vec_model(
cols = [ID, NORM, PREFIX, SUFFIX, SHAPE, ORTH]
with Model.define_operators({">>": chain, "|": concatenate, "**": clone}):
norm = HashEmbed(
nO=width, nV=embed_size, column=cols.index(NORM), dropout=dropout
nO=width, nV=embed_size, column=cols.index(NORM), dropout=dropout,
seed=0
)
if subword_features:
prefix = HashEmbed(
nO=width, nV=embed_size // 2, column=cols.index(PREFIX), dropout=dropout
nO=width, nV=embed_size // 2, column=cols.index(PREFIX), dropout=dropout,
seed=1
)
suffix = HashEmbed(
nO=width, nV=embed_size // 2, column=cols.index(SUFFIX), dropout=dropout
nO=width, nV=embed_size // 2, column=cols.index(SUFFIX), dropout=dropout,
seed=2
)
shape = HashEmbed(
nO=width, nV=embed_size // 2, column=cols.index(SHAPE), dropout=dropout
nO=width, nV=embed_size // 2, column=cols.index(SHAPE), dropout=dropout,
seed=3
)
else:
prefix, suffix, shape = (None, None, None)