fix the api comments

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

@@ -22,15 +22,16 @@ from ....layer.basic import Dense, OneHot
 
 class ConditionalVAE(Cell):
     r"""
-    Conditional Variational auto-encoder (CVAE).
+    Conditional Variational Auto-Encoder (CVAE).
 
     The difference with VAE is that CVAE uses labels information.
-    see more details in `<http://papers.nips.cc/paper/5775-learning-structured-output-representation-using-deep-
-    conditional-generative-models>`.
+    see more details in `Learning Structured Output Representation using Deep Conditional Generative Models
+    <http://papers.nips.cc/paper/5775-learning-structured-output-representation-using-deep-conditional-
+    generative-models>`_.
 
     Note:
         When define the encoder and decoder, the shape of the encoder's output tensor and decoder's input tensor
-        should be math:`(N, hidden_size)`.
+        should be :math:`(N, hidden_size)`.
         The latent_size should be less than or equal to the hidden_size.
 
     Args:
@@ -42,7 +43,7 @@ class ConditionalVAE(Cell):
 
     Inputs:
         - **input_x** (Tensor) - the same shape as the input of encoder.
-        - **input_y** (Tensor) - the tensor of the target data, the shape is math:`(N, 1)`.
+        - **input_y** (Tensor) - the tensor of the target data, the shape is :math:`(N, 1)`.
 
     Outputs:
         - **output** (tuple) - (recon_x(Tensor), x(Tensor), mu(Tensor), std(Tensor)).
@@ -100,13 +101,13 @@ class ConditionalVAE(Cell):
         Args:
             sample_y (Tensor): Define the label of sample, int tensor.
             generate_nums (int): The number of samples to generate.
-            shape(tuple): The shape of sample, it should be math:`(generate_nums, C, H, W)` or math:`(-1, C, H, W)`.
+            shape(tuple): The shape of sample, it should be (generate_nums, C, H, W) or (-1, C, H, W).
 
         Returns:
             Tensor, the generated sample.
         """
         generate_nums = check_int_positive(generate_nums)
-        if not isinstance(shape, tuple) or len(shape) != 4 or shape[0] != generate_nums or shape[0] != -1:
+        if not isinstance(shape, tuple) or len(shape) != 4 or (shape[0] != -1 and shape[0] != generate_nums):
             raise ValueError('The shape should be (generate_nums, C, H, W) or (-1, C, H, W).')
         sample_z = self.normal((generate_nums, self.latent_size), self.to_tensor(0.0), self.to_tensor(1.0), seed=0)
         sample_y = self.one_hot(sample_y)

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

@@ -22,14 +22,14 @@ from ....layer.basic import Dense
 
 class VAE(Cell):
     r"""
-    Variational auto-encoder (VAE).
+    Variational Auto-Encoder (VAE).
 
     The VAE defines a generative model, `Z` is sampled from the prior, then used to reconstruct `X` by a decoder.
-    see more details in `Auto-Encoding Variational Bayes<https://arxiv.org/abs/1312.6114>`_.
+    see more details in `Auto-Encoding Variational Bayes <https://arxiv.org/abs/1312.6114>`_.
 
     Note:
         When define the encoder and decoder, the shape of the encoder's output tensor and decoder's input tensor
-        should be math:`(N, hidden_size)`.
+        should be :math:`(N, hidden_size)`.
         The latent_size should be less than or equal to the hidden_size.
 
     Args:
@@ -88,13 +88,13 @@ class VAE(Cell):
 
         Args:
             generate_nums (int): The number of samples to generate.
-            shape(tuple): The shape of sample, it should be math:`(generate_nums, C, H, W)` or math:`(-1, C, H, W)`.
+            shape(tuple): The shape of sample, it should be (generate_nums, C, H, W) or (-1, C, H, W).
 
         Returns:
             Tensor, the generated sample.
         """
         generate_nums = check_int_positive(generate_nums)
-        if not isinstance(shape, tuple) or len(shape) != 4 or shape[0] != generate_nums or shape[0] != -1:
+        if not isinstance(shape, tuple) or len(shape) != 4 or (shape[0] != -1 and shape[0] != generate_nums):
             raise ValueError('The shape should be (generate_nums, C, H, W) or (-1, C, H, W).')
         sample_z = self.normal((generate_nums, self.latent_size), self.to_tensor(0.0), self.to_tensor(1.0), seed=0)
         sample = self._decode(sample_z)

mindspore/nn/probability/infer/variational/elbo.py

@@ -27,7 +27,7 @@ class ELBO(Cell):
     the posterior distribution. It maximizes the evidence lower bound (ELBO), a lower bound on the logarithm of
     the marginal probability of the observations log p(x). The ELBO is equal to the negative KL divergence up to
     an additive constant.
-    see more details in `Variational Inference: A Review for Statisticians<https://arxiv.org/abs/1601.00670>`_.
+    see more details in `Variational Inference: A Review for Statisticians <https://arxiv.org/abs/1601.00670>`_.
 
     Args:
         latent_prior(str): The prior distribution of latent space. Default: Normal.

mindspore/nn/probability/infer/variational/svi.py

@@ -28,7 +28,7 @@ class SVI:
     Variational inference casts the inference problem as an optimization. Some distributions over the hidden
     variables that is indexed by a set of free parameters, and then optimize the parameters to make it closest to
     the posterior of interest.
-    see more details in `Variational Inference: A Review for Statisticians<https://arxiv.org/abs/1601.00670>`_.
+    see more details in `Variational Inference: A Review for Statisticians <https://arxiv.org/abs/1601.00670>`_.
 
     Args:
         net_with_loss(Cell): Cell with loss function.

mindspore/nn/probability/toolbox/uncertainty_evaluation.py

@@ -219,7 +219,7 @@ class EpistemicUncertaintyModel(Cell):
     after Dense layer or Conv layer, then use dropout during train and eval time.
 
     See more details in `Dropout as a Bayesian Approximation: Representing Model uncertainty in Deep Learning
-    <https://arxiv.org/abs/1506.02142>`.
+    <https://arxiv.org/abs/1506.02142>`_.
     """
 
     def __init__(self, epi_model):
@@ -257,7 +257,7 @@ class AleatoricUncertaintyModel(Cell):
     uncertainty, the loss function should be modified in order to add variance into loss.
 
     See more details in `What Uncertainties Do We Need in Bayesian Deep Learning for Computer Vision?
-    <https://arxiv.org/abs/1703.04977>`.
+    <https://arxiv.org/abs/1703.04977>`_.
     """
 
     def __init__(self, ale_model, num_classes, task):