Merge pull request #11497 from tensor-tang/doc

Doc update

paddle/fluid/operators/activation_op.cc

@@ -252,15 +252,14 @@ class SoftShrinkOpMaker : public framework::OpProtoAndCheckerMaker {
     AddOutput("Out", "Output of Softshrink operator");
     AddAttr<float>("lambda", "non-negative offset").SetDefault(0.5f);
     AddComment(R"DOC(
-Softshrink Activation Operator.
+:strong:`Softshrink Activation Operator`
 
-$$
-out = \begin{cases} 
+..  math::
+    out = \begin{cases} 
          x - \lambda, \text{if } x > \lambda \\
          x + \lambda, \text{if } x < -\lambda \\
          0,  \text{otherwise}
          \end{cases}
-$$
 
 )DOC");
   }

paddle/fluid/operators/mean_op.cc

@@ -33,12 +33,10 @@ class MeanOp : public framework::OperatorWithKernel {
 class MeanOpMaker : public framework::OpProtoAndCheckerMaker {
  public:
   void Make() override {
-    AddInput("X", "The input of mean op");
-    AddOutput("Out", "The output of mean op").Reuse("X");
+    AddInput("X", "(Tensor) The input of mean op");
+    AddOutput("Out", "(Tensor) The output of mean op").Reuse("X");
     AddComment(R"DOC(
-Mean Operator.
-
-Out is a scalar which is the mean of all elements in X. 
+Mean Operator calculates the mean of all elements in X.
 
 )DOC");
   }

python/paddle/fluid/layers/io.py

@@ -541,6 +541,9 @@ def __create_unshared_decorated_reader__(op_type, reader, attrs, name=None):
 
 
 def shuffle(reader, buffer_size):
+    """
+    Shuffle the reader.
+    """
     return __create_unshared_decorated_reader__(
         'create_shuffle_reader', reader, {'buffer_size': int(buffer_size)})
 

python/paddle/fluid/layers/nn.py

@@ -225,11 +225,11 @@ def embedding(input,
             have two elements which indicate the size of the dictionary of
             embeddings and the size of each embedding vector respectively.
         is_sparse(bool): The flag indicating whether to use sparse update.
-        is_distributed (bool): Whether to run lookup table from remote parameter server.
+        is_distributed(bool): Whether to run lookup table from remote parameter server.
         padding_idx(int|long|None): If :attr:`None`, it makes no effect to lookup.
             Otherwise the given :attr:`padding_idx` indicates padding the output
             with zeros whenever lookup encounters it in :attr:`input`. If
-            :math:`padding_idx < 0`, the padding_idx to use in lookup is
+            :math:`padding_idx < 0`, the :attr:`padding_idx` to use in lookup is
             :math:`size[0] + dim`.
         param_attr(ParamAttr): Parameters for this layer
         dtype(np.dtype|core.VarDesc.VarType|str): The type of data : float32, float_16, int etc
@@ -1235,14 +1235,17 @@ def conv2d(input,
            act=None,
            name=None):
     """
-    **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
+    and strides, paddings, dilations, groups parameters. Input and
+    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/>`_ .
+    Filter is in MCHW format, where M is the number of output image channels,
+    C is the number of input image channels, H is the height of the filter,
+    and W is the width of the filter. If the groups is greater than 1,
+    C will equal the number of input image channels divided by the groups.
+    Please refer to UFLDL's `convolution
+    <http://ufldl.stanford.edu/tutorial/supervised/FeatureExtractionUsingConvolution/>`_
+    for more detials.
     If bias attribution 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.
@@ -1253,15 +1256,14 @@ def conv2d(input,
 
         Out = \sigma (W \\ast X + b)
 
-    In the above equation:
+    Where:
 
     * :math:`X`: Input value, a tensor with NCHW format.
     * :math:`W`: Filter value, a tensor with MCHW format.
     * :math:`\\ast`: Convolution operation.
     * :math:`b`: Bias value, a 2-D tensor with shape [M, 1].
     * :math:`\\sigma`: Activation function.
-    * :math:`Out`: Output value, the shape of :math:`Out` and :math:`X` may be
-                   different.
+    * :math:`Out`: Output value, the shape of :math:`Out` and :math:`X` may be different.
 
     Example:
 
@@ -1272,6 +1274,7 @@ def conv2d(input,
           Filter shape: :math:`(C_{out}, C_{in}, H_f, W_f)`
 
         - Output:
+
           Output shape: :math:`(N, C_{out}, H_{out}, W_{out})`
 
         Where
@@ -1306,7 +1309,8 @@ def conv2d(input,
         bias_attr (ParamAttr): Bias parameter for the Conv2d layer. Default: None
         use_cudnn (bool): Use cudnn kernel or not, it is valid only when the cudnn
             library is installed. Default: True
-        use_mkldnn (bool): Use mkldnn kernels or not.
+        use_mkldnn (bool): Use mkldnn kernels or not, it is valid only when compiled
+            with mkldnn library. Default: False
         act (str): Activation type. Default: None
         name (str|None): A name for this layer(optional). If set None, the layer
             will be named automatically.

python/paddle/fluid/layers/tensor.py

@@ -201,6 +201,7 @@ def assign(input, output):
 
     Examples:
         .. code-block:: python
+
           out = fluid.layers.create_tensor(dtype='float32')
           hidden = fluid.layers.fc(input=data, size=10)
           fluid.layers.assign(hidden, out)