modify comments of API in mdp

mindspore/nn/probability/bijector/power_transform.py

@@ -41,8 +41,7 @@ class PowerTransform(Bijector):
         name (str): The name of the bijector. Default: 'PowerTransform'.
         param (dict): The parameters used to initialize the bijector. These parameters are only used when other
             Bijectors inherit from powertransform to pass in parameters. In this case the derived Bijector may overwrite
-            the argument `param`.
-          Default: None.
+            the argument `param`. Default: None.
 
     Examples:
         >>> # To initialize a PowerTransform bijector of power 0.5.

mindspore/nn/probability/dpn/vae/cvae.py

@@ -42,8 +42,9 @@ class ConditionalVAE(Cell):
         num_classes(int): The number of classes.
 
     Inputs:
-        - **input_x** (Tensor) - The input tensor is the same shape as the input of encoder, with the shape
-        being :math:`(N, C, H, W)`.
+        - **input_x** (Tensor) - The shape of input tensor is :math:`(N, C, H, W)`, which is the same as the input of
+        encoder.
+
         - **input_y** (Tensor) - The tensor of the target data, the shape is :math:`(N,)`.
 
     Outputs:

mindspore/nn/probability/dpn/vae/vae.py

@@ -39,8 +39,8 @@ class VAE(Cell):
         latent_size(int): The size of the latent space.
 
     Inputs:
-        - **input** (Tensor) - The input tensor is the same shape as the input of encoder, the shape
-        is :math:`(N, C, H, W)`.
+        - **input** (Tensor) - The shape of input tensor is :math:`(N, C, H, W)`, which is the same as the input of
+        encoder.
 
     Outputs:
         - **output** (Tuple) - (recon_x(Tensor), x(Tensor), mu(Tensor), std(Tensor)).