update document

python/paddle/fluid/layers/control_flow.py

@@ -76,13 +76,13 @@ def split_lod_tensor(input, mask, level=0):
     Examples:
         .. code-block:: python
 
-          x = layers.data(name='x', shape=[1])
+          x = fluid.layers.data(name='x', shape=[1])
           x.persistable = True
 
-          y = layers.data(name='y', shape=[1])
+          y = fluid.layers.data(name='y', shape=[1])
           y.persistable = True
 
-          out_true, out_false = layers.split_lod_tensor(
+          out_true, out_false = fluid.layers.split_lod_tensor(
                 input=x, mask=y, level=level)
 
     """
@@ -990,6 +990,7 @@ def array_read(array, i):
         Variable: The tensor type variable that has the data written to it.
     Examples:
         .. code-block:: python
+
           tmp = fluid.layers.zeros(shape=[10], dtype='int32')
           i = fluid.layers.fill_constant(shape=[1], dtype='int64', value=10)
           arr = layers.array_read(tmp, i=i)
@@ -1027,7 +1028,7 @@ def shrink_memory(x, i, table):
 
 def array_length(array):
     """
-    **Get the length of Input LoDTensorArray**
+    **Get the Length of Input LoDTensorArray**
 
     This function performs the operation to find the length of the input
     LOD_TENSOR_ARRAY.
@@ -1048,6 +1049,7 @@ def array_length(array):
           i = fluid.layers.fill_constant(shape=[1], dtype='int64', value=10)
           arr = fluid.layers.array_write(tmp, i=i)
           arr_len = fluid.layers.array_length(arr)
+
     """
     helper = LayerHelper('array_length', **locals())
     tmp = helper.create_tmp_variable(dtype='int64')

python/paddle/fluid/layers/learning_rate_scheduler.py

@@ -163,7 +163,7 @@ def polynomial_decay(learning_rate,
                      power=1.0,
                      cycle=False):
     """
-    **polynomial_decay**
+    **Polynomial Decay**
 
     Applies polynomial decay to the initial learning rate.
 
@@ -180,9 +180,9 @@ def polynomial_decay(learning_rate,
         learning_rate(Variable|float32): A scalar float32 value or a Variable. This
           will be the initial learning rate during training
         decay_steps(int32): A Python `int32` number.
-        end_learning_rate(float): A Python `float` number.
-        power(float): A Python `float` number
-        cycle(bool, Default False): Boolean. If set true, decay the learning rate every decay_steps.
+        end_learning_rate(float, Default: 0.0001): A Python `float` number.
+        power(float, Default: 1.0): A Python `float` number
+        cycle(bool, Default: False): Boolean. If set true, decay the learning rate every decay_steps.
 
     Returns:
         The decayed learning rate

python/paddle/fluid/layers/nn.py

@@ -1615,7 +1615,9 @@ def batch_norm(input,
 
     Can be used as a normalizer function for conv2d and fully_connected operations.
     The required data format for this layer is one of the following:
+
     1. NHWC `[batch, in_height, in_width, in_channels]`
+
     2. NCHW `[batch, in_channels, in_height, in_width]`
 
     Refer to `Batch Normalization: Accelerating Deep Network Training by Reducing