diff --git a/python/paddle/fluid/layers/control_flow.py b/python/paddle/fluid/layers/control_flow.py
index 80e8ff484a4c04df1b41bbca284d7c604962934c..f4013b61d06e8e55f16700078a4611aade20c751 100644
--- a/python/paddle/fluid/layers/control_flow.py
+++ b/python/paddle/fluid/layers/control_flow.py
@@ -748,16 +748,25 @@ def max_sequence_len(rank_table):
 
 
 def lod_tensor_to_array(x, table):
-    """ Convert a LOD_TENSOR to an LOD_TENSOR_ARRAY.
+    """ 
+    Convert a LoDTensor to a LoDTensorArray.
+
+    This function split a LoDTesnor to a LoDTensorArray according to its LoD 
+    information. LoDTensorArray is an alias of C++ std::vector<LoDTensor> in 
+    Paddle. The generated LoDTensorArray of this function can be further read 
+    or written by 'read_from_array()' and 'write_to_array()' operators. However, 
+    this function is generally an internal component of Paddle 'DynamicRNN'. 
+    Users should not use it directly.
 
     Args:
-        x (Variable|list): The LOD tensor to be converted to a LOD tensor array.
+        x (Variable|list): The LoDTensor to be converted to a LoDTensorArray.
         table (ParamAttr|list): The variable that stores the level of lod
                                 which is ordered by sequence length in
-                                descending order.
+                                descending order. It is generally generated 
+                                by 'layers.lod_rank_table()' API.
 
     Returns:
-        Variable: The variable of type array that has been converted from a
+        Variable: The LoDTensorArray that has been converted from the input 
                   tensor.
 
     Examples:
@@ -1047,6 +1056,13 @@ def array_length(array):
 
 
 class ConditionalBlockGuard(BlockGuard):
+    """
+    ConditionalBlockGuard is derived from BlockGuard. It is dedicated for 
+    holding a ConditionalBlock, and helping users entering and exiting the 
+    ConditionalBlock via Python's 'with' keyword. However, ConditionalBlockGuard 
+    is generally an internal component of IfElse, users should not use it directly.
+    """
+
     def __init__(self, block):
         if not isinstance(block, ConditionalBlock):
             raise TypeError("block should be conditional block")
@@ -1563,17 +1579,15 @@ def reorder_lod_tensor_by_rank(x, rank_table):
 
 def is_empty(x, cond=None, **ignored):
     """
-    **Is Empty**
-
-    This layer returns the truth value of whether the variable is empty.
+    Test whether an Variable is empty.
 
     Args:
-        x(Variable): Operand of *is_empty*
-        cond(Variable|None): Optional output variable to store the result
-                             of *is_empty*
+        x (Variable): The Variable to be tested.
+        cond (Variable|None): Output parameter. Returns the test result 
+                              of given 'x'.
 
     Returns:
-        Variable: The tensor variable storing the output of *is_empty*.
+        Variable: The tensor variable storing the test result of 'x'.
 
     Raises:
         TypeError: If input cond is not a variable, or cond's dtype is
diff --git a/python/paddle/fluid/layers/learning_rate_scheduler.py b/python/paddle/fluid/layers/learning_rate_scheduler.py
index 716cc7824eff0c56cc55a055310fa8b1913ac5e6..9cbb559093d384f70ef880de513ddcb21d080413 100644
--- a/python/paddle/fluid/layers/learning_rate_scheduler.py
+++ b/python/paddle/fluid/layers/learning_rate_scheduler.py
@@ -70,21 +70,40 @@ def noam_decay(d_model, warmup_steps):
 
 
 def exponential_decay(learning_rate, decay_steps, decay_rate, staircase=False):
-    """Applies exponential decay to the learning rate.
+    """
+    Applies exponential decay to the learning rate. 
+
+    When training a model, it is often recommended to lower the learning rate as the 
+    training progresses. By using this function, the learning rate will be decayed by 
+    'decay_rate' every 'decay_steps' steps.
+
+    >>> if staircase == True:
+    >>>     decayed_learning_rate = learning_rate * decay_rate ^ floor(global_step / decay_steps)
+    >>> else:
+    >>>     decayed_learning_rate = learning_rate * decay_rate ^ (global_step / decay_steps)
 
-    ```python
-    decayed_learning_rate = learning_rate *
-            decay_rate ^ (global_step / decay_steps)
-    ```
     Args:
-        learning_rate: A scalar float32 value or a Variable. This
-          will be the initial learning rate during training
-        decay_steps: A Python `int32` number.
-        decay_rate: A Python `float` number.
-        staircase: Boolean. If set true, decay the learning rate every decay_steps.
+        learning_rate(Variable|float): The initial learning rate.
+        decay_steps(int): See the decay computation above.
+        decay_rate(float): The decay rate. See the decay computation above.
+        staircase(Boolean): If True, decay the learning rate at discrete intervals.
+                            Default: False
 
     Returns:
         The decayed learning rate
+
+    Examples:
+        .. code-block:: python
+
+          base_lr = 0.1
+          sgd_optimizer = fluid.optimizer.SGD(
+                learning_rate=fluid.layers.exponential_decay(
+                    learning_rate=base_lr,
+                    decay_steps=10000,
+                    decay_rate=0.5,
+                    staircase=True))
+          sgd_optimizer.minimize(avg_cost)
+
     """
     global_step = _decay_step_counter()
 
@@ -128,22 +147,39 @@ def natural_exp_decay(learning_rate, decay_steps, decay_rate, staircase=False):
 
 
 def inverse_time_decay(learning_rate, decay_steps, decay_rate, staircase=False):
-    """Applies inverse time decay to the initial learning rate.
+    """
+    Applies inverse time decay to the initial learning rate.
 
-    >>> if staircase:
+    When training a model, it is often recommended to lower the learning rate as the 
+    training progresses. By using this function, an inverse decay function will be 
+    applied to the initial learning rate.
+
+    >>> if staircase == True:
     >>>     decayed_learning_rate = learning_rate / (1 + decay_rate * floor(global_step / decay_step))
     >>> else:
     >>>     decayed_learning_rate = learning_rate / (1 + decay_rate * global_step / decay_step)
 
     Args:
-        learning_rate: A scalar float32 value or a Variable. This
-          will be the initial learning rate during training.
-        decay_steps: A Python `int32` number.
-        decay_rate: A Python `float` number.
-        staircase: Boolean. If set true, decay the learning rate every decay_steps.
+        learning_rate(Variable|float): The initial learning rate.
+        decay_steps(int): See the decay computation above.
+        decay_rate(float): The decay rate. See the decay computation above.
+        staircase(Boolean): If True, decay the learning rate at discrete intervals.
+                            Default: False
 
     Returns:
         The decayed learning rate
+
+    Examples:
+        .. code-block:: python
+
+          base_lr = 0.1
+          sgd_optimizer = fluid.optimizer.SGD(
+                learning_rate=fluid.layers.inverse_time_decay(
+                    learning_rate=base_lr,
+                    decay_steps=10000,
+                    decay_rate=0.5,
+                    staircase=True))
+          sgd_optimizer.minimize(avg_cost)
     """
     global_step = _decay_step_counter()
 
diff --git a/python/paddle/fluid/layers/nn.py b/python/paddle/fluid/layers/nn.py
index c8cbb5ef00b7dac4ae3f833d3d98653e17bee2ab..047c3aa2b7acd0e19b05dfae13c28d2f16007e10 100644
--- a/python/paddle/fluid/layers/nn.py
+++ b/python/paddle/fluid/layers/nn.py
@@ -102,14 +102,15 @@ def fc(input,
     """
     **Fully Connected Layer**
 
-    The fully connected layer can take multiple tensors as its inputs. It
-    creates a variable called weights for each input tensor, which represents
-    a fully connected weight matrix from each input unit to each output unit.
-    The fully connected layer multiplies each input tensor with its coresponding
-    weight to produce an output Tensor. If multiple input tensors are given,
-    the results of multiple multiplications will be sumed up. If bias_attr is
-    not None, a bias variable will be created and added to the output. Finally,
-    if activation is not None, it will be applied to the output as well.
+    This function creates a fully connected layer in the network. It can take 
+    multiple tensors as its inputs. It creates a variable called weights for 
+    each input tensor, which represents a fully connected weight matrix from 
+    each input unit to each output unit. The fully connected layer multiplies 
+    each input tensor with its coresponding weight to produce an output Tensor. 
+    If multiple input tensors are given, the results of multiple multiplications 
+    will be sumed up. If bias_attr is not None, a bias variable will be created 
+    and added to the output. Finally, if activation is not None, it will be applied 
+    to the output as well.
 
     This process can be formulated as follows:
 
@@ -878,7 +879,7 @@ def cos_sim(X, Y):
     Args:
         X (Variable): The input X.
         Y (Variable): The input Y.
-    
+
     Returns:
         Variable: the output of cosine(X, Y).
     """
@@ -1083,7 +1084,7 @@ def chunk_eval(input,
         chunk_scheme (str): ${chunk_scheme_comment}
         num_chunk_types (int): ${num_chunk_types_comment}
         excluded_chunk_types (list): ${excluded_chunk_types_comment}
-    
+
     Returns:
         tuple: tuple containing: (precision, recall, f1_score,
                num_infer_chunks, num_label_chunks,
@@ -1143,7 +1144,7 @@ def sequence_conv(input,
         bias_attr (ParamAttr|None): attributes for bias
         param_attr (ParamAttr|None): attributes for parameter
         act (str): the activation type
-    
+
     Returns:
         Variable: output of sequence_conv
     """
@@ -1509,6 +1510,7 @@ def sequence_last_step(input):
     return sequence_pool(input=input, pool_type="last")
 
 
+@templatedoc()
 def pool2d(input,
            pool_size=-1,
            pool_type="max",
@@ -1520,12 +1522,12 @@ def pool2d(input,
            use_mkldnn=False,
            name=None):
     """
-    This function adds the operator for pooling in 2 dimensions, using the
-    pooling configurations mentioned in input parameters.
+    ${comment}
 
     Args:
         input (Variable): ${input_comment}
-        pool_size (int): ${ksize_comment}
+        pool_size (int): The side length of pooling windows. All pooling 
+                         windows are squares with pool_size on a side.
         pool_type (str): ${pooling_type_comment}
         pool_stride (int): stride of the pooling layer.
         pool_padding (int): padding size.
@@ -1533,11 +1535,29 @@ def pool2d(input,
         use_cudnn (bool): ${use_cudnn_comment}
         ceil_mode (bool): ${ceil_mode_comment}
         use_mkldnn (bool): ${use_mkldnn_comment}
-        name (str): A name for this layer(optional). If set None, the layer
-            will be named automatically.
-    
+        name (str|None): A name for this layer(optional). If set None, the 
+                        layer will be named automatically.
+
     Returns:
         Variable: output of pool2d layer.
+
+    Raises:
+        ValueError: If 'pool_type' is not "max" nor "avg"
+        ValueError: If 'global_pooling' is False and 'pool_size' is -1
+        ValueError: If 'use_cudnn' is not a bool value.
+
+    Examples:
+
+        .. code-block:: python
+
+          data = fluid.layers.data(
+              name='data', shape=[3, 32, 32], dtype='float32')
+          conv2d = fluid.layers.pool2d(
+                            input=data, 
+                            pool_size=2, 
+                            pool_type='max', 
+                            pool_stride=1, 
+                            global_pooling=False)
     """
     if pool_type not in ["max", "avg"]:
         raise ValueError(
@@ -1800,7 +1820,7 @@ def beam_search_decode(ids, scores, name=None):
         ids (Variable): ${ids_comment}
         scores (Variable): ${scores_comment}
         name (str): The name of this layer. It is optional.
-    
+
     Returns:
         tuple: a tuple of two output variable: sentence_ids, sentence_scores
     """
@@ -2063,7 +2083,7 @@ def beam_search(pre_ids, ids, scores, beam_size, end_id, level=0):
         beam_size (int): ${beam_size_comment}
         end_id (int): ${end_id_comment}
         level (int): ${level_comment}
-    
+
     Returns:
         tuple: a tuple of beam_search output variables: selected_ids, selected_scores
     '''
@@ -2719,7 +2739,7 @@ def topk(input, k, name=None):
     This operator is used to find values and indices of the k largest entries
     for the last dimension.
 
-    If the input is a vector (rank=1), finds the k largest entries in the vector
+    If the input is a vector (1-D Tensor), finds the k largest entries in the vector
     and outputs their values and indices as vectors. Thus values[j] is the j-th
     largest entry in input, and its index is indices[j].
 
@@ -2729,9 +2749,11 @@ def topk(input, k, name=None):
     Args:
         input(Variable): The input variable which can be a vector or Tensor with
             higher rank.
-        k(int): An integer value to specify the top k largest elements.
+        k(int):  The number of top elements to look for along the last dimension 
+                 of input.
         name(str|None): A name for this layer(optional). If set None, the layer
-                       will be named automatically.
+                       will be named automatically. 
+                       Default: None
 
     Returns:
         values(Variable): The k largest elements along each last dimensional
@@ -2739,13 +2761,16 @@ def topk(input, k, name=None):
         indices(Variable): The indices of values within the last dimension of
             input.
 
+    Raises:
+        ValueError: If k < 1 or k is not less than the last dimension of input
+
     Examples:
         .. code-block:: python
 
             top5_values, top5_indices = layers.topk(input, k=5)
     """
     shape = input.shape
-    if k < 1 and k >= shape[-1]:
+    if k < 1 or k >= shape[-1]:
         raise ValueError("k must be greater than 0 and less than %d." %
                          (shape[-1]))
 
@@ -3045,7 +3070,7 @@ def nce(input,
         param_attr (ParamAttr|None): attributes for parameter
         bias_attr (ParamAttr|None): attributes for bias
         num_neg_samples (int): ${num_neg_samples_comment}
-    
+
     Returns:
         Variable: output of nce layer.
     """
diff --git a/python/paddle/fluid/layers/tensor.py b/python/paddle/fluid/layers/tensor.py
index 62b01d595a812ee8fc094e40b6dfb5c3f56cd012..e03c8ca91462961976ede253908e319957ba874e 100644
--- a/python/paddle/fluid/layers/tensor.py
+++ b/python/paddle/fluid/layers/tensor.py
@@ -79,20 +79,33 @@ def create_global_var(shape,
                       force_cpu=False,
                       name=None):
     """
-    Create a global variable. such as global_step
+    Create a new variable in the global block(block 0).
+
     Args:
         shape(list[int]): shape of the variable
-        value(float): the value of the variable
-        dtype(string): element type of the parameter
-        persistable(bool): if this variable is persistable
-        force_cpu(bool): force this variable to be on CPU
+        value(float): the value of the variable. The new created 
+                      variable will be filled with it.
+        dtype(string): data type of the variable
+        persistable(bool): if this variable is persistable. 
+                           Default: False
+        force_cpu(bool): force this variable to be on CPU. 
+                         Default: False
+        name(str|None): The name of the variable. If set to None the variable 
+                        name will be generated automatically. 
+                        Default: None
 
     Returns:
         Variable: the created Variable
+
+    Examples:
+        .. code-block:: python
+
+            var = fluid.create_global_var(shape=[2,3], value=1.0, dtype='float32', 
+                                 persistable=True, force_cpu=True, name='new_var')
     """
     helper = LayerHelper("global_var", **locals())
     var = helper.create_global_variable(
-        dtype=dtype, shape=shape, persistable=persistable, name=name)
+        dtype=dtype, shape=shape, persistable=persistable)
     helper.set_variable_initializer(
         var, initializer=Constant(
             value=float(value), force_cpu=force_cpu))
@@ -152,10 +165,11 @@ def sums(input, out=None):
     Args:
         input (Variable|list): The input tensor that has the elements
                                that need to be summed up.
+        out (Variable|None): Output parameter. Returns the sum result.
+                             Default: None
 
     Returns:
-        Variable: The tensor type variable that has the sum of input
-                  written to it.
+        Variable: the sum of input. The same as the argument 'out'
 
     Examples:
         .. code-block::python
@@ -328,13 +342,13 @@ def argmin(x, axis=0):
         x(Variable): The input to compute the indices of
                      the min elements.
         axis(int): Axis to compute indices along.
-    
+
     Returns:
         Variable: The tensor variable storing the output
-    
+
     Examples:
         .. code-block:: python
-          
+
           out = fluid.layers.argmin(x=in, axis=0)
           out = fluid.layers.argmin(x=in, axis=-1)  
     """
@@ -359,13 +373,13 @@ def argmax(x, axis=0):
         x(Variable): The input to compute the indices of
                      the max elements.
         axis(int): Axis to compute indices along.
-    
+
     Returns:
         Variable: The tensor variable storing the output
-    
+
     Examples:
         .. code-block:: python
-          
+
           out = fluid.layers.argmax(x=in, axis=0)
           out = fluid.layers.argmax(x=in, axis=-1)  
     """