refine doc for prelu (#17810)

* refine doc for prelu

paddle/fluid/API.spec

@@ -170,7 +170,7 @@ paddle.fluid.layers.pow (ArgSpec(args=['x', 'factor', 'name'], varargs=None, key
 paddle.fluid.layers.stanh (ArgSpec(args=['x', 'scale_a', 'scale_b', 'name'], varargs=None, keywords=None, defaults=(0.6666666666666666, 1.7159, None)), ('document', '959936a477efc6c1447a9c8bf8ce94bb'))
 paddle.fluid.layers.hard_sigmoid (ArgSpec(args=['x', 'slope', 'offset', 'name'], varargs=None, keywords=None, defaults=(0.2, 0.5, None)), ('document', '607d79ca873bee40eed1c79a96611591'))
 paddle.fluid.layers.swish (ArgSpec(args=['x', 'beta', 'name'], varargs=None, keywords=None, defaults=(1.0, None)), ('document', 'ef745e55a48763ee7b46b21a81dc7e84'))
-paddle.fluid.layers.prelu (ArgSpec(args=['x', 'mode', 'param_attr', 'name'], varargs=None, keywords=None, defaults=(None, None)), ('document', 'f6acef7ff7d887e49ff499fbb1dad4a9'))
+paddle.fluid.layers.prelu (ArgSpec(args=['x', 'mode', 'param_attr', 'name'], varargs=None, keywords=None, defaults=(None, None)), ('document', '2da40e447716338affebfe058d05d9a9'))
 paddle.fluid.layers.brelu (ArgSpec(args=['x', 't_min', 't_max', 'name'], varargs=None, keywords=None, defaults=(0.0, 24.0, None)), ('document', '3db337c195e156e6ef2b8b4a57113600'))
 paddle.fluid.layers.leaky_relu (ArgSpec(args=['x', 'alpha', 'name'], varargs=None, keywords=None, defaults=(0.02, None)), ('document', 'f878486c82b576938151daad0de995a0'))
 paddle.fluid.layers.soft_relu (ArgSpec(args=['x', 'threshold', 'name'], varargs=None, keywords=None, defaults=(40.0, None)), ('document', '3490ed5c9835ae039a82979daf3918a4'))

python/paddle/fluid/layers/nn.py

@@ -8830,14 +8830,19 @@ def prelu(x, mode, param_attr=None, name=None):
     .. math::
         y = \max(0, x) + \\alpha * \min(0, x)
 
+    There are three modes for the activation:
+
+    .. code-block:: text
+
+        all: All elements share same alpha.
+        channel: Elements in same channel share same alpha.
+        element: All elements do not share alpha. Each element has its own alpha.
+
     Args:
         x (Variable): The input tensor.
+        mode (string): The mode for weight sharing. 
         param_attr(ParamAttr|None): The parameter attribute for the learnable
-          weight (alpha).
-        mode (string): The mode for weight sharing. It supports all, channel
-          and element. all: all elements share same weight
-          channel:elements in a channel share same weight
-          element:each element has a weight
+          weight (alpha), it can be create by ParamAttr.
         name(str|None): A name for this layer(optional). If set None, the layer
           will be named automatically.
 
@@ -8848,9 +8853,13 @@ def prelu(x, mode, param_attr=None, name=None):
 
         .. code-block:: python
 
-            x = fluid.layers.data(name="x", shape=[10,10], dtype="float32")
+            import paddle.fluid as fluid
+            from paddle.fluid.param_attr import ParamAttr
+            x = fluid.layers.data(name="x", shape=[5,10,10], dtype="float32")
             mode = 'channel'
-            output = fluid.layers.prelu(x,mode)
+            output = fluid.layers.prelu(
+                     x,mode,param_attr=ParamAttr(name='alpha'))
+
     """
     helper = LayerHelper('prelu', **locals())
     if mode not in ['all', 'channel', 'element']: