diff --git a/python/paddle/incubate/optimizer/functional/bfgs.py b/python/paddle/incubate/optimizer/functional/bfgs.py
index 9d98460e03c3ca8b06ef7fc4518c96ca9b112556..bc244d9c19da1a7f3658be9431d5c41a3afc63b5 100644
--- a/python/paddle/incubate/optimizer/functional/bfgs.py
+++ b/python/paddle/incubate/optimizer/functional/bfgs.py
@@ -81,46 +81,46 @@ def minimize_bfgs(
         .. code-block:: python
             :name: code-example1
 
-            # Example1: 1D Grid Parameters
-            import paddle
-            # Randomly simulate a batch of input data
-            inputs = paddle. normal(shape=(100, 1))
-            labels = inputs * 2.0
-            # define the loss function
-            def loss(w):
-                y = w * inputs
-                return paddle.nn.functional.square_error_cost(y, labels).mean()
-            # Initialize weight parameters
-            w = paddle.normal(shape=(1,))
-            # Call the bfgs method to solve the weight that makes the loss the smallest, and update the parameters
-            for epoch in range(0, 10):
-                # Call the bfgs method to optimize the loss, note that the third parameter returned represents the weight
-                w_update = paddle.incubate.optimizer.functional.minimize_bfgs(loss, w)[2]
-                # Use paddle.assign to update parameters in place
-                paddle. assign(w_update, w)
+            >>> # Example1: 1D Grid Parameters
+            >>> import paddle
+            >>> # Randomly simulate a batch of input data
+            >>> inputs = paddle. normal(shape=(100, 1))
+            >>> labels = inputs * 2.0
+            >>> # define the loss function
+            >>> def loss(w):
+            ...     y = w * inputs
+            ...     return paddle.nn.functional.square_error_cost(y, labels).mean()
+            >>> # Initialize weight parameters
+            >>> w = paddle.normal(shape=(1,))
+            >>> # Call the bfgs method to solve the weight that makes the loss the smallest, and update the parameters
+            >>> for epoch in range(0, 10):
+            ...     # Call the bfgs method to optimize the loss, note that the third parameter returned represents the weight
+            ...     w_update = paddle.incubate.optimizer.functional.minimize_bfgs(loss, w)[2]
+            ...     # Use paddle.assign to update parameters in place
+            ...     paddle. assign(w_update, w)
 
         .. code-block:: python
             :name: code-example2
 
-            # Example2: Multidimensional Grid Parameters
-            import paddle
-            def flatten(x):
-                return x. flatten()
-            def unflatten(x):
-                return x.reshape((2,2))
-            # Assume the network parameters are more than one dimension
-            def net(x):
-                assert len(x.shape) > 1
-                return x.square().mean()
-            # function to be optimized
-            def bfgs_f(flatten_x):
-                return net(unflatten(flatten_x))
-            x = paddle.rand([2,2])
-            for i in range(0, 10):
-                # Flatten x before using minimize_bfgs
-                x_update = paddle.incubate.optimizer.functional.minimize_bfgs(bfgs_f, flatten(x))[2]
-                # unflatten x_update, then update parameters
-                paddle. assign(unflatten(x_update), x)
+            >>> # Example2: Multidimensional Grid Parameters
+            >>> import paddle
+            >>> def flatten(x):
+            ...     return x. flatten()
+            >>> def unflatten(x):
+            ...     return x.reshape((2,2))
+            >>> # Assume the network parameters are more than one dimension
+            >>> def net(x):
+            ...     assert len(x.shape) > 1
+            ...     return x.square().mean()
+            >>> # function to be optimized
+            >>> def bfgs_f(flatten_x):
+            ...     return net(unflatten(flatten_x))
+            >>> x = paddle.rand([2,2])
+            >>> for i in range(0, 10):
+            ...     # Flatten x before using minimize_bfgs
+            ...     x_update = paddle.incubate.optimizer.functional.minimize_bfgs(bfgs_f, flatten(x))[2]
+            ...     # unflatten x_update, then update parameters
+            ...     paddle.assign(unflatten(x_update), x)
     """
 
     if dtype not in ['float32', 'float64']:
diff --git a/python/paddle/incubate/optimizer/functional/lbfgs.py b/python/paddle/incubate/optimizer/functional/lbfgs.py
index af30efe44a8daa733b249a5505708cdea6bcce45..fc482e4ca18b5db9e4e492cad220746527b89271 100644
--- a/python/paddle/incubate/optimizer/functional/lbfgs.py
+++ b/python/paddle/incubate/optimizer/functional/lbfgs.py
@@ -82,46 +82,46 @@ def minimize_lbfgs(
         .. code-block:: python
             :name: code-example1
 
-            # Example1: 1D Grid Parameters
-            import paddle
-            # Randomly simulate a batch of input data
-            inputs = paddle. normal(shape=(100, 1))
-            labels = inputs * 2.0
-            # define the loss function
-            def loss(w):
-                y = w * inputs
-                return paddle.nn.functional.square_error_cost(y, labels).mean()
-            # Initialize weight parameters
-            w = paddle.normal(shape=(1,))
-            # Call the bfgs method to solve the weight that makes the loss the smallest, and update the parameters
-            for epoch in range(0, 10):
-                # Call the bfgs method to optimize the loss, note that the third parameter returned represents the weight
-                w_update = paddle.incubate.optimizer.functional.minimize_bfgs(loss, w)[2]
-                # Use paddle.assign to update parameters in place
-                paddle. assign(w_update, w)
+            >>> # Example1: 1D Grid Parameters
+            >>> import paddle
+            >>> # Randomly simulate a batch of input data
+            >>> inputs = paddle. normal(shape=(100, 1))
+            >>> labels = inputs * 2.0
+            >>> # define the loss function
+            >>> def loss(w):
+            ...     y = w * inputs
+            ...     return paddle.nn.functional.square_error_cost(y, labels).mean()
+            >>> # Initialize weight parameters
+            >>> w = paddle.normal(shape=(1,))
+            >>> # Call the bfgs method to solve the weight that makes the loss the smallest, and update the parameters
+            >>> for epoch in range(0, 10):
+            ...     # Call the bfgs method to optimize the loss, note that the third parameter returned represents the weight
+            ...     w_update = paddle.incubate.optimizer.functional.minimize_bfgs(loss, w)[2]
+            ...     # Use paddle.assign to update parameters in place
+            ...     paddle.assign(w_update, w)
 
         .. code-block:: python
             :name: code-example2
 
-            # Example2: Multidimensional Grid Parameters
-            import paddle
-            def flatten(x):
-                return x. flatten()
-            def unflatten(x):
-                return x.reshape((2,2))
-            # Assume the network parameters are more than one dimension
-            def net(x):
-                assert len(x.shape) > 1
-                return x.square().mean()
-            # function to be optimized
-            def bfgs_f(flatten_x):
-                return net(unflatten(flatten_x))
-            x = paddle.rand([2,2])
-            for i in range(0, 10):
-                # Flatten x before using minimize_bfgs
-                x_update = paddle.incubate.optimizer.functional.minimize_bfgs(bfgs_f, flatten(x))[2]
-                # unflatten x_update, then update parameters
-                paddle. assign(unflatten(x_update), x)
+            >>> # Example2: Multidimensional Grid Parameters
+            >>> import paddle
+            >>> def flatten(x):
+            ...     return x. flatten()
+            >>> def unflatten(x):
+            ...     return x.reshape((2,2))
+            >>> # Assume the network parameters are more than one dimension
+            >>> def net(x):
+            ...     assert len(x.shape) > 1
+            ...     return x.square().mean()
+            >>> # function to be optimized
+            >>> def bfgs_f(flatten_x):
+            ...     return net(unflatten(flatten_x))
+            >>> x = paddle.rand([2,2])
+            >>> for i in range(0, 10):
+            ...     # Flatten x before using minimize_bfgs
+            ...     x_update = paddle.incubate.optimizer.functional.minimize_bfgs(bfgs_f, flatten(x))[2]
+            ...     # unflatten x_update, then update parameters
+            ...     paddle.assign(unflatten(x_update), x)
 
     """
     if dtype not in ['float32', 'float64']:
diff --git a/python/paddle/incubate/passes/ir.py b/python/paddle/incubate/passes/ir.py
index 0e292e51a0aeafe62a2e38478a617d07c56f42e7..c657f20abcb99524b6673c13d077ce7abc8c583d 100644
--- a/python/paddle/incubate/passes/ir.py
+++ b/python/paddle/incubate/passes/ir.py
@@ -469,16 +469,16 @@ def RegisterPass(function=None, input_specs={}):
     Examples:
         .. code-block:: python
 
-        import paddle
-        from paddle.fluid.ir import RegisterPass
-
-        @RegisterPass
-        def multi_add_to_addn():
-            def pattern(x, y, z):
-                return paddle.add(paddle.add(x, y), z)
-            def replace(x, y, z):
-                return paddle.add_n([x, y, z])
-            return pattern, replace
+            >>> import paddle
+            >>> from paddle.fluid.ir import RegisterPass
+
+            >>> @RegisterPass
+            >>> def multi_add_to_addn():
+            ...    def pattern(x, y, z):
+            ...        return paddle.add(paddle.add(x, y), z)
+            ...    def replace(x, y, z):
+            ...        return paddle.add_n([x, y, z])
+            ...    return pattern, replace
     """
 
     def _is_pass_pair(check_pair):