From 88755900818535527f2724d7286d2229a2e748d3 Mon Sep 17 00:00:00 2001
From: Matthew Honnibal <honnibal+gh@gmail.com>
Date: Sun, 20 Aug 2017 14:42:07 +0200
Subject: [PATCH] Add optimizer in Language.update if sgd=None

---
 spacy/language.py | 26 ++++++++++++++++----------
 1 file changed, 16 insertions(+), 10 deletions(-)

diff --git a/spacy/language.py b/spacy/language.py
index ed880d9ca..50ed0a166 100644
--- a/spacy/language.py
+++ b/spacy/language.py
@@ -200,6 +200,7 @@ class Language(object):
             else:
                 flat_list.append(pipe)
         self.pipeline = flat_list
+        self._optimizer = None
 
     @property
     def meta(self):
@@ -278,7 +279,7 @@ class Language(object):
         return self.tokenizer(text)
 
     def update(self, docs, golds, drop=0., sgd=None, losses=None,
-            update_tensors=False):
+            update_shared=False):
         """Update the models in the pipeline.
 
         docs (iterable): A batch of `Doc` objects.
@@ -298,6 +299,10 @@ class Language(object):
                 "Got: %d, %d" % (len(docs), len(golds)))
         if len(docs) == 0:
             return
+        if sgd is None:
+            if self._optimizer is None:
+                self._optimizer = Adam(Model.ops, 0.001)
+            sgd = self._optimizer
         tok2vec = self.pipeline[0]
         feats = tok2vec.doc2feats(docs)
         grads = {}
@@ -312,12 +317,13 @@ class Language(object):
                 continue
             d_tokvecses = proc.update((docs, tokvecses), golds,
                                       drop=drop, sgd=get_grads, losses=losses)
-            if update_tensors and d_tokvecses is not None:
+            if update_shared and d_tokvecses is not None:
                 for i, d_tv in enumerate(d_tokvecses):
                     all_d_tokvecses[i] += d_tv
-        bp_tokvecses(all_d_tokvecses, sgd=sgd)
-        for key, (W, dW) in grads.items():
-            sgd(W, dW, key=key)
+        if update_shared and bp_tokvecses is not None:
+            bp_tokvecses(all_d_tokvecses, sgd=sgd)
+            for key, (W, dW) in grads.items():
+                sgd(W, dW, key=key)
         # Clear the tensor variable, to free GPU memory.
         # If we don't do this, the memory leak gets pretty
         # bad, because we may be holding part of a batch.
@@ -378,11 +384,11 @@ class Language(object):
         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.)
-        optimizer = Adam(Model.ops, learn_rate, L2=L2, beta1=beta1,
-                         beta2=beta2, eps=eps)
-        optimizer.max_grad_norm = max_grad_norm
-        optimizer.device = device
-        return optimizer
+        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 evaluate(self, docs_golds):
         scorer = Scorer()