diff --git a/mindspore/nn/optim/adam.py b/mindspore/nn/optim/adam.py
index 7fd1b0270ae..cb3425a046c 100755
--- a/mindspore/nn/optim/adam.py
+++ b/mindspore/nn/optim/adam.py
@@ -220,7 +220,7 @@ class Adam(Optimizer):
         >>> group_params = [{'params': conv_params, 'weight_decay': 0.01},
         >>>                 {'params': no_conv_params, 'lr': 0.01},
         >>>                 {'order_params': net.trainable_params()}]
-        >>> optm = nn.Adam(group_params, learning_rate=0.1, weight_decay=0.0)
+        >>> optim = nn.Adam(group_params, learning_rate=0.1, weight_decay=0.0)
         >>> # The conv_params's parameters will use default learning rate of 0.1 and weight decay of 0.01.
         >>> # The no_conv_params's parameters will use learning rate of 0.01 and defaule weight decay of 0.0.
         >>> # The final parameters order in which the optimizer will be followed is the value of 'order_params'.
diff --git a/mindspore/nn/optim/lazyadam.py b/mindspore/nn/optim/lazyadam.py
index a39160d2e9d..30d2992a8f4 100644
--- a/mindspore/nn/optim/lazyadam.py
+++ b/mindspore/nn/optim/lazyadam.py
@@ -168,7 +168,7 @@ class LazyAdam(Optimizer):
         >>> group_params = [{'params': conv_params, 'weight_decay': 0.01},
         >>>                 {'params': no_conv_params, 'lr': 0.01},
         >>>                 {'order_params': net.trainable_params()}]
-        >>> opt = nn.LazyAdam(group_params, learning_rate=0.1, weight_decay=0.0)
+        >>> optim = nn.LazyAdam(group_params, learning_rate=0.1, weight_decay=0.0)
         >>> # The conv_params's parameters will use default learning rate of 0.1 and weight decay of 0.01.
         >>> # The no_conv_params's parameters will use learning rate of 0.01 and default weight decay of 0.0.
         >>> # The final parameters order in which the optimizer will be followed is the value of 'order_params'.
diff --git a/mindspore/ops/operations/array_ops.py b/mindspore/ops/operations/array_ops.py
index fff51ef309c..ca3da86128b 100644
--- a/mindspore/ops/operations/array_ops.py
+++ b/mindspore/ops/operations/array_ops.py
@@ -3013,12 +3013,12 @@ class DepthToSpace(PrimitiveWithInfer):
 
     This is the reverse operation of SpaceToDepth.
 
+    The depth of output tensor is :math:`input\_depth / (block\_size * block\_size)`.
+
     The output tensor's `height` dimension is :math:`height * block\_size`.
 
     The output tensor's `weight` dimension is :math:`weight * block\_size`.
 
-    The depth of output tensor is :math:`input\_depth / (block\_size * block\_size)`.
-
     The input tensor's depth must be divisible by `block_size * block_size`.
     The data format is "NCHW".
 
@@ -3029,7 +3029,7 @@ class DepthToSpace(PrimitiveWithInfer):
         - **x** (Tensor) - The target tensor. It must be a 4-D tensor.
 
     Outputs:
-        Tensor, the same type as `x`.
+        Tensor, has the same shape and dtype as the 'x'.
 
     Examples:
         >>> x = Tensor(np.random.rand(1,12,1,1), mindspore.float32)
diff --git a/mindspore/ops/operations/math_ops.py b/mindspore/ops/operations/math_ops.py
index babb511385c..b76e6292a7e 100644
--- a/mindspore/ops/operations/math_ops.py
+++ b/mindspore/ops/operations/math_ops.py
@@ -741,6 +741,7 @@ class CumSum(PrimitiveWithInfer):
     Inputs:
         - **input** (Tensor) - The input tensor to accumulate.
         - **axis**  (int) - The axis to accumulate the tensor's value. Only constant value is allowed.
+          Must be in the range [-rank(input), rank(input)).
 
     Outputs:
         Tensor, the shape of the output tensor is consistent with the input tensor's.
@@ -1764,6 +1765,7 @@ class Div(_MathBinaryOp):
         >>> input_y = Tensor(np.array([3.0, 2.0, 3.0]), mindspore.float32)
         >>> div = P.Div()
         >>> div(input_x, input_y)
+        [-1.3, 2.5, 2.0]
     """
 
     def infer_value(self, x, y):