diff --git a/scheduled_sampling/random_schedule_generator.py b/scheduled_sampling/random_schedule_generator.py
index 046dce63520aa961ace5b538305b6134ee042a79..7569eaffc29ab0abda3e44764f2ccf647b8b306e 100644
--- a/scheduled_sampling/random_schedule_generator.py
+++ b/scheduled_sampling/random_schedule_generator.py
@@ -1,21 +1,20 @@
 import numpy as np
 import math
-import pdb
-'''
-The random sampling rate for scheduled sampling algoithm, which uses devcayed
-sampling rate.
-'''
 
 
 class RandomScheduleGenerator:
-    '''
-    schduled_type: is the type of the decay. It supports constant, linear,
-    exponential, and inverse_sigmoid right now.
-    a: parameter of the decay (MUST BE DOUBLE)
-    b: parameter of the decay (MUST BE DOUBLE)
-    '''
+    """
+    The random sampling rate for scheduled sampling algoithm, which uses devcayed
+    sampling rate.
+    """
 
     def __init__(self, schedule_type, a, b):
+        """
+        schduled_type: is the type of the decay. It supports constant, linear,
+        exponential, and inverse_sigmoid right now.
+        a: parameter of the decay (MUST BE DOUBLE)
+        b: parameter of the decay (MUST BE DOUBLE)
+        """
         self.schedule_type = schedule_type
         self.a = a
         self.b = b
@@ -24,33 +23,25 @@ class RandomScheduleGenerator:
             "constant": lambda a, b, d: a,
             "linear": lambda a, b, d: max(a, 1 - d / b),
             "exponential": lambda a, b, d: pow(a, d / b),
-            "inverse_sigmoid": lambda a, b, d: b / (b + exp(d * a / b)),
+            "inverse_sigmoid": lambda a, b, d: b / (b + math.exp(d * a / b)),
         }
         assert (self.schedule_type in self.schedule_computers)
         self.schedule_computer = self.schedule_computers[self.schedule_type]
 
-    '''
-    Get the schedule sampling rate. Usually not needed to be called by the users
-    '''
-
     def getScheduleRate(self):
+        """
+        Get the schedule sampling rate. Usually not needed to be called by the users
+        """
         return self.schedule_computer(self.a, self.b, self.data_processed_)
 
-    '''
-    Get a batch_size of sampled indexes. These indexes can be passed to a
-    MultiplexLayer to select from the grouth truth and generated samples
-    from the last time step.
-    '''
-
     def processBatch(self, batch_size):
+        """
+        Get a batch_size of sampled indexes. These indexes can be passed to a
+        MultiplexLayer to select from the grouth truth and generated samples
+        from the last time step.
+        """
         rate = self.getScheduleRate()
         numbers = np.random.rand(batch_size)
         indexes = (numbers >= rate).astype('int32').tolist()
         self.data_processed_ += batch_size
         return indexes
-
-
-if __name__ == "__main__":
-    schedule_generator = RandomScheduleGenerator("linear", 0.1, 500000)
-    true_token_flag = schedule_generator.processBatch(5)
-    pdb.set_trace()
diff --git a/scheduled_sampling/scheduled_sampling.py b/scheduled_sampling/scheduled_sampling.py
index e641c44846d4a3ebb47190ef2a9293a9ecfd2f73..1dead8969a2f5579102731d62de241afe96e0996 100644
--- a/scheduled_sampling/scheduled_sampling.py
+++ b/scheduled_sampling/scheduled_sampling.py
@@ -74,7 +74,7 @@ def seqToseq_net(source_dict_dim, target_dict_dim, is_generating=False):
             decoder_state=decoder_mem)
 
         gru_out_memory = paddle.layer.memory(
-            name='gru_out', size=target_dict_dim)  # , boot_with_const_id=0)
+            name='gru_out', size=target_dict_dim)
 
         generated_word = paddle.layer.max_id(input=gru_out_memory)