explosion/spaCy
1
1
Fork 0
mirror of https://github.com/explosion/spaCy.git synced 2024-11-11 04:08:09 +03:00
Code Issues Packages Projects Releases Wiki Activity

Remove unused resume_training method, and pass optimizer through

Browse Source
This commit is contained in:
Matthew Honnibal 2017-11-06 14:26:00 +01:00
parent 13336a6197
commit 465adfee94
1 changed files with 7 additions and 34 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

41
spacy/language.py
View File

@ -407,27 +407,7 @@ class Language(object):
for doc, gold in docs_golds: for doc, gold in docs_golds:
yield doc, gold yield doc, gold
def resume_training(self, **cfg): def begin_training(self, get_gold_tuples=None, sgd=None, **cfg):
if cfg.get('device', -1) >= 0:
device = util.use_gpu(cfg['device'])
if self.vocab.vectors.data.shape[1] >= 1:
self.vocab.vectors.data = Model.ops.asarray(
self.vocab.vectors.data)
else:
device = None
learn_rate = util.env_opt('learn_rate', 0.001)
beta1 = util.env_opt('optimizer_B1', 0.9)
beta2 = util.env_opt('optimizer_B2', 0.999)
eps = util.env_opt('optimizer_eps', 1e-08)
L2 = util.env_opt('L2_penalty', 1e-6)
max_grad_norm = util.env_opt('grad_norm_clip', 1.)
self._optimizer = Adam(Model.ops, learn_rate, L2=L2, beta1=beta1,
beta2=beta2, eps=eps)
self._optimizer.max_grad_norm = max_grad_norm
self._optimizer.device = device
return self._optimizer
def begin_training(self, get_gold_tuples=None, **cfg):
"""Allocate models, pre-process training data and acquire a trainer and """Allocate models, pre-process training data and acquire a trainer and
optimizer. Used as a contextmanager. optimizer. Used as a contextmanager.
@ -452,21 +432,14 @@ class Language(object):
else: else:
device = None device = None
link_vectors_to_models(self.vocab) link_vectors_to_models(self.vocab)
if sgd is None:
sgd = create_default_optimizer(Model.ops)
self._optimizer = sgd
for name, proc in self.pipeline: for name, proc in self.pipeline:
if hasattr(proc, 'begin_training'): if hasattr(proc, 'begin_training'):
context = proc.begin_training(get_gold_tuples(), proc.begin_training(get_gold_tuples(),
pipeline=self.pipeline) pipeline=self.pipeline,
contexts.append(context) sgd=self._optimizer)
learn_rate = util.env_opt('learn_rate', 0.001)
beta1 = util.env_opt('optimizer_B1', 0.9)
beta2 = util.env_opt('optimizer_B2', 0.999)
eps = util.env_opt('optimizer_eps', 1e-08)
L2 = util.env_opt('L2_penalty', 1e-6)
max_grad_norm = util.env_opt('grad_norm_clip', 1.)
self._optimizer = Adam(Model.ops, learn_rate, L2=L2, beta1=beta1,
beta2=beta2, eps=eps)
self._optimizer.max_grad_norm = max_grad_norm
self._optimizer.device = device
return self._optimizer return self._optimizer
def evaluate(self, docs_golds, verbose=False): def evaluate(self, docs_golds, verbose=False):