add conv2d_python doc

python/paddle/v2/fluid/layers/nn.py

@@ -481,11 +481,67 @@ def conv2d(input,
            act=None,
            name=None):
     """
-    This function creates the op for a 2-dimensional Convolution.
-    This is performed using the parameters of filters(size, dimensionality etc)
-    , stride and other configurations for a Convolution operation.
-    This funciton can also append an activation on top of the
-    conv-2d output, if mentioned in the input parameters.
+    **Convlution2D Layer**
+
+    The convolution2D layer calculates the output based on the input, filter
+    and strides, paddings, dilations, groups parameters. Input(Input) and Output(Output)
+    are in NCHW format. Where N is batch size, C is the number of channels, H is the height
+    of the feature, and W is the width of the feature.
+    The details of convolution layer, please refer UFLDL's `convolution,
+    <http://ufldl.stanford.edu/tutorial/supervised/FeatureExtractionUsingConvolution/>`_ .
+    If bias_attr and activation type are provided, bias is added to the output of the convolution,
+    and the corresponding activation function is applied to the final result.
+    For each input :math:`X`, the equation is:
+
+    .. math::
+
+        Out = \sigma (W\ast X + b)
+
+    In the above equation:
+
+        * :math:`X`: Input value, a tensor with NCHW format.
+        * :math:`W`: Filter value, a tensor with MCHW format.
+        * :math:`b`: Bias, .
+        * :math:\sigma : Activation function.
+        * :math:`Out`: Output value, the shape of :math:`Out` and :math:`X` may be different.
+
+    Example:
+
+        Input:
+           Input shape: $(N, C_{in}, H_{in}, W_{in})$
+           Filter shape: $(C_{out}, C_{in}, H_f, W_f)$
+        Output:
+           Output shape: $(N, C_{out}, H_{out}, W_{out})$
+        Where
+        $$
+           H_{out}= \\frac{(H_{in} + 2 * paddings[0] - (dilations[0] * (H_f - 1) + 1))}{strides[0]}+ 1 \\
+           W_{out}= \\frac{(W_{in} + 2 * paddings[1] - (dilations[1] * (W_f - 1) + 1))}{strides[1]}+ 1
+        $$
+
+    All the input variables are passed in as local variables to the LayerHelper
+    constructor.
+
+    Args:
+       input(Variable): Input tensors. The format of input tensor is NCHW.
+       num_filters(int): Number of filters
+       filter_size(list/int): Filter size of Conv2d Layer
+       stride(list/int, optional): Strides(h_s, w_s) of Conv2d Layer. Default: 1
+       padding(list/int, optional): Paddings(h_pad, w_pad) of Conv2d Layer. Default: 0
+       groups(int, optional): The groups number of the Conv2d Layer. Default: 1
+       param_attr(ParamAttr): The parameters to the Conv2d Layer. Default: None
+       bias_attr(ParamAttr): Bias parameter for the Conv2d layer. Default: None
+       act(str): Activation type. Default: None
+       name(str): Name/alias of the function
+
+    Returns:
+        Variable: The tensor variable storing the convolution and \
+                  non-linearity activation result.
+
+    Examples:
+        .. code-block:: python
+
+          data = fluid.layers.data(name='data', shape=[3,32, 32], dtype='float32')
+          conv2d = fluid.layers.conv2d(input=data, num_filters=2, filter_size=3, act="relu")
     """
 
     if stride is None: