diff --git a/mindspore/nn/optim/lazyadam.py b/mindspore/nn/optim/lazyadam.py
index 9da6095974..9175f4f6ba 100644
--- a/mindspore/nn/optim/lazyadam.py
+++ b/mindspore/nn/optim/lazyadam.py
@@ -172,7 +172,7 @@ class LazyAdam(Optimizer):
             If false, the result is unpredictable. Default: False.
         use_nesterov (bool): Whether to use Nesterov Accelerated Gradient (NAG) algorithm to update the gradients.
             If true, update the gradients using NAG.
-            If true, update the gradients without using NAG. Default: False.
+            If false, update the gradients without using NAG. Default: False.
         weight_decay (float): Weight decay (L2 penalty). Default: 0.0.
         loss_scale (float): A floating point value for the loss scale. Should be equal to or greater than 1. Default:
                             1.0.
diff --git a/mindspore/ops/operations/math_ops.py b/mindspore/ops/operations/math_ops.py
index 8c6fa02d9b..96b4317675 100644
--- a/mindspore/ops/operations/math_ops.py
+++ b/mindspore/ops/operations/math_ops.py
@@ -1772,7 +1772,7 @@ class Erfc(PrimitiveWithInfer):
         >>> input_x = Tensor(np.array([-1, 0, 1, 2, 3]), mindspore.float32)
         >>> erfc = P.Erfc()
         >>> erfc(input_x)
-        [1.8427168, 0., 0.1572832, 0.00469124, 0.00002235]
+        [1.8427168, 1.0, 0.1572832, 0.00469124, 0.00002235]
     """
 
     @prim_attr_register
@@ -2895,6 +2895,8 @@ class FloatStatus(PrimitiveWithInfer):
         >>> float_status = P.FloatStatus()
         >>> input_x = Tensor(np.array([np.log(-1), 1, np.log(0)]), mindspore.float32)
         >>> result = float_status(input_x)
+        >>> print(result)
+        [1.]
     """
 
     @prim_attr_register
diff --git a/mindspore/ops/operations/nn_ops.py b/mindspore/ops/operations/nn_ops.py
index cb2e821a76..7960e6a628 100644
--- a/mindspore/ops/operations/nn_ops.py
+++ b/mindspore/ops/operations/nn_ops.py
@@ -90,7 +90,8 @@ class Flatten(PrimitiveWithInfer):
         >>> input_tensor = Tensor(np.ones(shape=[1, 2, 3, 4]), mindspore.float32)
         >>> flatten = P.Flatten()
         >>> output = flatten(input_tensor)
-        >>> assert output.shape == (1, 24)
+        >>> print(output.shape)
+        (1, 24)
     """
 
     @prim_attr_register
@@ -700,7 +701,7 @@ class FusedBatchNormEx(PrimitiveWithInfer):
     Outputs:
         Tuple of 6 Tensors, the normalized input, the updated parameters and reserve.
 
-        - **output_x** (Tensor) - The input of FusedBatchNormEx, same type and shape as the `input_x`.
+        - **output_x** (Tensor) - The output of FusedBatchNormEx, same type and shape as the `input_x`.
         - **updated_scale** (Tensor) - Updated parameter scale, Tensor of shape :math:`(C,)`, data type: float32.
         - **updated_bias** (Tensor) - Updated parameter bias, Tensor of shape :math:`(C,)`, data type: float32.
         - **updated_moving_mean** (Tensor) - Updated mean value, Tensor of shape :math:`(C,)`, data type: float32.
@@ -3206,7 +3207,7 @@ class Adam(PrimitiveWithInfer):
             If false, the result is unpredictable. Default: False.
         use_nesterov (bool): Whether to use Nesterov Accelerated Gradient (NAG) algorithm to update the gradients.
             If true, update the gradients using NAG.
-            If true, update the gradients without using NAG. Default: False.
+            If false, update the gradients without using NAG. Default: False.
 
     Inputs:
         - **var** (Tensor) - Weights to be updated.
@@ -3306,7 +3307,7 @@ class FusedSparseAdam(PrimitiveWithInfer):
             If false, the result is unpredictable. Default: False.
         use_nesterov (bool): Whether to use Nesterov Accelerated Gradient (NAG) algorithm to update the gradients.
             If true, update the gradients using NAG.
-            If true, update the gradients without using NAG. Default: False.
+            If false, update the gradients without using NAG. Default: False.
 
     Inputs:
         - **var** (Parameter) - Parameters to be updated with float32 data type.
@@ -3439,7 +3440,7 @@ class FusedSparseLazyAdam(PrimitiveWithInfer):
             If false, the result is unpredictable. Default: False.
         use_nesterov (bool): Whether to use Nesterov Accelerated Gradient (NAG) algorithm to update the gradients.
             If true, update the gradients using NAG.
-            If true, update the gradients without using NAG. Default: False.
+            If false, update the gradients without using NAG. Default: False.
 
     Inputs:
         - **var** (Parameter) - Parameters to be updated with float32 data type.