diff --git a/mindspore/nn/layer/normalization.py b/mindspore/nn/layer/normalization.py
index f8a914967e..9971a6cf5d 100644
--- a/mindspore/nn/layer/normalization.py
+++ b/mindspore/nn/layer/normalization.py
@@ -365,10 +365,16 @@ class BatchNorm2d(_BatchNorm):
             The values of str refer to the function `initializer` including 'zeros', 'ones', etc. Default: 'zeros'.
         moving_var_init (Union[Tensor, str, Initializer, numbers.Number]): Initializer for the moving variance.
             The values of str refer to the function `initializer` including 'zeros', 'ones', etc. Default: 'ones'.
-        use_batch_statistics (bool): If true, use the mean value and variance value of current batch data. If false,
-            use the mean value and variance value of specified value. If None, the training process will use the mean
-            and variance of current batch data and track the running mean and variance, the evaluation process will use
-            the running mean and variance. Default: None.
+        use_batch_statistics (bool):
+
+            - If true, use the mean value and variance value of current batch data and track running mean
+              and running varance.
+            - If false, use the mean value and variance value of specified value, and not track statistical value.
+            - If None, The use_batch_statistics is automatically assigned process according to
+              the training and eval mode. During training, batchnorm2d process will be the same
+              with use_batch_statistics=True. Contrarily, in eval, batchnorm2d process will be the same
+              with use_batch_statistics=False.
+
         data_format (str): The optional value for data format, is 'NHWC' or 'NCHW'.
             Default: 'NCHW'.
 
diff --git a/mindspore/nn/sparse/sparse.py b/mindspore/nn/sparse/sparse.py
index ce50905cf8..d6cad5d56f 100644
--- a/mindspore/nn/sparse/sparse.py
+++ b/mindspore/nn/sparse/sparse.py
@@ -29,20 +29,23 @@ class SparseToDense(Cell):
     Returns:
         Tensor, the tensor converted.
 
+    Supported Platforms:
+        ``CPU``
+
     Examples:
-        >>> class SparseToDenseCell(nn.Cell):
-        ...     def __init__(self, dense_shape):
-        ...         super(SparseToDenseCell, self).__init__()
-        ...         self.dense_shape = dense_shape
-        ...         self.sparse_to_dense = nn.SparseToDense()
-        ...     def construct(self, indices, values):
-        ...         sparse = SparseTensor(indices, values, self.dense_shape)
-        ...         return self.sparse_to_dense(sparse)
-        ...
+        >>> import mindspore as ms
+        >>> from mindspore import Tensor, SparseTensor
+        >>> import mindspore.nn as nn
         >>> indices = Tensor([[0, 1], [1, 2]])
-        >>> values = Tensor([1, 2], dtype=ms.float32)
+        >>> values = Tensor([1, 2], dtype=ms.int32)
         >>> dense_shape = (3, 4)
-        >>> SparseToDenseCell(dense_shape)(indices, values)
+        >>> sparse_tensor = SparseTensor(indices, values, dense_shape)
+        >>> sparse_to_dense = nn.SparseToDense()
+        >>> result = sparse_to_dense(sparse_tensor)
+        >>> print(result)
+        [[0 1 0 0]
+         [0 0 2 0]
+         [0 0 0 0]]
     """
     def __init__(self):
         super(SparseToDense, self).__init__()