Update chinese doc of layers.sums. (#1234)

* Update chinese doc of layers.sums.
test=develop
test=document_preview

* Add more examples and more detail imformation of output.
test=develop
test=document_preview

* Refine the format.
test=develop
test=document_preview

* Refine the comment in example codes.
test=develop
test=document_preview

* Refine the introduce of out.
test=develop
test=document_preview

* Refine the introduction of out.
test=develop
test=document_preview

doc/fluid/api_cn/layers_cn/sums_cn.rst

@@ -5,43 +5,50 @@ sums
 
 .. py:function:: paddle.fluid.layers.sums(input,out=None)
 
-该函数对输入进行求和，并返回求和结果作为输出。
+该OP计算多个输入Tensor逐个元素相加的和。
 
-参数：
-    - **input** (Variable|list)-输入张量，有需要求和的元素
-    - **out** (Variable|None)-输出参数。求和结果。默认：None
-
-返回：输入的求和。和参数'out'等同
-
-返回类型：变量（Variable）
-
-**代码示例**：
+- 示例：3个Tensor求和
 
 .. code-block:: python
 
-    import paddle.fluid as fluid
+  输入：
+      x0.shape = [2, 3]
+      x0.data = [[1., 2., 3.],
+                 [4., 5., 6.]]
+      x1.shape = [2, 3]
+      x1.data = [[10., 20., 30.],
+                 [40., 50., 60.]]
+      x2.shape = [2, 3]
+      x2.data = [[100., 200., 300.],
+                 [400., 500., 600.]]
 
-    # sum of several tensors
-    a0 = fluid.layers.fill_constant(shape=[1], dtype='int64', value=1)
-    a1 = fluid.layers.fill_constant(shape=[1], dtype='int64', value=2)
-    a2 = fluid.layers.fill_constant(shape=[1], dtype='int64', value=3)
-    sums = fluid.layers.sums(input=[a0, a1, a2])
+  输出：
+      out.shape = [2, 3]
+      out.data = [[111., 222., 333.],
+                  [444., 555., 666.]]
 
-    # sum of a tensor array
-    array = fluid.layers.create_array('int64')
-    i = fluid.layers.zeros(shape=[1], dtype='int64', force_cpu=True)
-    fluid.layers.array_write(a0, array=array, i=i)
-    i = fluid.layers.increment(x=i)
-    fluid.layers.array_write(a1, array=array, i=i)
-    i = fluid.layers.increment(x=i)
-    fluid.layers.array_write(a2, array=array, i=i)
-    sums = fluid.layers.sums(input=array)
 
+参数：
+    - **input** (list) - 多个维度相同的Tensor组成的元组。支持的数据类型：float32，float64，int32，int64。
+    - **out** (Variable，可选) - 指定求和的结果Tensor，可以是程序中已经创建的任何Variable。默认值为None，此时将创建新的Variable来保存输出结果。
 
+返回：输入的和，数据类型和维度与输入Tensor相同。若 ``out`` 为 ``None`` ，返回值是一个新的Variable；否则，返回值就是 ``out`` 。
 
+返回类型：Variable
 
+**代码示例**：
 
+.. code-block:: python
 
+    import paddle.fluid as fluid
 
+    x0 = fluid.layers.fill_constant(shape=[16, 32], dtype='int64', value=1)
+    x1 = fluid.layers.fill_constant(shape=[16, 32], dtype='int64', value=2)
+    x2 = fluid.layers.fill_constant(shape=[16, 32], dtype='int64', value=3)
+    x3 = fluid.layers.fill_constant(shape=[16, 32], dtype='int64', value=0)
 
+    # 多个Tensor求和，结果保存在一个新建的Variable sum0，即sum0=x0+x1+x2，值为[[6, ..., 6], ..., [6, ..., 6]]
+    sum0 = fluid.layers.sums(input=[x0, x1, x2])
 
+    # 多个Tensor求和，sum1和x3是同一个Variable，相当于x3=x0+x1+x2，值为[[6, ..., 6], ..., [6, ..., 6]]
+    sum1 = fluid.layers.sums(input=[x0, x1, x2], out=x3)