diff --git a/python/paddle/fluid/initializer.py b/python/paddle/fluid/initializer.py
index 47199fcd1adbe2d0d3aff35e8ac3872a0258f74e..f09097b57bd7192923b638647ea7213b2c8d638a 100644
--- a/python/paddle/fluid/initializer.py
+++ b/python/paddle/fluid/initializer.py
@@ -1164,10 +1164,11 @@ def calculate_gain(nonlinearity, param=None):
 
     Examples:
         .. code-block:: python
-
+          :name: code-example1
             import paddle
             gain = paddle.nn.initializer.calculate_gain('tanh') # 5.0 / 3
             gain = paddle.nn.initializer.calculate_gain('leaky_relu', param=1.0) # 1.0 = math.sqrt(2.0 / (1+param^2))
+            initializer = paddle.nn.initializer.Orthogonal(gain)
 
     """
     if param is None:
diff --git a/python/paddle/nn/initializer/constant.py b/python/paddle/nn/initializer/constant.py
index 292eaff362b40773fb2980174b146cb506d54a9a..66818dab451a353881bcb948b01f211265896c29 100644
--- a/python/paddle/nn/initializer/constant.py
+++ b/python/paddle/nn/initializer/constant.py
@@ -22,11 +22,11 @@ class Constant(ConstantInitializer):
     """Implement the constant initializer.
 
     Args:
-        value (float32): constant value to initialize the parameter 
+        value (float32|float64, optional): constant value to initialize the parameter. Default: 0.0.
 
     Examples:
         .. code-block:: python
-
+          :name: code-example1
             import paddle
             import paddle.nn as nn
 
diff --git a/python/paddle/nn/initializer/kaiming.py b/python/paddle/nn/initializer/kaiming.py
index b8ed7febb6bc7917b5a28d1f5d39b161a28eb4be..456496571924e080b23477efd83e386ce4508876 100644
--- a/python/paddle/nn/initializer/kaiming.py
+++ b/python/paddle/nn/initializer/kaiming.py
@@ -36,7 +36,7 @@ class KaimingNormal(MSRAInitializer):
         \sqrt{\frac{2.0}{fan\_in}}
 
     Args:
-        fan_in (float32|None): fan_in for Kaiming normal Initializer. If None, it is\
+        fan_in (float32|None, optional): fan_in for Kaiming normal Initializer. If None, it is 
         inferred from the variable. default is None.
 
     Note:
@@ -44,7 +44,7 @@ class KaimingNormal(MSRAInitializer):
 
     Examples:
         .. code-block:: python
-
+          :name: code-example1
             import paddle
             import paddle.nn as nn
 
@@ -79,7 +79,7 @@ class KaimingUniform(MSRAInitializer):
         x = \sqrt{\frac{6.0}{fan\_in}}
 
     Args:
-        fan_in (float32|None): fan_in for Kaiming uniform Initializer. If None, it is\
+        fan_in (float32|None, optional): fan_in for Kaiming uniform Initializer. If None, it is 
         inferred from the variable. default is None.
 
     Note:
@@ -87,7 +87,7 @@ class KaimingUniform(MSRAInitializer):
 
     Examples:
         .. code-block:: python
-
+          :name: code-example1
             import paddle
             import paddle.nn as nn
 
diff --git a/python/paddle/tensor/creation.py b/python/paddle/tensor/creation.py
index 521839af902b5606bf5189b55a5e6df1ae866e38..6b5993744f7cf39ecf3e94fcfd74bdeba9a14233 100644
--- a/python/paddle/tensor/creation.py
+++ b/python/paddle/tensor/creation.py
@@ -962,7 +962,7 @@ def tril(x, diagonal=0, name=None):
 
 def triu(x, diagonal=0, name=None):
     r"""
-    This op returns the upper triangular part of a matrix (2-D tensor) or batch of matrices
+    Return the upper triangular part of a matrix (2-D tensor) or batch of matrices
     :attr:`x`, the other elements of the result tensor are set to 0.
     The upper triangular part of the matrix is defined as the elements on and
     above the diagonal.
diff --git a/python/paddle/tensor/manipulation.py b/python/paddle/tensor/manipulation.py
index 96d24a7f915ee7a726191286173fb1a34c755505..c445402412e16b6d0c72f7bc058c7831432ed0cd 100755
--- a/python/paddle/tensor/manipulation.py
+++ b/python/paddle/tensor/manipulation.py
@@ -1887,7 +1887,7 @@ def split(x, num_or_sections, axis=0, name=None):
 
 def squeeze(x, axis=None, name=None):
     """
-    This OP will squeeze the dimension(s) of size 1 of input tensor x's shape. 
+    Squeeze the dimension(s) of size 1 of input tensor x's shape. 
     
     Note that the output Tensor will share data with origin Tensor and doesn't have a 
     Tensor copy in ``dygraph`` mode. If you want to use the Tensor copy version, 
@@ -1944,7 +1944,7 @@ def squeeze(x, axis=None, name=None):
 
     Examples:
         .. code-block:: python
-
+	  :name: code-example1
             import paddle
             
             x = paddle.rand([5, 1, 10])
@@ -2139,13 +2139,13 @@ def unique(x,
             :ref:`api_guide_Name`. Default: None.
 
     Returns: 
-        tuple: (out, indices, inverse, counts). `out` is the unique tensor for `x`. `indices` is \
+        tuple (out, indices, inverse, counts). `out` is the unique tensor for `x`. `indices` is \
             provided only if `return_index` is True. `inverse` is provided only if `return_inverse` \
             is True. `counts` is provided only if `return_counts` is True.
 
     Examples:
         .. code-block:: python
-
+	  :name: code-example1
             import paddle
 
             x = paddle.to_tensor([2, 3, 3, 1, 5, 3])
diff --git a/python/paddle/tensor/math.py b/python/paddle/tensor/math.py
index ffca233ff16bf92f97737329a2bf89bc575b950c..1cb350f4d7288ef0858ee0e382ed05babe4686ac 100644
--- a/python/paddle/tensor/math.py
+++ b/python/paddle/tensor/math.py
@@ -1319,7 +1319,7 @@ def nanmean(x, axis=None, keepdim=False, name=None):
 @templatedoc(op_type="sum")
 def add_n(inputs, name=None):
     """
-    This OP is used to sum one or more Tensor of the input.
+    Sum one or more Tensor of the input.
     
     For example:
 
@@ -1365,7 +1365,7 @@ def add_n(inputs, name=None):
 
     Examples:
         .. code-block:: python
-
+          :name: code-example1
             import paddle
 
             input0 = paddle.to_tensor([[1, 2, 3], [4, 5, 6]], dtype='float32')
diff --git a/python/paddle/tensor/random.py b/python/paddle/tensor/random.py
index f43bda1129589636ec1b5e4b7b5ee837e3785c72..990b20a26772c318744989bcad176e05ff723843 100644
--- a/python/paddle/tensor/random.py
+++ b/python/paddle/tensor/random.py
@@ -631,13 +631,13 @@ def randint(low=0, high=None, shape=[1], dtype=None, name=None):
     If ``high`` is None (the default), the range is [0, ``low``).
 
     Args:
-        low (int): The lower bound on the range of random values to generate.
+        low (int, optional): The lower bound on the range of random values to generate.
             The ``low`` is included in the range. If ``high`` is None, the
             range is [0, ``low``). Default is 0.
         high (int, optional): The upper bound on the range of random values to
             generate, the ``high`` is excluded in the range. Default is None
             (see above for behavior if high = None). Default is None.
-        shape (list|tuple|Tensor): The shape of the output Tensor. If ``shape``
+        shape (list|tuple|Tensor, optional): The shape of the output Tensor. If ``shape``
             is a list or tuple, the elements of it should be integers or Tensors
             (with the shape [1], and the data type int32 or int64). If ``shape``
             is a Tensor, it should be a 1-D Tensor(with the data type int32 or
diff --git a/python/paddle/tensor/search.py b/python/paddle/tensor/search.py
index 94a05294aaa63cc8c56df5b01ce3c6b6ad429e93..f46b53a3b71f4acb3627c9dd55986eb597a1641d 100644
--- a/python/paddle/tensor/search.py
+++ b/python/paddle/tensor/search.py
@@ -207,7 +207,7 @@ def argmax(x, axis=None, keepdim=False, dtype="int64", name=None):
 
 def argmin(x, axis=None, keepdim=False, dtype="int64", name=None):
     """
-    This OP computes the indices of the min elements of the input tensor's
+    Computing the indices of the min elements of the input tensor's
     element along the provided axis.
 
     Args:
@@ -217,7 +217,7 @@ def argmin(x, axis=None, keepdim=False, dtype="int64", name=None):
             is [-R, R), where R is x.ndim. when axis < 0, it works the same way
             as axis + R. Default is None, the input `x` will be into the flatten tensor, and selecting the min value index.
         keepdim(bool, optional): Whether to keep the given axis in output. If it is True, the dimensions will be same as input x and with size one in the axis. Otherwise the output dimentions is one fewer than x since the axis is squeezed. Default is False.
-        dtype(str): Data type of the output tensor which can
+        dtype(str, optional): Data type of the output tensor which can
                     be int32, int64. The default value is 'int64', and it will
                     return the int64 indices.
         name(str, optional): The default value is None. Normally there is no
@@ -225,11 +225,11 @@ def argmin(x, axis=None, keepdim=False, dtype="int64", name=None):
             refer to :ref:`api_guide_Name`.
 
     Returns:
-        Tensor, return the tensor of `int32` if set :attr:`dtype` is `int32`, otherwise return the tensor of `int64`
+        Tensor, return the tensor of `int32` if set :attr:`dtype` is `int32`, otherwise return the tensor of `int64`.
 
     Examples:
         .. code-block:: python
-
+          :name: code-example1
             import paddle
 
             x =  paddle.to_tensor([[5,8,9,5],
@@ -834,7 +834,7 @@ def masked_select(x, mask, name=None):
 
 def topk(x, k, axis=None, largest=True, sorted=True, name=None):
     """
-    This OP is used to find values and indices of the k largest or smallest at the optional axis.
+    Return values and indices of the k largest or smallest at the optional axis.
     If the input is a 1-D Tensor, finds the k largest or smallest values and indices.
     If the input is a Tensor with higher rank, this operator computes the top k values and indices along the :attr:`axis`.
 
@@ -856,35 +856,27 @@ def topk(x, k, axis=None, largest=True, sorted=True, name=None):
     Examples:
 
         .. code-block:: python
+          :name: code-example1
+            import paddle
 
-           import paddle
+            data_1 = paddle.to_tensor([1, 4, 5, 7])
+            value_1, indices_1 = paddle.topk(data_1, k=1)
+            print(value_1) # [7]
+            print(indices_1) # [3]
+
+            data_2 = paddle.to_tensor([[1, 4, 5, 7], [2, 6, 2, 5]])
+            value_2, indices_2 = paddle.topk(data_2, k=1)
+            print(value_2) # [[7], [6]]
+            print(indices_2) # [[3], [1]]
+
+            value_3, indices_3 = paddle.topk(data_2, k=1, axis=-1)
+            print(value_3) # [[7], [6]]
+            print(indices_3) # [[3], [1]]
+
+            value_4, indices_4 = paddle.topk(data_2, k=1, axis=0)
+            print(value_4) # [[2, 6, 5, 7]]
+            print(indices_4) # [[1, 1, 0, 0]]
 
-           tensor_1 = paddle.to_tensor([1, 4, 5, 7])
-           value_1, indices_1 = paddle.topk(tensor_1, k=1)
-           print(value_1)
-           # [7]
-           print(indices_1)
-           # [3] 
-           tensor_2 = paddle.to_tensor([[1, 4, 5, 7], [2, 6, 2, 5]])
-           value_2, indices_2 = paddle.topk(tensor_2, k=1)
-           print(value_2)
-           # [[7]
-           #  [6]]
-           print(indices_2)
-           # [[3]
-           #  [1]]
-           value_3, indices_3 = paddle.topk(tensor_2, k=1, axis=-1)
-           print(value_3)
-           # [[7]
-           #  [6]]
-           print(indices_3)
-           # [[3]
-           #  [1]]
-           value_4, indices_4 = paddle.topk(tensor_2, k=1, axis=0)
-           print(value_4)
-           # [[2 6 5 7]]
-           print(indices_4)
-           # [[1 1 0 0]]
 
     """