diff --git a/spacy/cli/train.py b/spacy/cli/train.py
index 35ce4c43b..05d035769 100644
--- a/spacy/cli/train.py
+++ b/spacy/cli/train.py
@@ -114,10 +114,7 @@ def train(cmd, lang, output_dir, train_data, dev_data, n_iter=10, n_sents=0,
                 util.set_env_log(False)
                 epoch_model_path = output_path / ('model%d' % i)
                 nlp.to_disk(epoch_model_path)
-                nlp_loaded = lang_class(pipeline=pipeline)
-                for name in pipeline:
-                    nlp_loaded.add_pipe(nlp.create_pipe(name), name=name)
-                nlp_loaded = nlp_loaded.from_disk(epoch_model_path)
+                nlp_loaded = util.load_model_from_path(epoch_model_path)
                 dev_docs = list(corpus.dev_docs(
                                 nlp_loaded,
                                 gold_preproc=gold_preproc))
@@ -131,11 +128,7 @@ def train(cmd, lang, output_dir, train_data, dev_data, n_iter=10, n_sents=0,
                 else:
                     gpu_wps = nwords/(end_time-start_time)
                     with Model.use_device('cpu'):
-                        nlp_loaded = lang_class(pipeline=pipeline)
-                        for name in pipeline:
-                            nlp_loaded.add_pipe(nlp.create_pipe(name), name=name)
-
-                        nlp_loaded = nlp_loaded.from_disk(epoch_model_path)
+                        nlp_loaded = util.load_model_from_path(epoch_model_path)
                         dev_docs = list(corpus.dev_docs(
                                         nlp_loaded, gold_preproc=gold_preproc))
                         start_time = timer()
diff --git a/spacy/syntax/nn_parser.pyx b/spacy/syntax/nn_parser.pyx
index a8a1d4334..939414bd3 100644
--- a/spacy/syntax/nn_parser.pyx
+++ b/spacy/syntax/nn_parser.pyx
@@ -800,11 +800,20 @@ cdef class Parser:
         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
+            if self.model[-1].is_noop:
+                smaller = self.model[1]
+                dims = dict(self.model[1]._dims)
+                dims['nO'] = self.moves.n_moves
+                larger = self.model[1].__class__(**dims)
+                copy_array(larger.W[:, :smaller.nO], smaller.W)
+                copy_array(larger.b[:smaller.nO], smaller.b)
+                self.model = (self.model[0], larger, self.model[2])
+            else:
+                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):
         if 'model' in cfg:
diff --git a/spacy/tests/parser/test_add_label.py b/spacy/tests/parser/test_add_label.py
index b89cca113..3fbfc96a6 100644
--- a/spacy/tests/parser/test_add_label.py
+++ b/spacy/tests/parser/test_add_label.py
@@ -22,14 +22,14 @@ def vocab():
 @pytest.fixture
 def parser(vocab):
     parser = NeuralDependencyParser(vocab)
-    parser.cfg['token_vector_width'] = 4
-    parser.cfg['hidden_width'] = 6
+    parser.cfg['token_vector_width'] = 8
+    parser.cfg['hidden_width'] = 30
     parser.cfg['hist_size'] = 0
     parser.add_label('left')
     parser.begin_training([], **parser.cfg)
     sgd = Adam(NumpyOps(), 0.001)
 
-    for i in range(30):
+    for i in range(10):
         losses = {}
         doc = Doc(vocab, words=['a', 'b', 'c', 'd'])
         gold = GoldParse(doc, heads=[1, 1, 3, 3],
@@ -37,6 +37,8 @@ def parser(vocab):
         parser.update([doc], [gold], sgd=sgd, losses=losses)
     return parser
 
+def test_init_parser(parser):
+    pass
 
 def test_add_label(parser):
     doc = Doc(parser.vocab, words=['a', 'b', 'c', 'd'])