diff --git a/doc/api/v1/trainer_config_helpers/layers.rst b/doc/api/v1/trainer_config_helpers/layers.rst
index 9dec89063ae94038d7d847db9061e7e61ba9de9b..75c1b35246486528524fd5baa04704249d5a9275 100644
--- a/doc/api/v1/trainer_config_helpers/layers.rst
+++ b/doc/api/v1/trainer_config_helpers/layers.rst
@@ -498,10 +498,10 @@ hsigmoid
     :members: hsigmoid
     :noindex:
 
-smooth_l1
----------
+smooth_l1_cost
+--------------
 ..  automodule:: paddle.trainer_config_helpers.layers
-    :members: smooth_l1
+    :members: smooth_l1_cost
     :noindex:
 
 Check Layer 
diff --git a/doc/api/v2/config/layer.rst b/doc/api/v2/config/layer.rst
index 4e3589ebc47039a4bc4e04b130c0aa536dda73a1..0ade7990193d710792bbff78f6b7d338549471f6 100644
--- a/doc/api/v2/config/layer.rst
+++ b/doc/api/v2/config/layer.rst
@@ -421,7 +421,7 @@ hsigmoid
 
 smooth_l1
 ---------
-..  automodule:: paddle.v2.layer.smooth_l1
+..  autoclass:: paddle.v2.layer.smooth_l1_cost
     :noindex:
 
 Check Layer 
diff --git a/python/paddle/trainer_config_helpers/layers.py b/python/paddle/trainer_config_helpers/layers.py
index 1796e48f09ae50642897af7e783f020580772ac4..b9e3d264042275070dd96bc6c192f9376378b8fe 100755
--- a/python/paddle/trainer_config_helpers/layers.py
+++ b/python/paddle/trainer_config_helpers/layers.py
@@ -116,7 +116,7 @@ __all__ = [
     'spp_layer',
     'pad_layer',
     'eos_layer',
-    'smooth_l1',
+    'smooth_l1_cost',
     'layer_support',
 ]
 
@@ -5283,7 +5283,7 @@ def multi_binary_label_cross_entropy(input,
 
 @wrap_name_default()
 @layer_support()
-def smooth_l1(input, label, name=None, layer_attr=None):
+def smooth_l1_cost(input, label, name=None, layer_attr=None):
     """
     This is a L1 loss but more smooth. It requires that the
     size of input and label are equal. The formula is as follows,
@@ -5296,19 +5296,15 @@ def smooth_l1(input, label, name=None, layer_attr=None):
 
     .. math::
 
-        mooth_{L1}(x) =
-        \begin{cases}
-        0.5x^2& \text{if} |x| < 1 \\
-        |x|-0.5& \text{otherwise}
-        \end{cases}
+        smooth_{L1}(x) = \\begin{cases} 0.5x^2& \\text{if}  \\ |x| < 1 \\\\ |x|-0.5& \\text{otherwise} \end{cases}
 
     More details can be found by referring to `Fast R-CNN
     <https://arxiv.org/pdf/1504.08083v2.pdf>`_
 
     .. code-block:: python
 
-       cost = smooth_l1(input=input_layer,
-                        label=label_layer)
+       cost = smooth_l1_cost(input=input_layer,
+                             label=label_layer)
 
     :param input: The input layer.
     :type input: LayerOutput