diff --git a/fluid/ocr_recognition/crnn_ctc_model.py b/fluid/ocr_recognition/crnn_ctc_model.py
index 719c0158ec0e28c46a2915e42bd81533f848673c..73616ecb36ca2661eb8e4898caf34fc2d91b9bdc 100644
--- a/fluid/ocr_recognition/crnn_ctc_model.py
+++ b/fluid/ocr_recognition/crnn_ctc_model.py
@@ -26,7 +26,12 @@ def conv_bn_pool(input,
             bias_attr=bias,
             is_test=is_test)
     tmp = fluid.layers.pool2d(
-        input=tmp, pool_size=2, pool_type='max', pool_stride=2, use_cudnn=True)
+        input=tmp,
+        pool_size=2,
+        pool_type='max',
+        pool_stride=2,
+        use_cudnn=True,
+        ceil_mode=True)
 
     return tmp
 
@@ -136,26 +141,61 @@ def encoder_net(images,
 def ctc_train_net(images, label, args, num_classes):
     regularizer = fluid.regularizer.L2Decay(args.l2)
     gradient_clip = None
-    fc_out = encoder_net(
-        images,
-        num_classes,
-        regularizer=regularizer,
-        gradient_clip=gradient_clip)
+    if args.parallel:
+        places = fluid.layers.get_places()
+        pd = fluid.layers.ParallelDo(places)
+        with pd.do():
+            images_ = pd.read_input(images)
+            label_ = pd.read_input(label)
+
+            fc_out = encoder_net(
+                images_,
+                num_classes,
+                regularizer=regularizer,
+                gradient_clip=gradient_clip)
+
+            cost = fluid.layers.warpctc(
+                input=fc_out,
+                label=label_,
+                blank=num_classes,
+                norm_by_times=True)
+            sum_cost = fluid.layers.reduce_sum(cost)
+
+            decoded_out = fluid.layers.ctc_greedy_decoder(
+                input=fc_out, blank=num_classes)
+
+            pd.write_output(sum_cost)
+            pd.write_output(decoded_out)
+
+        sum_cost, decoded_out = pd()
+        sum_cost = fluid.layers.reduce_sum(sum_cost)
+
+    else:
+        fc_out = encoder_net(
+            images,
+            num_classes,
+            regularizer=regularizer,
+            gradient_clip=gradient_clip)
+
+        cost = fluid.layers.warpctc(
+            input=fc_out, label=label, blank=num_classes, norm_by_times=True)
+        sum_cost = fluid.layers.reduce_sum(cost)
+        decoded_out = fluid.layers.ctc_greedy_decoder(
+            input=fc_out, blank=num_classes)
 
-    cost = fluid.layers.warpctc(
-        input=fc_out, label=label, blank=num_classes, norm_by_times=True)
-    sum_cost = fluid.layers.reduce_sum(cost)
+    casted_label = fluid.layers.cast(x=label, dtype='int64')
+    error_evaluator = fluid.evaluator.EditDistance(
+        input=decoded_out, label=casted_label)
+
+    inference_program = fluid.default_main_program().clone()
+    with fluid.program_guard(inference_program):
+        inference_program = fluid.io.get_inference_program(error_evaluator)
 
     optimizer = fluid.optimizer.Momentum(
         learning_rate=args.learning_rate, momentum=args.momentum)
-    optimizer.minimize(sum_cost)
+    _, params_grads = optimizer.minimize(sum_cost)
 
-    decoded_out = fluid.layers.ctc_greedy_decoder(
-        input=fc_out, blank=num_classes)
-    casted_label = fluid.layers.cast(x=label, dtype='int64')
-    error_evaluator = fluid.evaluator.EditDistance(
-        input=decoded_out, label=casted_label)
-    return sum_cost, error_evaluator
+    return sum_cost, error_evaluator, inference_program
 
 
 def ctc_infer(images, num_classes):
diff --git a/fluid/ocr_recognition/ctc_train.py b/fluid/ocr_recognition/ctc_train.py
index 85b1d2e708f73d7ac049af276626a38e76d19399..c2d8fd26bbdeb3ad5c9fb2c1ade3b2b22a0dfd44 100644
--- a/fluid/ocr_recognition/ctc_train.py
+++ b/fluid/ocr_recognition/ctc_train.py
@@ -1,5 +1,4 @@
 """Trainer for OCR CTC model."""
-import paddle.v2 as paddle
 import paddle.fluid as fluid
 import dummy_reader
 import ctc_reader
@@ -24,12 +23,12 @@ add_arg('momentum',       float, 0.9,    "Momentum.")
 add_arg('rnn_hidden_size',int,   200,    "Hidden size of rnn layers.")
 add_arg('device',         int,   0,      "Device id.'-1' means running on CPU"
                                          "while '0' means GPU-0.")
+add_arg('parallel',     bool,   True,     "Whether use parallel training.")
 # yapf: disable
 
 def load_parameter(place):
     params = load_param('./name.map', './data/model/results_without_avg_window/pass-00000/')
     for name in params:
-        #        print "param: %s" % name
         t = fluid.global_scope().find_var(name).get_tensor()
         t.set(params[name], place)
 
@@ -41,7 +40,8 @@ def train(args, data_reader=dummy_reader):
     # define network
     images = fluid.layers.data(name='pixel', shape=data_shape, dtype='float32')
     label = fluid.layers.data(name='label', shape=[1], dtype='int32', lod_level=1)
-    sum_cost, error_evaluator = ctc_train_net(images, label, args, num_classes)
+    sum_cost, error_evaluator, inference_program = ctc_train_net(images, label, args, num_classes)
+
     # data reader
     train_reader = data_reader.train(args.batch_size)
     test_reader = data_reader.test()
@@ -51,11 +51,8 @@ def train(args, data_reader=dummy_reader):
         place = fluid.CUDAPlace(args.device)
     exe = fluid.Executor(place)
     exe.run(fluid.default_startup_program())
-
     #load_parameter(place)
 
-    inference_program = fluid.io.get_inference_program(error_evaluator)
-
     for pass_id in range(args.pass_num):
         error_evaluator.reset(exe)
         batch_id = 1
@@ -78,7 +75,6 @@ def train(args, data_reader=dummy_reader):
                 sys.stdout.flush()
             batch_id += 1
 
-        # evaluate model on test data
         error_evaluator.reset(exe)
         for data in test_reader():
             exe.run(inference_program, feed=get_feeder_data(data, place))