explosion/spaCy
1
1
Fork 0
mirror of https://github.com/explosion/spaCy.git synced 2025-01-13 10:46:29 +03:00
Code Issues Packages Projects Releases Wiki Activity

Allow parser.add_label for pretrained models

Browse Source
This commit is contained in:
Matthew Honnibal 2017-10-09 03:35:40 +02:00
parent be4f0b6460
commit d43a83e37a
1 changed files with 11 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

12
spacy/syntax/nn_parser.pyx
View File

@ -51,7 +51,7 @@ from .._ml import Tok2Vec, doc2feats, rebatch, fine_tune
from .._ml import Residual, drop_layer, flatten from .._ml import Residual, drop_layer, flatten
from .._ml import link_vectors_to_models from .._ml import link_vectors_to_models
from .._ml import HistoryFeatures from .._ml import HistoryFeatures
from ..compat import json_dumps from ..compat import json_dumps, copy_array
from . import _parse_features from . import _parse_features
from ._parse_features cimport CONTEXT_SIZE from ._parse_features cimport CONTEXT_SIZE
@ -781,12 +781,22 @@ cdef class Parser:
self.moves.finalize_doc(doc) self.moves.finalize_doc(doc)
def add_label(self, label): def add_label(self, label):
resized = False
for action in self.moves.action_types: for action in self.moves.action_types:
added = self.moves.add_action(action, label) added = self.moves.add_action(action, label)
if added: if added:
# Important that the labels be stored as a list! We need the # Important that the labels be stored as a list! We need the
# order, or the model goes out of synch # order, or the model goes out of synch
self.cfg.setdefault('extra_labels', []).append(label) self.cfg.setdefault('extra_labels', []).append(label)
resized = True
if self.model not in (True, False, None) and resized:
# Weights are stored in (nr_out, nr_in) format, so we're basically
# just adding rows here.
smaller = self.model[-1]._layers[-1]
larger = Affine(self.moves.n_moves, smaller.nI)
copy_array(larger.W[:smaller.nO], smaller.W)
copy_array(larger.b[:smaller.nO], smaller.b)
self.model[-1]._layers[-1] = larger
def begin_training(self, gold_tuples, pipeline=None, **cfg): def begin_training(self, gold_tuples, pipeline=None, **cfg):
if 'model' in cfg: if 'model' in cfg: