diff --git a/paddle/operators/transpose_op.cc b/paddle/operators/transpose_op.cc
index f18be3843455e8064ab86de79f407b478fdc5a88..7b3fa8062bf6e6d05c0962fe0eef242c01b07f97 100644
--- a/paddle/operators/transpose_op.cc
+++ b/paddle/operators/transpose_op.cc
@@ -72,17 +72,29 @@ Transpose Operator.
 The input tensor will be permuted according to the axis values given.
 The op functions is similar to how numpy.transpose works in python.
 
-For example: input = numpy.arange(6).reshape((2,3))
-the input is:
-array([[0, 1, 2],
-      [3, 4, 5]])
-given axis is: [1, 0]
-
-output = input.transpose(axis)
-then the output is:
-array([[0, 3],
-       [1, 4],
-       [2, 5]])
+For example:
+
+    .. code-block:: python
+
+      input = numpy.arange(6).reshape((2,3))
+
+      the input is:
+
+      array([[0, 1, 2],
+           [3, 4, 5]])
+
+      given axis is:
+
+      [1, 0]
+
+      output = input.transpose(axis)
+
+      then the output is:
+
+      array([[0, 3],
+           [1, 4],
+           [2, 5]])
+
 So, given a input tensor of shape(N, C, H, W) and the axis is {0, 2, 3, 1},
 the output tensor shape will be (N, H, W, C)