fix doc of some sparse api (#47020)

python/paddle/incubate/sparse/binary.py

@@ -38,7 +38,7 @@ def matmul(x, y, name=None):
 
     Applies matrix multiplication of two Tensors.
 
-    The supported input/output Tensor layout are as follows:
+    The supported input/output Tensor type are as follows:
 
     Note:
         x[SparseCsrTensor] @ y[SparseCsrTensor] -> out[SparseCsrTensor]
@@ -53,12 +53,12 @@ def matmul(x, y, name=None):
     is zero or more batch dimensions.
 
     Args:
-        x (Tensor): The input tensor. It can be SparseCooTensor/SparseCsrTensor. The data type can be float32 or float64.
-        y (Tensor): The input tensor. It can be SparseCooTensor/SparseCsrTensor/DenseTensor. The data type can be float32 or float64.
+        x (SparseTensor): The input tensor. It can be SparseCooTensor/SparseCsrTensor. The data type can be float32 or float64.
+        y (SparseTensor|DenseTensor): The input tensor. It can be SparseCooTensor/SparseCsrTensor/DenseTensor. The data type can be float32 or float64.
         name (str, optional): Name for the operation (optional, default is None). For more information, please refer to :ref:`api_guide_Name`.
 
     Returns:
-        Tensor: Its layout is determined by that of `x` and `y` .
+        SparseTensor|DenseTensor: Determined by `x` and `y` .
 
     Examples:
 
@@ -121,13 +121,13 @@ def masked_matmul(x, y, mask, name=None):
     where `*` is zero or more batch dimensions.
 
     Args:
-        x (Tensor): The input tensor. It is DenseTensor. The data type can be float32 or float64.
-        y (Tensor): The input tensor. It is DenseTensor. The data type can be float32 or float64.
-        mask (Tensor): The mask tensor, which can be SparseCooTensor/SparseCsrTensor. It specify sparse coordinates. The data type can be float32 or float64.
+        x (DenseTensor): The input tensor. It is DenseTensor. The data type can be float32 or float64.
+        y (DenseTensor): The input tensor. It is DenseTensor. The data type can be float32 or float64.
+        mask (SparseTensor): The mask tensor, which can be SparseCooTensor/SparseCsrTensor. It specify sparse coordinates. The data type can be float32 or float64.
         name (str, optional): Name for the operation (optional, default is None). For more information, please refer to :ref:`api_guide_Name`.
 
     Returns:
-        Tensor: SparseCoo or SparseCsr, which is determined by that of `mask` .
+        SparseTensor: SparseCooTensor or SparseCsrTensor, which is same with `mask` .
 
     Examples:
 
@@ -171,32 +171,30 @@ def mv(x, vec, name=None):
     The supported input/output Tensor layout are as follows:
 
     Note:
-        x[SparseCsrTensor] @ y[DenseTensor] -> out[SparseCsrTensor]
-        x[SparseCooTensor] @ y[DenseTensor] -> out[SparseCooTensor]
+        x[SparseCsrTensor] @ vec[DenseTensor] -> out[DenseTensor]
+        x[SparseCooTensor] @ vec[DenseTensor] -> out[DenseTensor]
 
     It supports backward propagation.
 
-    The shape of `x` should be `[M, N]` , and the shape of `y` should be `[N]` ,
+    The shape of `x` should be `[M, N]` , and the shape of `vec` should be `[N]` ,
     and the shape of `out` will be `[M]` .
 
     Args:
-        x (Tensor): The input 2D tensor. It must be SparseCooTensor/SparseCsrTensor. The data type can be float32 or float64.
-        y (Tensor): The input 1D tensor. It must be DenseTensor vector. The data type can be float32 or float64.
+        x (SparseTensor): The input 2D tensor. It must be SparseCooTensor/SparseCsrTensor. The data type can be float32 or float64.
+        vec (DenseTensor): The input 1D tensor. It must be DenseTensor vector. The data type can be float32 or float64.
         name (str, optional): Name for the operation (optional, default is None). For more information, please refer to :ref:`api_guide_Name`.
 
     Returns:
-        Tensor: 1D Tensor.
+        DenseTensor: 1D DenseTensor whose dtype is same with input.
 
     Examples:
 
         .. code-block:: python
 
             import paddle
-            from paddle.fluid.framework import _test_eager_guard
             paddle.seed(100)
 
             # csr @ dense -> dense
-            with _test_eager_guard():
             crows = [0, 2, 3, 5]
             cols = [1, 3, 2, 0, 1]
             values = [1., 2., 3., 4., 5.]

python/paddle/incubate/sparse/multiary.py

@@ -29,7 +29,7 @@ def addmm(input, x, y, beta=1.0, alpha=1.0, name=None):
 
     ..  math::
 
-        Out = alpha * x * y + beta * input
+        out = alpha * x * y + beta * input
 
     The supported input/output Tensor layout are as follows:
 
@@ -44,15 +44,15 @@ def addmm(input, x, y, beta=1.0, alpha=1.0, name=None):
     Dimensions `input` , `x` , `y` must be same and >= 2D. Automatic broadcasting of Tensor is not supported.
 
     Args:
-        input (Tensor): The input tensor. Shape is [*, M, N]. The data type can be float32 or float64.
-        x (Tensor): The input tensor. Shape is [*, M, K]. The data type can be float32 or float64.
-        y (Tensor): The input tensor. Shape is [*, K, N]. The data type can be float32 or float64.
+        input (SparseTensor|DenseTensor): The input tensor. Shape is [*, M, N]. The data type can be float32 or float64.
+        x (SparseTensor): The input SparseTensor. Shape is [*, M, K]. The data type can be float32 or float64.
+        y (SparseTensor|DenseTensor): The input tensor. Shape is [*, K, N]. The data type can be float32 or float64.
         beta (float, optional): Coefficient of `input` . Default: 1.0
         alpha (float, optional): Coefficient of `x * y` . Default: 1.0
         name (str, optional): Name for the operation (optional, default is None). For more information, please refer to :ref:`api_guide_Name`.
 
     Returns:
-        Tensor: Its layout is determined by that of `x` and `y` . dtype and shape is the same with `input`
+        SparseTensor|DenseTensor: Tensor type, date type and shape is the same with `input` .
 
     Examples:
 

python/paddle/incubate/sparse/nn/layer/activation.py

@@ -66,8 +66,8 @@ class Softmax(Layer):
         Only support axis=-1 for SparseCsrTensor, which is faster when read data
         by row (axis=-1).
 
-    From the point of view of dense matrix, for each row :math:`i` and each column :math:`j`
-    in the matrix, we have:
+    Transform x to dense matix, and :math:`i` is row index, :math:`j` is column index.
+    If axis=-1, We have:
 
     .. math::
 
@@ -130,7 +130,7 @@ class ReLU6(Layer):
 
     .. math::
 
-        ReLU(x) = min(max(0,x), 6)
+        ReLU6(x) = min(max(0,x), 6)
 
     Parameters:
         name (str, optional): Name for the operation (optional, default is None).

python/paddle/incubate/sparse/unary.py

@@ -549,7 +549,7 @@ def coalesce(x):
 @dygraph_only
 def rad2deg(x, name=None):
     """
-    Convert each of the elements of input x from angles in radians to degrees,
+    Convert each of the elements of input x from radian to degree,
     requiring x to be a SparseCooTensor or SparseCsrTensor.
 
     .. math::
@@ -582,7 +582,7 @@ def rad2deg(x, name=None):
 @dygraph_only
 def deg2rad(x, name=None):
     """
-    Convert each of the elements of input x from degrees to angles in radians,
+    Convert each of the elements of input x from degree to radian,
     requiring x to be a SparseCooTensor or SparseCsrTensor.
 
     .. math::