diff --git a/CMakeLists.txt b/CMakeLists.txt
index 231224f9249848b6e4981a98e0538794bf5d3c08..f180b5cfa6dc73b46eff5b6fc331fa5bf8395d6f 100644
--- a/CMakeLists.txt
+++ b/CMakeLists.txt
@@ -72,6 +72,7 @@ option(PY_VERSION       "Compile PaddlePaddle with python3 support"     ${PY_VER
 if(NOT PY_VERSION)
   set(PY_VERSION 2.7)
 endif()
+set(PYBIND11_PYTHON_VERSION ${PY_VERSION})
 
 # CMAKE_BUILD_TYPE
 if(NOT CMAKE_BUILD_TYPE)
diff --git a/python/paddle/fluid/optimizer.py b/python/paddle/fluid/optimizer.py
index a3c32cfea67bdbb6a29cdc40503fbfc8af426068..a07325f46a2892222c2d1dcd74aa7cb01f6760a1 100644
--- a/python/paddle/fluid/optimizer.py
+++ b/python/paddle/fluid/optimizer.py
@@ -106,7 +106,7 @@ class Optimizer(object):
         param_lr = param.optimize_attr['learning_rate']
         if type(param_lr) == Variable:
             # param learning rate has been updated (LARS)
-            print(("returns updated param lr ", param_lr))
+            print("returns updated param lr ", param_lr)
             return param_lr
         else:
             if param_lr == 1.0:
diff --git a/python/paddle/fluid/tests/book/high-level-api/fit_a_line/test_fit_a_line.py b/python/paddle/fluid/tests/book/high-level-api/fit_a_line/test_fit_a_line.py
index a27e6c45f68998a4ceb607f11967d82e238b866b..36a1a223cfd7c69aff3e8648da990d23e4e75202 100644
--- a/python/paddle/fluid/tests/book/high-level-api/fit_a_line/test_fit_a_line.py
+++ b/python/paddle/fluid/tests/book/high-level-api/fit_a_line/test_fit_a_line.py
@@ -94,7 +94,7 @@ def infer(use_cuda, inference_program, params_dirname=None):
     tensor_x = numpy.random.uniform(0, 10, [batch_size, 13]).astype("float32")
 
     results = inferencer.infer({'x': tensor_x})
-    print(("infer results: ", results[0]))
+    print("infer results: ", results[0])
 
 
 def main(use_cuda):
diff --git a/python/paddle/fluid/tests/book/high-level-api/image_classification/test_image_classification_resnet.py b/python/paddle/fluid/tests/book/high-level-api/image_classification/test_image_classification_resnet.py
index 8f38d53ea1ba69a90dfe502604f2937b2fb161b6..a1f62db093904b617f0e37dc20d586ccea7eacd2 100644
--- a/python/paddle/fluid/tests/book/high-level-api/image_classification/test_image_classification_resnet.py
+++ b/python/paddle/fluid/tests/book/high-level-api/image_classification/test_image_classification_resnet.py
@@ -105,7 +105,7 @@ def train(use_cuda, train_program, params_dirname):
             avg_cost, accuracy = trainer.test(
                 reader=test_reader, feed_order=['pixel', 'label'])
 
-            print(('Loss {0:2.2}, Acc {1:2.2}'.format(avg_cost, accuracy)))
+            print('Loss {0:2.2}, Acc {1:2.2}'.format(avg_cost, accuracy))
 
             if accuracy > 0.01:  # Low threshold for speeding up CI
                 if params_dirname is not None:
@@ -134,7 +134,7 @@ def infer(use_cuda, inference_program, params_dirname=None):
     tensor_img = numpy.random.rand(1, 3, 32, 32).astype("float32")
     results = inferencer.infer({'pixel': tensor_img})
 
-    print(("infer results: ", results))
+    print("infer results: ", results)
 
 
 def main(use_cuda):
diff --git a/python/paddle/fluid/tests/book/high-level-api/image_classification/test_image_classification_vgg.py b/python/paddle/fluid/tests/book/high-level-api/image_classification/test_image_classification_vgg.py
index f37d3e6d6d123f1671bc6a9c05cca927271ebc3a..8429551765740e7db0eda82ce0b17cff129359b0 100644
--- a/python/paddle/fluid/tests/book/high-level-api/image_classification/test_image_classification_vgg.py
+++ b/python/paddle/fluid/tests/book/high-level-api/image_classification/test_image_classification_vgg.py
@@ -82,7 +82,7 @@ def train(use_cuda, train_program, params_dirname):
             avg_cost, accuracy = trainer.test(
                 reader=test_reader, feed_order=['pixel', 'label'])
 
-            print(('Loss {0:2.2}, Acc {1:2.2}'.format(avg_cost, accuracy)))
+            print('Loss {0:2.2}, Acc {1:2.2}'.format(avg_cost, accuracy))
 
             if accuracy > 0.01:  # Low threshold for speeding up CI
                 if params_dirname is not None:
@@ -111,7 +111,7 @@ def infer(use_cuda, inference_program, params_dirname=None):
     tensor_img = numpy.random.rand(1, 3, 32, 32).astype("float32")
     results = inferencer.infer({'pixel': tensor_img})
 
-    print(("infer results: ", results))
+    print("infer results: ", results)
 
 
 def main(use_cuda):
diff --git a/python/paddle/fluid/tests/book/high-level-api/label_semantic_roles/test_label_semantic_roles_newapi.py b/python/paddle/fluid/tests/book/high-level-api/label_semantic_roles/test_label_semantic_roles_newapi.py
index 6e177478e81442244a37309351a30e6ac6e6328d..e3602e2d5643c233b2575d1adb7f181127f60287 100755
--- a/python/paddle/fluid/tests/book/high-level-api/label_semantic_roles/test_label_semantic_roles_newapi.py
+++ b/python/paddle/fluid/tests/book/high-level-api/label_semantic_roles/test_label_semantic_roles_newapi.py
@@ -171,7 +171,7 @@ def train(use_cuda, train_program, params_dirname):
             # get avg cost
             avg_cost = np.array(avg_cost_set).mean()
 
-            print(("avg_cost: %s" % avg_cost))
+            print("avg_cost: %s" % avg_cost)
 
             if float(avg_cost) < 100.0:  # Large value to increase CI speed
                 trainer.save_params(params_dirname)
@@ -183,8 +183,8 @@ def train(use_cuda, train_program, params_dirname):
                     sys.exit("got NaN loss, training failed.")
 
         elif isinstance(event, fluid.EndStepEvent):
-            print(("Step {0}, Epoch {1} Metrics {2}".format(
-                event.step, event.epoch, list(map(np.array, event.metrics)))))
+            print("Step {0}, Epoch {1} Metrics {2}".format(
+                event.step, event.epoch, list(map(np.array, event.metrics))))
             if event.step == 1:  # Run 2 iterations to speed CI
                 trainer.save_params(params_dirname)
                 trainer.stop()
@@ -206,14 +206,14 @@ def infer(use_cuda, inference_program, params_dirname):
         inference_program, param_path=params_dirname, place=place)
 
     # Setup input by creating LoDTensor to represent sequence of words.
-    # Here each word is the basic element of the LoDTensor and the shape of 
-    # each word (base_shape) should be [1] since it is simply an index to 
+    # Here each word is the basic element of the LoDTensor and the shape of
+    # each word (base_shape) should be [1] since it is simply an index to
     # look up for the corresponding word vector.
     # Suppose the recursive_sequence_lengths info is set to [[3, 4, 2]],
-    # which has only one level of detail. Then the created LoDTensor will have only 
-    # one higher level structure (sequence of words, or sentence) than the basic 
-    # element (word). Hence the LoDTensor will hold data for three sentences of 
-    # length 3, 4 and 2, respectively. 
+    # which has only one level of detail. Then the created LoDTensor will have only
+    # one higher level structure (sequence of words, or sentence) than the basic
+    # element (word). Hence the LoDTensor will hold data for three sentences of
+    # length 3, 4 and 2, respectively.
     # Note that recursive_sequence_lengths should be a list of lists.
     recursive_seq_lens = [[3, 4, 2]]
     base_shape = [1]
@@ -248,7 +248,7 @@ def infer(use_cuda, inference_program, params_dirname):
         },
         return_numpy=False)
 
-    print(("infer results: ", np.array(results[0]).shape))
+    print("infer results: ", np.array(results[0]).shape)
 
 
 def main(use_cuda):
diff --git a/python/paddle/fluid/tests/book/high-level-api/machine_translation/test_machine_translation.py b/python/paddle/fluid/tests/book/high-level-api/machine_translation/test_machine_translation.py
index c8dbea4807de920220631ae817566d40cd03c8ff..6fb0c85a8be2b4560ea1fdb32f01146a9206ee78 100644
--- a/python/paddle/fluid/tests/book/high-level-api/machine_translation/test_machine_translation.py
+++ b/python/paddle/fluid/tests/book/high-level-api/machine_translation/test_machine_translation.py
@@ -197,7 +197,7 @@ def train(use_cuda, is_sparse, is_local=True):
 
     def event_handler(event):
         if isinstance(event, fluid.EndStepEvent):
-            print(('pass_id=' + str(event.epoch) + ' batch=' + str(event.step)))
+            print('pass_id=' + str(event.epoch) + ' batch=' + str(event.step))
             if event.step == 10:
                 trainer.stop()
 
@@ -259,7 +259,7 @@ def decode_main(use_cuda, is_sparse):
             feed=feed_dict,
             fetch_list=[translation_ids, translation_scores],
             return_numpy=False)
-        print((result_ids.recursive_sequence_lengths()))
+        print(result_ids.recursive_sequence_lengths())
         break
 
 
diff --git a/python/paddle/fluid/tests/book/high-level-api/recognize_digits/test_recognize_digits_conv.py b/python/paddle/fluid/tests/book/high-level-api/recognize_digits/test_recognize_digits_conv.py
index 2ade9a4bc615efcf7a921b193b2fe56b7ce87ad0..898807db6f343cbefcc877e0f03ed6c5b82dd669 100644
--- a/python/paddle/fluid/tests/book/high-level-api/recognize_digits/test_recognize_digits_conv.py
+++ b/python/paddle/fluid/tests/book/high-level-api/recognize_digits/test_recognize_digits_conv.py
@@ -78,14 +78,14 @@ def train(use_cuda, train_program, params_dirname):
             avg_cost, acc = trainer.test(
                 reader=test_reader, feed_order=['img', 'label'])
 
-            print(("avg_cost: %s" % avg_cost))
-            print(("acc     : %s" % acc))
+            print("avg_cost: %s" % avg_cost)
+            print("acc     : %s" % acc)
 
             if acc > 0.2:  # Smaller value to increase CI speed
                 trainer.save_params(params_dirname)
             else:
-                print(('BatchID {0}, Test Loss {1:0.2}, Acc {2:0.2}'.format(
-                    event.epoch + 1, avg_cost, acc)))
+                print('BatchID {0}, Test Loss {1:0.2}, Acc {2:0.2}'.format(
+                    event.epoch + 1, avg_cost, acc))
                 if math.isnan(avg_cost):
                     sys.exit("got NaN loss, training failed.")
         elif isinstance(event, fluid.EndStepEvent):
@@ -118,7 +118,7 @@ def infer(use_cuda, inference_program, params_dirname=None):
 
     results = inferencer.infer({'img': tensor_img})
 
-    print(("infer results: ", results[0]))
+    print("infer results: ", results[0])
 
 
 def main(use_cuda):
diff --git a/python/paddle/fluid/tests/book/high-level-api/recognize_digits/test_recognize_digits_mlp.py b/python/paddle/fluid/tests/book/high-level-api/recognize_digits/test_recognize_digits_mlp.py
index ddf7d05d43cf8be4065e070f416722b0b5eee2fa..6dd64be315159f1835244fa027e578434e6cb038 100644
--- a/python/paddle/fluid/tests/book/high-level-api/recognize_digits/test_recognize_digits_mlp.py
+++ b/python/paddle/fluid/tests/book/high-level-api/recognize_digits/test_recognize_digits_mlp.py
@@ -61,14 +61,14 @@ def train(use_cuda, train_program, params_dirname):
             avg_cost, acc = trainer.test(
                 reader=test_reader, feed_order=['img', 'label'])
 
-            print(("avg_cost: %s" % avg_cost))
-            print(("acc     : %s" % acc))
+            print("avg_cost: %s" % avg_cost)
+            print("acc     : %s" % acc)
 
             if acc > 0.2:  # Smaller value to increase CI speed
                 trainer.save_params(params_dirname)
             else:
-                print(('BatchID {0}, Test Loss {1:0.2}, Acc {2:0.2}'.format(
-                    event.epoch + 1, avg_cost, acc)))
+                print('BatchID {0}, Test Loss {1:0.2}, Acc {2:0.2}'.format(
+                    event.epoch + 1, avg_cost, acc))
                 if math.isnan(avg_cost):
                     sys.exit("got NaN loss, training failed.")
 
@@ -96,7 +96,7 @@ def infer(use_cuda, inference_program, params_dirname=None):
 
     results = inferencer.infer({'img': tensor_img})
 
-    print(("infer results: ", results[0]))
+    print("infer results: ", results[0])
 
 
 def main(use_cuda):
diff --git a/python/paddle/fluid/tests/book/high-level-api/recommender_system/test_recommender_system_newapi.py b/python/paddle/fluid/tests/book/high-level-api/recommender_system/test_recommender_system_newapi.py
index 2605c1f56fd049fc1a0851a4bb3c9f4d1a4a5525..60f3d8e105209938360487d963b0328d95e7b1f0 100644
--- a/python/paddle/fluid/tests/book/high-level-api/recommender_system/test_recommender_system_newapi.py
+++ b/python/paddle/fluid/tests/book/high-level-api/recommender_system/test_recommender_system_newapi.py
@@ -180,7 +180,7 @@ def train(use_cuda, train_program, params_dirname):
             # get avg cost
             avg_cost = np.array(avg_cost_set).mean()
 
-            print(("avg_cost: %s" % avg_cost))
+            print("avg_cost: %s" % avg_cost)
 
             if float(avg_cost) < 4:  # Smaller value to increase CI speed
                 trainer.save_params(params_dirname)
@@ -240,7 +240,7 @@ def infer(use_cuda, inference_program, params_dirname):
         },
         return_numpy=False)
 
-    print(("infer results: ", np.array(results[0])))
+    print("infer results: ", np.array(results[0]))
 
 
 def main(use_cuda):
diff --git a/python/paddle/fluid/tests/book/high-level-api/understand_sentiment/test_understand_sentiment_conv.py b/python/paddle/fluid/tests/book/high-level-api/understand_sentiment/test_understand_sentiment_conv.py
index 4a739252e19c269aeaaa115cff304cc1d7aaeef9..24e65d1bd54cff7ad64453a3a61f50351d32ef08 100644
--- a/python/paddle/fluid/tests/book/high-level-api/understand_sentiment/test_understand_sentiment_conv.py
+++ b/python/paddle/fluid/tests/book/high-level-api/understand_sentiment/test_understand_sentiment_conv.py
@@ -82,21 +82,21 @@ def train(use_cuda, train_program, params_dirname):
             avg_cost, acc = trainer.test(
                 reader=test_reader, feed_order=['words', 'label'])
 
-            print(("avg_cost: %s" % avg_cost))
-            print(("acc     : %s" % acc))
+            print("avg_cost: %s" % avg_cost)
+            print("acc     : %s" % acc)
 
             if acc > 0.2:  # Smaller value to increase CI speed
                 trainer.save_params(params_dirname)
                 trainer.stop()
 
             else:
-                print(('BatchID {0}, Test Loss {1:0.2}, Acc {2:0.2}'.format(
-                    event.epoch + 1, avg_cost, acc)))
+                print('BatchID {0}, Test Loss {1:0.2}, Acc {2:0.2}'.format(
+                    event.epoch + 1, avg_cost, acc))
                 if math.isnan(avg_cost):
                     sys.exit("got NaN loss, training failed.")
         elif isinstance(event, fluid.EndStepEvent):
-            print(("Step {0}, Epoch {1} Metrics {2}".format(
-                event.step, event.epoch, list(map(np.array, event.metrics)))))
+            print("Step {0}, Epoch {1} Metrics {2}".format(
+                event.step, event.epoch, list(map(np.array, event.metrics))))
             if event.step == 1:  # Run 2 iterations to speed CI
                 trainer.save_params(params_dirname)
                 trainer.stop()
@@ -123,14 +123,14 @@ def infer(use_cuda, inference_program, params_dirname=None):
         place=place)
 
     # Setup input by creating LoDTensor to represent sequence of words.
-    # Here each word is the basic element of the LoDTensor and the shape of 
-    # each word (base_shape) should be [1] since it is simply an index to 
+    # Here each word is the basic element of the LoDTensor and the shape of
+    # each word (base_shape) should be [1] since it is simply an index to
     # look up for the corresponding word vector.
     # Suppose the recursive_sequence_lengths info is set to [[3, 4, 2]],
-    # which has only one level of detail. Then the created LoDTensor will have only 
-    # one higher level structure (sequence of words, or sentence) than the basic 
-    # element (word). Hence the LoDTensor will hold data for three sentences of 
-    # length 3, 4 and 2, respectively. 
+    # which has only one level of detail. Then the created LoDTensor will have only
+    # one higher level structure (sequence of words, or sentence) than the basic
+    # element (word). Hence the LoDTensor will hold data for three sentences of
+    # length 3, 4 and 2, respectively.
     # Note that recursive_sequence_lengths should be a list of lists.
     recursive_seq_lens = [[3, 4, 2]]
     base_shape = [1]
@@ -138,7 +138,7 @@ def infer(use_cuda, inference_program, params_dirname=None):
     tensor_words = fluid.create_random_int_lodtensor(
         recursive_seq_lens, base_shape, place, low=0, high=len(word_dict) - 1)
     results = inferencer.infer({'words': tensor_words})
-    print(("infer results: ", results))
+    print("infer results: ", results)
 
 
 def main(use_cuda):
diff --git a/python/paddle/fluid/tests/book/high-level-api/understand_sentiment/test_understand_sentiment_dynamic_rnn.py b/python/paddle/fluid/tests/book/high-level-api/understand_sentiment/test_understand_sentiment_dynamic_rnn.py
index 690d6e47c108fbf7fc513785199e6e4cf3869e30..b3b1505a0fad07144f3f53c22abd5553054d8c51 100644
--- a/python/paddle/fluid/tests/book/high-level-api/understand_sentiment/test_understand_sentiment_dynamic_rnn.py
+++ b/python/paddle/fluid/tests/book/high-level-api/understand_sentiment/test_understand_sentiment_dynamic_rnn.py
@@ -97,21 +97,21 @@ def train(use_cuda, train_program, params_dirname):
             avg_cost, acc = trainer.test(
                 reader=test_reader, feed_order=['words', 'label'])
 
-            print(("avg_cost: %s" % avg_cost))
-            print(("acc     : %s" % acc))
+            print("avg_cost: %s" % avg_cost)
+            print("acc     : %s" % acc)
 
             if acc > 0.2:  # Smaller value to increase CI speed
                 trainer.save_params(params_dirname)
                 trainer.stop()
 
             else:
-                print(('BatchID {0}, Test Loss {1:0.2}, Acc {2:0.2}'.format(
-                    event.epoch + 1, avg_cost, acc)))
+                print('BatchID {0}, Test Loss {1:0.2}, Acc {2:0.2}'.format(
+                    event.epoch + 1, avg_cost, acc))
                 if math.isnan(avg_cost):
                     sys.exit("got NaN loss, training failed.")
         elif isinstance(event, fluid.EndStepEvent):
-            print(("Step {0}, Epoch {1} Metrics {2}".format(
-                event.step, event.epoch, list(map(np.array, event.metrics)))))
+            print("Step {0}, Epoch {1} Metrics {2}".format(
+                event.step, event.epoch, list(map(np.array, event.metrics))))
             if event.step == 1:  # Run 2 iterations to speed CI
                 trainer.save_params(params_dirname)
                 trainer.stop()
@@ -138,14 +138,14 @@ def infer(use_cuda, inference_program, params_dirname=None):
         place=place)
 
     # Setup input by creating LoDTensor to represent sequence of words.
-    # Here each word is the basic element of the LoDTensor and the shape of 
-    # each word (base_shape) should be [1] since it is simply an index to 
+    # Here each word is the basic element of the LoDTensor and the shape of
+    # each word (base_shape) should be [1] since it is simply an index to
     # look up for the corresponding word vector.
     # Suppose the recursive_sequence_lengths info is set to [[3, 4, 2]],
-    # which has only one level of detail. Then the created LoDTensor will have only 
-    # one higher level structure (sequence of words, or sentence) than the basic 
-    # element (word). Hence the LoDTensor will hold data for three sentences of 
-    # length 3, 4 and 2, respectively. 
+    # which has only one level of detail. Then the created LoDTensor will have only
+    # one higher level structure (sequence of words, or sentence) than the basic
+    # element (word). Hence the LoDTensor will hold data for three sentences of
+    # length 3, 4 and 2, respectively.
     # Note that recursive_sequence_lengths should be a list of lists.
     recursive_seq_lens = [[3, 4, 2]]
     base_shape = [1]
@@ -153,7 +153,7 @@ def infer(use_cuda, inference_program, params_dirname=None):
     tensor_words = fluid.create_random_int_lodtensor(
         recursive_seq_lens, base_shape, place, low=0, high=len(word_dict) - 1)
     results = inferencer.infer({'words': tensor_words})
-    print(("infer results: ", results))
+    print("infer results: ", results)
 
 
 def main(use_cuda):
diff --git a/python/paddle/fluid/tests/book/high-level-api/understand_sentiment/test_understand_sentiment_stacked_lstm.py b/python/paddle/fluid/tests/book/high-level-api/understand_sentiment/test_understand_sentiment_stacked_lstm.py
index af41abaf2308dbc14a33d43a5008feba14677c19..25f99ff0fd2d1050bb62338a6bf87aa29f913fb6 100644
--- a/python/paddle/fluid/tests/book/high-level-api/understand_sentiment/test_understand_sentiment_stacked_lstm.py
+++ b/python/paddle/fluid/tests/book/high-level-api/understand_sentiment/test_understand_sentiment_stacked_lstm.py
@@ -91,21 +91,21 @@ def train(use_cuda, train_program, params_dirname):
             avg_cost, acc = trainer.test(
                 reader=test_reader, feed_order=['words', 'label'])
 
-            print(("avg_cost: %s" % avg_cost))
-            print(("acc     : %s" % acc))
+            print("avg_cost: %s" % avg_cost)
+            print("acc     : %s" % acc)
 
             if acc > 0.2:  # Smaller value to increase CI speed
                 trainer.save_params(params_dirname)
                 trainer.stop()
 
             else:
-                print(('BatchID {0}, Test Loss {1:0.2}, Acc {2:0.2}'.format(
-                    event.epoch + 1, avg_cost, acc)))
+                print('BatchID {0}, Test Loss {1:0.2}, Acc {2:0.2}'.format(
+                    event.epoch + 1, avg_cost, acc))
                 if math.isnan(avg_cost):
                     sys.exit("got NaN loss, training failed.")
         elif isinstance(event, fluid.EndStepEvent):
-            print(("Step {0}, Epoch {1} Metrics {2}".format(
-                event.step, event.epoch, list(map(np.array, event.metrics)))))
+            print("Step {0}, Epoch {1} Metrics {2}".format(
+                event.step, event.epoch, list(map(np.array, event.metrics))))
             if event.step == 1:  # Run 2 iterations to speed CI
                 trainer.save_params(params_dirname)
                 trainer.stop()
@@ -133,14 +133,14 @@ def infer(use_cuda, inference_program, params_dirname=None):
         place=place)
 
     # Setup input by creating LoDTensor to represent sequence of words.
-    # Here each word is the basic element of the LoDTensor and the shape of 
-    # each word (base_shape) should be [1] since it is simply an index to 
+    # Here each word is the basic element of the LoDTensor and the shape of
+    # each word (base_shape) should be [1] since it is simply an index to
     # look up for the corresponding word vector.
     # Suppose the recursive_sequence_lengths info is set to [[3, 4, 2]],
-    # which has only one level of detail. Then the created LoDTensor will have only 
-    # one higher level structure (sequence of words, or sentence) than the basic 
-    # element (word). Hence the LoDTensor will hold data for three sentences of 
-    # length 3, 4 and 2, respectively. 
+    # which has only one level of detail. Then the created LoDTensor will have only
+    # one higher level structure (sequence of words, or sentence) than the basic
+    # element (word). Hence the LoDTensor will hold data for three sentences of
+    # length 3, 4 and 2, respectively.
     # Note that recursive_sequence_lengths should be a list of lists.
     recursive_seq_lens = [[3, 4, 2]]
     base_shape = [1]
@@ -148,7 +148,7 @@ def infer(use_cuda, inference_program, params_dirname=None):
     tensor_words = fluid.create_random_int_lodtensor(
         recursive_seq_lens, base_shape, place, low=0, high=len(word_dict) - 1)
     results = inferencer.infer({'words': tensor_words})
-    print(("infer results: ", results))
+    print("infer results: ", results)
 
 
 def main(use_cuda):
diff --git a/python/paddle/fluid/tests/book/high-level-api/word2vec/test_word2vec_new_api.py b/python/paddle/fluid/tests/book/high-level-api/word2vec/test_word2vec_new_api.py
index 8e32f90d652fa8d25e7bed4cdb03748687b17115..02e65cf56c4d1bd262831320befd2edc735c0d1c 100644
--- a/python/paddle/fluid/tests/book/high-level-api/word2vec/test_word2vec_new_api.py
+++ b/python/paddle/fluid/tests/book/high-level-api/word2vec/test_word2vec_new_api.py
@@ -98,7 +98,7 @@ def train(use_cuda, train_program, params_dirname):
                 reader=test_reader,
                 feed_order=['firstw', 'secondw', 'thirdw', 'forthw', 'nextw'])
             avg_cost = outs[0]
-            print(("loss= ", avg_cost))
+            print("loss= ", avg_cost)
 
             if avg_cost < 10.0:
                 trainer.save_params(params_dirname)
@@ -149,7 +149,7 @@ def infer(use_cuda, inference_program, params_dirname=None):
             'forthw': fourth_word
         },
         return_numpy=False)
-    print((np.array(result[0])))
+    print(np.array(result[0]))
 
 
 def main(use_cuda, is_sparse):
diff --git a/python/paddle/fluid/tests/book/notest_understand_sentiment.py b/python/paddle/fluid/tests/book/notest_understand_sentiment.py
index 2b5585149d66fe2eb92f56c1e14f9628cd756c6b..ce6342c2dad0b33e57d0ea90fc6ef1660ae4e68b 100644
--- a/python/paddle/fluid/tests/book/notest_understand_sentiment.py
+++ b/python/paddle/fluid/tests/book/notest_understand_sentiment.py
@@ -180,7 +180,7 @@ def train(word_dict,
                 cost_val, acc_val = exe.run(main_program,
                                             feed=feeder.feed(data),
                                             fetch_list=[cost, acc_out])
-                print(("cost=" + str(cost_val) + " acc=" + str(acc_val)))
+                print("cost=" + str(cost_val) + " acc=" + str(acc_val))
                 if cost_val < 0.4 and acc_val > 0.8:
                     if save_dirname is not None:
                         fluid.io.save_inference_model(save_dirname, ["words"],
@@ -235,14 +235,14 @@ def infer(word_dict, use_cuda, save_dirname=None):
         word_dict_len = len(word_dict)
 
         # Setup input by creating LoDTensor to represent sequence of words.
-        # Here each word is the basic element of the LoDTensor and the shape of 
-        # each word (base_shape) should be [1] since it is simply an index to 
+        # Here each word is the basic element of the LoDTensor and the shape of
+        # each word (base_shape) should be [1] since it is simply an index to
         # look up for the corresponding word vector.
         # Suppose the recursive_sequence_lengths info is set to [[3, 4, 2]],
-        # which has only one level of detail. Then the created LoDTensor will have only 
-        # one higher level structure (sequence of words, or sentence) than the basic 
-        # element (word). Hence the LoDTensor will hold data for three sentences of 
-        # length 3, 4 and 2, respectively. 
+        # which has only one level of detail. Then the created LoDTensor will have only
+        # one higher level structure (sequence of words, or sentence) than the basic
+        # element (word). Hence the LoDTensor will hold data for three sentences of
+        # length 3, 4 and 2, respectively.
         # Note that recursive_sequence_lengths should be a list of lists.
         recursive_seq_lens = [[3, 4, 2]]
         base_shape = [1]
@@ -261,10 +261,10 @@ def infer(word_dict, use_cuda, save_dirname=None):
                           feed={feed_target_names[0]: tensor_words},
                           fetch_list=fetch_targets,
                           return_numpy=False)
-        print((results[0].recursive_sequence_lengths()))
+        print(results[0].recursive_sequence_lengths())
         np_data = np.array(results[0])
-        print(("Inference Shape: ", np_data.shape))
-        print(("Inference results: ", np_data))
+        print("Inference Shape: ", np_data.shape)
+        print("Inference results: ", np_data)
 
 
 def main(word_dict, net_method, use_cuda, parallel=False, save_dirname=None):
diff --git a/python/paddle/fluid/tests/book/test_fit_a_line.py b/python/paddle/fluid/tests/book/test_fit_a_line.py
index 58bcbdfb03903e3a6a8a2fb59c9abfbcec301e79..37b64fa94a9aad7042e153e414ed29de3142db5a 100644
--- a/python/paddle/fluid/tests/book/test_fit_a_line.py
+++ b/python/paddle/fluid/tests/book/test_fit_a_line.py
@@ -124,9 +124,9 @@ def infer(use_cuda, save_dirname=None):
         results = exe.run(inference_program,
                           feed={feed_target_names[0]: numpy.array(test_feat)},
                           fetch_list=fetch_targets)
-        print(("infer shape: ", results[0].shape))
-        print(("infer results: ", results[0]))
-        print(("ground truth: ", test_label))
+        print("infer shape: ", results[0].shape)
+        print("infer results: ", results[0])
+        print("ground truth: ", test_label)
 
 
 def main(use_cuda, is_local=True):
diff --git a/python/paddle/fluid/tests/book/test_image_classification.py b/python/paddle/fluid/tests/book/test_image_classification.py
index 1c74481fa76a5e004d92e70fad3732505690de39..de6fe5f140a86545e3291db165af824739a814ef 100644
--- a/python/paddle/fluid/tests/book/test_image_classification.py
+++ b/python/paddle/fluid/tests/book/test_image_classification.py
@@ -119,7 +119,7 @@ def train(net_type, use_cuda, save_dirname, is_local):
     avg_cost = fluid.layers.mean(cost)
     acc = fluid.layers.accuracy(input=predict, label=label)
 
-    # Test program 
+    # Test program
     test_program = fluid.default_main_program().clone(for_test=True)
 
     optimizer = fluid.optimizer.Adam(learning_rate=0.001)
@@ -163,10 +163,10 @@ def train(net_type, use_cuda, save_dirname, is_local):
                     acc_value = numpy.array(acc_list).mean()
                     avg_loss_value = numpy.array(avg_loss_list).mean()
 
-                    print((
+                    print(
                         'PassID {0:1}, BatchID {1:04}, Test Loss {2:2.2}, Acc {3:2.2}'.
                         format(pass_id, batch_id + 1,
-                               float(avg_loss_value), float(acc_value))))
+                               float(avg_loss_value), float(acc_value)))
 
                     if acc_value > 0.01:  # Low threshold for speeding up CI
                         fluid.io.save_inference_model(save_dirname, ["pixel"],
@@ -239,7 +239,7 @@ def infer(use_cuda, save_dirname=None):
             np.testing.assert_almost_equal(
                 results[0][i], transpiler_results[0][i], decimal=5)
 
-        print(("infer results: ", results[0]))
+        print("infer results: ", results[0])
 
         fluid.io.save_inference_model(save_dirname, feed_target_names,
                                       fetch_targets, exe,
diff --git a/python/paddle/fluid/tests/book/test_label_semantic_roles.py b/python/paddle/fluid/tests/book/test_label_semantic_roles.py
index 9dbd462fb4240d885a954a9204cc58ecefba4356..b7ac911cafdc751f38c7f66bc48263a17a84dc08 100644
--- a/python/paddle/fluid/tests/book/test_label_semantic_roles.py
+++ b/python/paddle/fluid/tests/book/test_label_semantic_roles.py
@@ -189,10 +189,10 @@ def train(use_cuda, save_dirname=None, is_local=True):
                 cost = cost[0]
 
                 if batch_id % 10 == 0:
-                    print(("avg_cost:" + str(cost)))
+                    print("avg_cost:" + str(cost))
                     if batch_id != 0:
-                        print(("second per batch: " + str(
-                            (time.time() - start_time) / batch_id)))
+                        print("second per batch: " + str((time.time(
+                        ) - start_time) / batch_id))
                     # Set the threshold low to speed up the CI test
                     if float(cost) < 60.0:
                         if save_dirname is not None:
@@ -248,14 +248,14 @@ def infer(use_cuda, save_dirname=None):
          fetch_targets] = fluid.io.load_inference_model(save_dirname, exe)
 
         # Setup input by creating LoDTensor to represent sequence of words.
-        # Here each word is the basic element of the LoDTensor and the shape of 
-        # each word (base_shape) should be [1] since it is simply an index to 
+        # Here each word is the basic element of the LoDTensor and the shape of
+        # each word (base_shape) should be [1] since it is simply an index to
         # look up for the corresponding word vector.
         # Suppose the recursive_sequence_lengths info is set to [[3, 4, 2]],
-        # which has only one level of detail. Then the created LoDTensor will have only 
-        # one higher level structure (sequence of words, or sentence) than the basic 
-        # element (word). Hence the LoDTensor will hold data for three sentences of 
-        # length 3, 4 and 2, respectively. 
+        # which has only one level of detail. Then the created LoDTensor will have only
+        # one higher level structure (sequence of words, or sentence) than the basic
+        # element (word). Hence the LoDTensor will hold data for three sentences of
+        # length 3, 4 and 2, respectively.
         # Note that recursive_sequence_lengths should be a list of lists.
         recursive_seq_lens = [[3, 4, 2]]
         base_shape = [1]
@@ -333,9 +333,9 @@ def infer(use_cuda, save_dirname=None):
                           },
                           fetch_list=fetch_targets,
                           return_numpy=False)
-        print((results[0].recursive_sequence_lengths()))
+        print(results[0].recursive_sequence_lengths())
         np_data = np.array(results[0])
-        print(("Inference Shape: ", np_data.shape))
+        print("Inference Shape: ", np_data.shape)
 
 
 def main(use_cuda, is_local=True):
diff --git a/python/paddle/fluid/tests/book/test_machine_translation.py b/python/paddle/fluid/tests/book/test_machine_translation.py
index 6578328643ce54cd7e9fb2bd39ffe67ff4f1e0b6..462faad3e1cb7108f3bd6934017efe25fb9a4276 100644
--- a/python/paddle/fluid/tests/book/test_machine_translation.py
+++ b/python/paddle/fluid/tests/book/test_machine_translation.py
@@ -205,8 +205,8 @@ def train_main(use_cuda, is_sparse, is_local=True):
                                feed=feeder.feed(data),
                                fetch_list=[avg_cost])
                 avg_cost_val = np.array(outs[0])
-                print(('pass_id=' + str(pass_id) + ' batch=' + str(batch_id) +
-                       " avg_cost=" + str(avg_cost_val)))
+                print('pass_id=' + str(pass_id) + ' batch=' + str(batch_id) +
+                      " avg_cost=" + str(avg_cost_val))
                 if batch_id > 3:
                     break
                 batch_id += 1
@@ -282,7 +282,7 @@ def decode_main(use_cuda, is_sparse):
             feed=feed_dict,
             fetch_list=[translation_ids, translation_scores],
             return_numpy=False)
-        print((result_ids.recursive_sequence_lengths()))
+        print(result_ids.recursive_sequence_lengths())
         break
 
 
diff --git a/python/paddle/fluid/tests/book/test_recognize_digits.py b/python/paddle/fluid/tests/book/test_recognize_digits.py
index 49e58a148a6a268b77046268503c6065f44f90e4..3e5f76d12d41d016c995e5c85feda3c1847e356f 100644
--- a/python/paddle/fluid/tests/book/test_recognize_digits.py
+++ b/python/paddle/fluid/tests/book/test_recognize_digits.py
@@ -142,10 +142,10 @@ def train(nn_type,
                                 params_filename=params_filename)
                         return
                     else:
-                        print((
+                        print(
                             'PassID {0:1}, BatchID {1:04}, Test Loss {2:2.2}, Acc {3:2.2}'.
                             format(pass_id, batch_id + 1,
-                                   float(avg_loss_val), float(acc_val))))
+                                   float(avg_loss_val), float(acc_val)))
                         if math.isnan(float(avg_loss_val)):
                             sys.exit("got NaN loss, training failed.")
         raise AssertionError("Loss of recognize digits is too large")
@@ -206,7 +206,7 @@ def infer(use_cuda,
         results = exe.run(inference_program,
                           feed={feed_target_names[0]: tensor_img},
                           fetch_list=fetch_targets)
-        print(("infer results: ", results[0]))
+        print("infer results: ", results[0])
 
 
 def main(use_cuda, parallel, nn_type, combine):
diff --git a/python/paddle/fluid/tests/book/test_recommender_system.py b/python/paddle/fluid/tests/book/test_recommender_system.py
index ca396e5cdf7b1067351a5f81793d8398b2d357a5..b30c8771fcf267260c4c5aa7076bedc89e3b7e8b 100644
--- a/python/paddle/fluid/tests/book/test_recommender_system.py
+++ b/python/paddle/fluid/tests/book/test_recommender_system.py
@@ -260,15 +260,15 @@ def infer(use_cuda, save_dirname=None):
 
         # Use the first data from paddle.dataset.movielens.test() as input
         assert feed_target_names[0] == "user_id"
-        # Use create_lod_tensor(data, recursive_sequence_lengths, place) API 
-        # to generate LoD Tensor where `data` is a list of sequences of index 
-        # numbers, `recursive_sequence_lengths` is the length-based level of detail 
+        # Use create_lod_tensor(data, recursive_sequence_lengths, place) API
+        # to generate LoD Tensor where `data` is a list of sequences of index
+        # numbers, `recursive_sequence_lengths` is the length-based level of detail
         # (lod) info associated with `data`.
         # For example, data = [[10, 2, 3], [2, 3]] means that it contains
         # two sequences of indexes, of length 3 and 2, respectively.
-        # Correspondingly, recursive_sequence_lengths = [[3, 2]] contains one 
-        # level of detail info, indicating that `data` consists of two sequences 
-        # of length 3 and 2, respectively. 
+        # Correspondingly, recursive_sequence_lengths = [[3, 2]] contains one
+        # level of detail info, indicating that `data` consists of two sequences
+        # of length 3 and 2, respectively.
         user_id = fluid.create_lod_tensor([[1]], [[1]], place)
 
         assert feed_target_names[1] == "gender_id"
@@ -304,7 +304,7 @@ def infer(use_cuda, save_dirname=None):
                           },
                           fetch_list=fetch_targets,
                           return_numpy=False)
-        print(("inferred score: ", np.array(results[0])))
+        print("inferred score: ", np.array(results[0]))
 
 
 def main(use_cuda):
diff --git a/python/paddle/fluid/tests/book/test_rnn_encoder_decoder.py b/python/paddle/fluid/tests/book/test_rnn_encoder_decoder.py
index 25181d830956b5c408c27a70bd120b163b50998a..2e79be2bd0fc7a368df86e188b7fa616055bb3e7 100644
--- a/python/paddle/fluid/tests/book/test_rnn_encoder_decoder.py
+++ b/python/paddle/fluid/tests/book/test_rnn_encoder_decoder.py
@@ -182,8 +182,8 @@ def train(use_cuda, save_dirname=None):
                            fetch_list=[avg_cost])
 
             avg_cost_val = np.array(outs[0])
-            print(('pass_id=' + str(pass_id) + ' batch=' + str(batch_id) +
-                   " avg_cost=" + str(avg_cost_val)))
+            print('pass_id=' + str(pass_id) + ' batch=' + str(batch_id) +
+                  " avg_cost=" + str(avg_cost_val))
             if math.isnan(float(avg_cost_val[0])):
                 sys.exit("got NaN loss, training failed.")
             if batch_id > 3:
@@ -213,14 +213,14 @@ def infer(use_cuda, save_dirname=None):
          fetch_targets] = fluid.io.load_inference_model(save_dirname, exe)
 
         # Setup input by creating LoDTensor to represent sequence of words.
-        # Here each word is the basic element of the LoDTensor and the shape of 
-        # each word (base_shape) should be [1] since it is simply an index to 
+        # Here each word is the basic element of the LoDTensor and the shape of
+        # each word (base_shape) should be [1] since it is simply an index to
         # look up for the corresponding word vector.
         # Suppose the recursive_sequence_lengths info is set to [[4, 6]],
-        # which has only one level of detail. Then the created LoDTensor will have only 
-        # one higher level structure (sequence of words, or sentence) than the basic 
-        # element (word). Hence the LoDTensor will hold data for two sentences of 
-        # length 4 and 6, respectively. 
+        # which has only one level of detail. Then the created LoDTensor will have only
+        # one higher level structure (sequence of words, or sentence) than the basic
+        # element (word). Hence the LoDTensor will hold data for two sentences of
+        # length 4 and 6, respectively.
         # Note that recursive_sequence_lengths should be a list of lists.
         recursive_seq_lens = [[4, 6]]
         base_shape = [1]
@@ -241,10 +241,10 @@ def infer(use_cuda, save_dirname=None):
                           },
                           fetch_list=fetch_targets,
                           return_numpy=False)
-        print((results[0].recursive_sequence_lengths()))
+        print(results[0].recursive_sequence_lengths())
         np_data = np.array(results[0])
-        print(("Inference shape: ", np_data.shape))
-        print(("Inference results: ", np_data))
+        print("Inference shape: ", np_data.shape)
+        print("Inference results: ", np_data)
 
 
 def main(use_cuda):
diff --git a/python/paddle/fluid/tests/book/test_word2vec.py b/python/paddle/fluid/tests/book/test_word2vec.py
index 61838440b0ed2847edd3d5ecb9f1419da3047846..e761e05795313da23a9d984263ac2e202939b1e7 100644
--- a/python/paddle/fluid/tests/book/test_word2vec.py
+++ b/python/paddle/fluid/tests/book/test_word2vec.py
@@ -169,11 +169,11 @@ def infer(use_cuda, save_dirname=None):
         word_dict = paddle.dataset.imikolov.build_dict()
         dict_size = len(word_dict)
 
-        # Setup inputs by creating 4 LoDTensors representing 4 words. Here each word 
-        # is simply an index to look up for the corresponding word vector and hence 
-        # the shape of word (base_shape) should be [1]. The recursive_sequence_lengths, 
-        # which is length-based level of detail (lod) of each LoDTensor, should be [[1]] 
-        # meaning there is only one level of detail and there is only one sequence of 
+        # Setup inputs by creating 4 LoDTensors representing 4 words. Here each word
+        # is simply an index to look up for the corresponding word vector and hence
+        # the shape of word (base_shape) should be [1]. The recursive_sequence_lengths,
+        # which is length-based level of detail (lod) of each LoDTensor, should be [[1]]
+        # meaning there is only one level of detail and there is only one sequence of
         # one word on this level.
         # Note that recursive_sequence_lengths should be a list of lists.
         recursive_seq_lens = [[1]]
@@ -204,9 +204,9 @@ def infer(use_cuda, save_dirname=None):
                           },
                           fetch_list=fetch_targets,
                           return_numpy=False)
-        print((results[0].recursive_sequence_lengths()))
+        print(results[0].recursive_sequence_lengths())
         np_data = np.array(results[0])
-        print(("Inference Shape: ", np_data.shape))
+        print("Inference Shape: ", np_data.shape)
 
 
 def main(use_cuda, is_sparse, is_parallel):
diff --git a/python/paddle/fluid/tests/book_memory_optimization/test_memopt_fit_a_line.py b/python/paddle/fluid/tests/book_memory_optimization/test_memopt_fit_a_line.py
index e425da1f9d7a36b64ae2dd4cc05e04200aba937c..ccc62b442f62fa9fa175de031b0732febe38ee9a 100644
--- a/python/paddle/fluid/tests/book_memory_optimization/test_memopt_fit_a_line.py
+++ b/python/paddle/fluid/tests/book_memory_optimization/test_memopt_fit_a_line.py
@@ -78,7 +78,7 @@ for pass_id in range(PASS_NUM):
 
         if avg_loss_value[0] < 10.0:
             exit(0)  # if avg cost less than 10.0, we think our code is good.
-        print((avg_loss_value[0]))
+        print(avg_loss_value[0])
         if math.isnan(float(avg_loss_value)):
             sys.exit("got NaN loss, training failed.")
 exit(1)
diff --git a/python/paddle/fluid/tests/book_memory_optimization/test_memopt_image_classification_train.py b/python/paddle/fluid/tests/book_memory_optimization/test_memopt_image_classification_train.py
index 16e5c5f322a475a6863efbe9f5d2d8d124d4d2b5..b2a59d27da9b3348b581d51a68d769bbf3b90d35 100644
--- a/python/paddle/fluid/tests/book_memory_optimization/test_memopt_image_classification_train.py
+++ b/python/paddle/fluid/tests/book_memory_optimization/test_memopt_image_classification_train.py
@@ -155,8 +155,8 @@ for pass_id in range(PASS_NUM):
             fetch_list=[avg_cost, batch_acc, batch_size])
         accuracy.add(value=acc, weight=weight)
         pass_acc = accuracy.eval()
-        print(("loss:" + str(loss) + " acc:" + str(acc) + " pass_acc:" +
-               str(pass_acc)))
+        print("loss:" + str(loss) + " acc:" + str(acc) + " pass_acc:" + str(
+            pass_acc))
         # this model is slow, so if we can train two mini batch, we think it works properly.
         if i > 0:
             exit(0)
diff --git a/python/paddle/fluid/tests/book_memory_optimization/test_memopt_machine_translation.py b/python/paddle/fluid/tests/book_memory_optimization/test_memopt_machine_translation.py
index f290dd3e6de41f6ee66ea2d32c3fa62961e8fa49..323ddfb6911fdd57b32344933373189370005126 100644
--- a/python/paddle/fluid/tests/book_memory_optimization/test_memopt_machine_translation.py
+++ b/python/paddle/fluid/tests/book_memory_optimization/test_memopt_machine_translation.py
@@ -124,8 +124,8 @@ def main():
                            feed=feeder.feed(data),
                            fetch_list=[avg_cost])
             avg_cost_val = np.array(outs[0])
-            print(('pass_id=' + str(pass_id) + ' batch=' + str(batch_id) +
-                   " avg_cost=" + str(avg_cost_val)))
+            print('pass_id=' + str(pass_id) + ' batch=' + str(batch_id) +
+                  " avg_cost=" + str(avg_cost_val))
             if batch_id > 2:
                 exit(0)
             if math.isnan(float(avg_cost_val)):
diff --git a/python/paddle/fluid/tests/demo/fc_gan.py b/python/paddle/fluid/tests/demo/fc_gan.py
index 0bc5a470296dcce8267a7cd173faab24af219405..3d92f50f0adeca79adefc291cdfba6a012fc2118 100644
--- a/python/paddle/fluid/tests/demo/fc_gan.py
+++ b/python/paddle/fluid/tests/demo/fc_gan.py
@@ -158,8 +158,8 @@ def main():
                 dg_loss_np = exe.run(dg_program,
                                      feed={'noise': n},
                                      fetch_list={dg_loss})[0]
-            print(("Pass ID={0}, Batch ID={1}, D-Loss={2}, DG-Loss={3}".format(
-                pass_id, batch_id, d_loss_np, dg_loss_np)))
+            print("Pass ID={0}, Batch ID={1}, D-Loss={2}, DG-Loss={3}".format(
+                pass_id, batch_id, d_loss_np, dg_loss_np))
         # generate image each batch
         fig = plot(generated_img)
         plt.savefig(
diff --git a/python/paddle/fluid/tests/test_detection.py b/python/paddle/fluid/tests/test_detection.py
index 3e0dffc1e97ead3ee3317cd1c8cfff2043a8535e..fd45abd0a77cb54a3ca8e60cf80a1efe9f9d2060 100644
--- a/python/paddle/fluid/tests/test_detection.py
+++ b/python/paddle/fluid/tests/test_detection.py
@@ -46,7 +46,7 @@ class TestDetection(unittest.TestCase):
                 scores=scores, loc=loc, prior_box=pb, prior_box_var=pbv)
             self.assertIsNotNone(out)
             self.assertEqual(out.shape[-1], 6)
-        print((str(program)))
+        print(str(program))
 
     def test_detection_api(self):
         program = Program()
@@ -81,7 +81,7 @@ class TestDetection(unittest.TestCase):
             self.assertIsNotNone(trg)
             self.assertIsNotNone(trg_weight)
 
-        print((str(program)))
+        print(str(program))
 
     def test_ssd_loss(self):
         program = Program()
@@ -105,7 +105,7 @@ class TestDetection(unittest.TestCase):
             loss = layers.ssd_loss(loc, scores, gt_box, gt_label, pb, pbv)
             self.assertIsNotNone(loss)
             self.assertEqual(loss.shape[-1], 1)
-        print((str(program)))
+        print(str(program))
 
 
 class TestPriorBox(unittest.TestCase):
@@ -196,7 +196,7 @@ class TestDetectionMAP(unittest.TestCase):
             map_out = layers.detection_map(detect_res, label, 21)
             self.assertIsNotNone(map_out)
             self.assertEqual(map_out.shape, (1, ))
-        print((str(program)))
+        print(str(program))
 
 
 if __name__ == '__main__':
diff --git a/python/paddle/fluid/tests/test_if_else_op.py b/python/paddle/fluid/tests/test_if_else_op.py
index a3495cc6d4730dae21ff17443106f269f540ddb2..082f64c146f65eee4be0757d07495c33764fa841 100644
--- a/python/paddle/fluid/tests/test_if_else_op.py
+++ b/python/paddle/fluid/tests/test_if_else_op.py
@@ -84,7 +84,7 @@ class TestMNISTIfElseOp(unittest.TestCase):
                                feed={'x': x_data,
                                      'y': y_data},
                                fetch_list=[avg_loss])
-                print((outs[0]))
+                print(outs[0])
                 if outs[0] < 1.0:
                     return
         self.assertFalse(True)
@@ -139,7 +139,7 @@ class TestMNISTIfElseOp(unittest.TestCase):
                                feed={'x': x_data,
                                      'y': y_data},
                                fetch_list=[avg_loss])
-                print((outs[0]))
+                print(outs[0])
                 if outs[0] < 1.0:
                     return
         self.assertFalse(True)
diff --git a/python/paddle/fluid/tests/unittests/benchmark.py b/python/paddle/fluid/tests/unittests/benchmark.py
index aeaa1751d78f135d5702cb4a01e188afe91f383e..92559965497710e6bd5dd3038a34723f16bde533 100644
--- a/python/paddle/fluid/tests/unittests/benchmark.py
+++ b/python/paddle/fluid/tests/unittests/benchmark.py
@@ -88,8 +88,8 @@ class BenchmarkSuite(OpTest):
         for place in places:
             elapses.append(self.timeit_output_with_place(place, iters))
         for place, elapse in zip(places, elapses):
-            print(("One pass of ({2}_op) at {0} cost {1}".format(
-                str(place), elapse, self.op_type)))
+            print("One pass of ({2}_op) at {0} cost {1}".format(
+                str(place), elapse, self.op_type))
 
     def timeit_grad_with_place(self, place, iters=100):
         inputs_to_check = self._get_input_names()
@@ -108,5 +108,5 @@ class BenchmarkSuite(OpTest):
         for place in places:
             elapses.append(self.timeit_grad_with_place(place, iters))
         for place, elapse in zip(places, elapses):
-            print(("One pass of ({2}_grad_op) at {0} cost {1}".format(
-                str(place), elapse, self.op_type)))
+            print("One pass of ({2}_grad_op) at {0} cost {1}".format(
+                str(place), elapse, self.op_type))
diff --git a/python/paddle/fluid/tests/unittests/parallel_executor_test_base.py b/python/paddle/fluid/tests/unittests/parallel_executor_test_base.py
index 831331589b307e88716136b5d18b2375e6213442..67c35e9de7e83699bf30ca946856bb907152cbdd 100644
--- a/python/paddle/fluid/tests/unittests/parallel_executor_test_base.py
+++ b/python/paddle/fluid/tests/unittests/parallel_executor_test_base.py
@@ -99,8 +99,8 @@ class TestParallelExecutorBase(unittest.TestCase):
             end = time.time()
 
             if batch_size is not None:
-                print(("%.4f Instance per second" % (
-                    (batch_size * iter + 2) / (end - begin))))
+                print("%.4f Instance per second" % (
+                    (batch_size * iter + 2) / (end - begin)))
 
             avg_last_loss_val = np.array(last_loss).mean()
             avg_first_loss_val = np.array(first_loss).mean()
@@ -108,6 +108,6 @@ class TestParallelExecutorBase(unittest.TestCase):
                     float(avg_first_loss_val)):
                 sys.exit("got NaN loss, training failed.")
 
-            print((first_loss, last_loss))
+            print(first_loss, last_loss)
             # self.assertGreater(first_loss[0], last_loss[0])
             return first_loss, last_loss
diff --git a/python/paddle/fluid/transpiler/memory_optimization_transpiler.py b/python/paddle/fluid/transpiler/memory_optimization_transpiler.py
index 1c7bab8e1ed63aea559dac66f5ab47ee32f1285b..907acb1cac12c2136de897e426224e898bcce662 100644
--- a/python/paddle/fluid/transpiler/memory_optimization_transpiler.py
+++ b/python/paddle/fluid/transpiler/memory_optimization_transpiler.py
@@ -246,11 +246,11 @@ class ControlFlowGraph(object):
                             continue
 
                         if PRINT_LOG:
-                            print((("Hit Cache !!!! cache pool index "
-                                    "is %d, var name is %s, "
-                                    "cached var name is %s, "
-                                    "var shape is %s ") % (index, x, cache_var,
-                                                           str(cache_shape))))
+                            print(("Hit Cache !!!! cache pool index "
+                                   "is %d, var name is %s, "
+                                   "cached var name is %s, "
+                                   "var shape is %s ") % (index, x, cache_var,
+                                                          str(cache_shape)))
                         self.pool.pop(index)
                         if x == cache_var:
                             break