diff --git a/paddle/fluid/API.spec b/paddle/fluid/API.spec
index 433d93c0c179cc6a2147c42e564c0af9834fd375..56bb4201994d9643b06a27d9c42d353b657d1774 100755
--- a/paddle/fluid/API.spec
+++ b/paddle/fluid/API.spec
@@ -188,7 +188,7 @@ paddle.fluid.layers.beam_search (ArgSpec(args=['pre_ids', 'pre_scores', 'ids', '
 paddle.fluid.layers.row_conv (ArgSpec(args=['input', 'future_context_size', 'param_attr', 'act'], varargs=None, keywords=None, defaults=(None, None)), ('document', '1d8a1c8b686b55631ba1b77805e4eacf'))
 paddle.fluid.layers.multiplex (ArgSpec(args=['inputs', 'index'], varargs=None, keywords=None, defaults=None), ('document', '2c4d1ae83da6ed35e3b36ba1b3b51d23'))
 paddle.fluid.layers.layer_norm (ArgSpec(args=['input', 'scale', 'shift', 'begin_norm_axis', 'epsilon', 'param_attr', 'bias_attr', 'act', 'name'], varargs=None, keywords=None, defaults=(True, True, 1, 1e-05, None, None, None, None)), ('document', '79797f827d89ae72c77960e9696883a9'))
-paddle.fluid.layers.group_norm (ArgSpec(args=['input', 'groups', 'epsilon', 'param_attr', 'bias_attr', 'act', 'data_layout', 'name'], varargs=None, keywords=None, defaults=(1e-05, None, None, None, 'NCHW', None)), ('document', '65231cc8281815124934b1439fbb750c'))
+paddle.fluid.layers.group_norm (ArgSpec(args=['input', 'groups', 'epsilon', 'param_attr', 'bias_attr', 'act', 'data_layout', 'name'], varargs=None, keywords=None, defaults=(1e-05, None, None, None, 'NCHW', None)), ('document', '87dd4b818f102bc1a780e1804c28bd38'))
 paddle.fluid.layers.spectral_norm (ArgSpec(args=['weight', 'dim', 'power_iters', 'eps', 'name'], varargs=None, keywords=None, defaults=(0, 1, 1e-12, None)), ('document', '9461e67095a6fc5d568fb2ce8fef66ff'))
 paddle.fluid.layers.softmax_with_cross_entropy (ArgSpec(args=['logits', 'label', 'soft_label', 'ignore_index', 'numeric_stable_mode', 'return_softmax', 'axis'], varargs=None, keywords=None, defaults=(False, -100, True, False, -1)), ('document', '54e1675aa0364f4a78fa72804ec0f413'))
 paddle.fluid.layers.smooth_l1 (ArgSpec(args=['x', 'y', 'inside_weight', 'outside_weight', 'sigma'], varargs=None, keywords=None, defaults=(None, None, None)), ('document', 'cbe8940643ac80ef75e1abdfbdb09e88'))
diff --git a/python/paddle/fluid/layers/nn.py b/python/paddle/fluid/layers/nn.py
index ae463ce449807bf78e926d197e7bda09e5f7b263..43406a551d9f1b00340719d5da664beff007ba5b 100755
--- a/python/paddle/fluid/layers/nn.py
+++ b/python/paddle/fluid/layers/nn.py
@@ -4306,30 +4306,39 @@ def group_norm(input,
 
     Refer to `Group Normalization <https://arxiv.org/abs/1803.08494>`_ .
 
-    Args:
-        input(Variable): The input tensor variable.
-        groups(int): The number of groups that divided from channels.
-        epsilon(float): The small value added to the variance to prevent
-            division by zero.
-        param_attr(ParamAttr|None): The parameter attribute for the learnable
-            scale :math:`g`. If it is set to False, no scale will be added to the output units.
-            If it is set to None, the bias is initialized one. Default: None.
-        bias_attr(ParamAttr|None): The parameter attribute for the learnable
-            bias :math:`b`. If it is set to False, no bias will be added to the output units.
-            If it is set to None, the bias is initialized zero. Default: None.
-        act(str): Activation to be applied to the output of group normalizaiton.
-        data_layout(string, default NCHW): NCHW(num_batch, channels, h, w) or NHWC(num_batch, h, w, channels).
-        name (str): The name of this layer. It is optional.
+    Parameters:
+        input(Variable): 4-D Tensor, the data type is float32 or float64.
+        groups(int): The number of groups that divided from channels, the data type
+            is int32.
+        epsilon(float, optional): The small value added to the variance to prevent
+            division by zero, the data type is float32. Default: 1e-05.
+        param_attr(ParamAttr|bool, optional): ParamAttr object that specifies weight parameter
+            attribute. If a bool type, only False is supported, which means there is no weight parameter.
+            Default: None, the default weight parameter attribute is used. For more information, please
+            refer to :ref:`api_guide_ParamAttr` .
+        bias_attr(ParamAttr|bool, optional): ParamAttr object that specifies bias parameter
+            attribute. If a bool type, only False is supported, which means there is no bias parameter.
+            Default: None, the default bias parameter attribute is used. For more information, please
+            refer to :ref:`api_guide_ParamAttr` .
+        act(str, optional): Activation to be applied to the output of group normalizaiton.
+        data_layout(str, optional): The data format of the input and output data. An optional string
+            from: `"NCHW"`, `"NHWC"`. When it is `"NCHW"`, the data is stored in the order of:
+            `[batch_size, channels, height, width]`. Default: "NCHW".
+        name (str, optional): The default value is None. Normally there is no need for user to set this
+            property. For more information, please refer to :ref:`api_guide_Name` .
 
     Returns:
-        Variable: A tensor variable which is the result after applying group normalization on the input.
+        Variable: A 4-D Tensor has same data type and data format with `input`.
+
+    Raises:
+        ValueError: If `data_layout` is neither 'NCHW' nor 'NHWC'.
 
     Examples:
+       .. code-block:: python
 
-        >>> import paddle.fluid as fluid
-        >>> data = fluid.layers.data(name='data', shape=[8, 32, 32],
-        >>>                          dtype='float32')
-        >>> x = fluid.layers.group_norm(input=data, groups=4)
+            import paddle.fluid as fluid
+            data = fluid.data(name='data', shape=[None, 8, 32, 32], dtype='float32')
+            x = fluid.layers.group_norm(input=data, groups=4)
     """
     helper = LayerHelper('group_norm', **locals())
     dtype = helper.input_dtype()