Add link_vectors_to_models function

spacy/_ml.py

@@ -4,6 +4,7 @@ from thinc.neural import Model, Maxout, Softmax, Affine
 from thinc.neural._classes.hash_embed import HashEmbed
 from thinc.neural.ops import NumpyOps, CupyOps
 from thinc.neural.util import get_array_module
+import thinc.extra.load_nlp
 import random
 import cytoolz
 
@@ -31,6 +32,7 @@ from . import util
 import numpy
 import io
 
+VECTORS_KEY = 'spacy_pretrained_vectors'
 
 @layerize
 def _flatten_add_lengths(seqs, pad=0, drop=0.):

spacy/pipeline.pyx

@@ -43,6 +43,7 @@ from .compat import json_dumps
 from .attrs import ID, LOWER, PREFIX, SUFFIX, SHAPE, TAG, DEP, POS
 from ._ml import rebatch, Tok2Vec, flatten
 from ._ml import build_text_classifier, build_tagger_model
+from ._ml import link_vectors_to_models
 from .parts_of_speech import X
 
 
@@ -121,6 +122,7 @@ class BaseThincComponent(object):
         token_vector_width = pipeline[0].model.nO
         if self.model is True:
             self.model = self.Model(1, token_vector_width)
+            link_vectors_to_models(self.vocab)
 
     def use_params(self, params):
         with self.model.use_params(params):
@@ -215,7 +217,7 @@ class TokenVectorEncoder(BaseThincComponent):
         self.model = model
         self.cfg = dict(cfg)
         self.cfg['pretrained_dims'] = self.vocab.vectors.data.shape[1]
-        self.cfg.setdefault('cnn_maxout_pieces', 2)
+        self.cfg.setdefault('cnn_maxout_pieces', 3)
 
     def __call__(self, doc):
         """Add context-sensitive vectors to a `Doc`, e.g. from a CNN or LSTM
@@ -288,6 +290,7 @@ class TokenVectorEncoder(BaseThincComponent):
         """
         if self.model is True:
             self.model = self.Model(**self.cfg)
+            link_vectors_to_models(self.vocab)
 
 
 class NeuralTagger(BaseThincComponent):
@@ -396,6 +399,7 @@ class NeuralTagger(BaseThincComponent):
                                           exc=vocab.morphology.exc)
         if self.model is True:
             self.model = self.Model(self.vocab.morphology.n_tags, **self.cfg)
+            link_vectors_to_models(self.vocab)
 
     @classmethod
     def Model(cls, n_tags, **cfg):
@@ -504,8 +508,9 @@ class NeuralLabeller(NeuralTagger):
                         self.labels[dep] = len(self.labels)
         token_vector_width = pipeline[0].model.nO
         if self.model is True:
-            self.model = self.Model(len(self.labels), token_vector_width,
+            self.model = self.Model(len(self.labels), token_vector_width=token_vector_width,
                                     pretrained_dims=self.vocab.vectors_length)
+            link_vectors_to_models(self.vocab)
 
     @classmethod
     def Model(cls, n_tags, **cfg):
@@ -585,6 +590,7 @@ class SimilarityHook(BaseThincComponent):
         """
         if self.model is True:
             self.model = self.Model(pipeline[0].model.nO)
+            link_vectors_to_models(self.vocab)
 
 
 class TextCategorizer(BaseThincComponent):
@@ -658,6 +664,7 @@ class TextCategorizer(BaseThincComponent):
             self.cfg['pretrained_dims'] = self.vocab.vectors_length
             self.model = self.Model(len(self.labels), token_vector_width,
                                     **self.cfg)
+            link_vectors_to_models(self.vocab)
 
 
 cdef class EntityRecognizer(LinearParser):

spacy/syntax/nn_parser.pyx

@@ -49,6 +49,7 @@ from ..util import get_async, get_cuda_stream
 from .._ml import zero_init, PrecomputableAffine, PrecomputableMaxouts
 from .._ml import Tok2Vec, doc2feats, rebatch, fine_tune
 from .._ml import Residual, drop_layer
+from .._ml import link_vectors_to_models
 from ..compat import json_dumps
 
 from . import _parse_features
@@ -309,7 +310,7 @@ cdef class Parser:
             cfg['beam_density'] = util.env_opt('beam_density', 0.0)
         if 'pretrained_dims' not in cfg:
             cfg['pretrained_dims'] = self.vocab.vectors.data.shape[1]
-        cfg.setdefault('cnn_maxout_pieces', 2)
+        cfg.setdefault('cnn_maxout_pieces', 3)
         self.cfg = cfg
         if 'actions' in self.cfg:
             for action, labels in self.cfg.get('actions', {}).items():
@@ -791,6 +792,7 @@ cdef class Parser:
         if self.model is True:
             cfg['pretrained_dims'] = self.vocab.vectors_length
             self.model, cfg = self.Model(self.moves.n_moves, **cfg)
+            link_vectors_to_models(self.vocab)
             self.cfg.update(cfg)
 
     def preprocess_gold(self, docs_golds):
@@ -872,8 +874,7 @@ cdef class Parser:
         msg = util.from_bytes(bytes_data, deserializers, exclude)
         if 'model' not in exclude:
             if self.model is True:
-                self.model, cfg = self.Model(self.moves.n_moves,
-                                    pretrained_dims=self.vocab.vectors_length)
+                self.model, cfg = self.Model(**self.cfg)
                 cfg['pretrained_dims'] = self.vocab.vectors_length
             else:
                 cfg = {}

spacy/vocab.pyx

@@ -27,6 +27,7 @@ from .vectors import Vectors
 from . import util
 from . import attrs
 from . import symbols
+from ._ml import link_vectors_to_models
 
 
 cdef class Vocab:
@@ -323,6 +324,7 @@ cdef class Vocab:
             self.lexemes_from_bytes(file_.read())
         if self.vectors is not None:
             self.vectors.from_disk(path, exclude='strings.json')
+        link_vectors_to_models(self)
         return self
 
     def to_bytes(self, **exclude):
@@ -362,6 +364,7 @@ cdef class Vocab:
             ('vectors', lambda b: serialize_vectors(b))
         ))
         util.from_bytes(bytes_data, setters, exclude)
+        link_vectors_to_models(self)
         return self
 
     def lexemes_to_bytes(self):
@@ -436,6 +439,7 @@ def unpickle_vocab(sstore, morphology, data_dir,
     vocab.lex_attr_getters = lex_attr_getters
     vocab.lexemes_from_bytes(lexemes_data)
     vocab.length = length
+    link_vectors_to_models(vocab)
     return vocab