diff --git a/mindspore/nn/probability/bijector/bijector.py b/mindspore/nn/probability/bijector/bijector.py
index c29e06445b..7d11f3e106 100644
--- a/mindspore/nn/probability/bijector/bijector.py
+++ b/mindspore/nn/probability/bijector/bijector.py
@@ -164,6 +164,8 @@ class Bijector(Cell):
                 self.common_dtype = value_t.dtype
             elif value_t.dtype != self.common_dtype:
                 raise TypeError(f"{name} should have the same dtype as other arguments.")
+            # check if the parameters are casted into float-type tensors
+            validator.check_type_name("dtype", value_t.dtype, mstype.float_type, type(self).__name__)
         # check if the dtype of the input_parameter agrees with the bijector's dtype
         elif value_t.dtype != self.dtype:
             raise TypeError(f"{name} should have the same dtype as the bijector's dtype.")
diff --git a/mindspore/nn/probability/bijector/power_transform.py b/mindspore/nn/probability/bijector/power_transform.py
index 5603213419..024f918be3 100644
--- a/mindspore/nn/probability/bijector/power_transform.py
+++ b/mindspore/nn/probability/bijector/power_transform.py
@@ -61,7 +61,7 @@ class PowerTransform(Bijector):
     """
 
     def __init__(self,
-                 power=0,
+                 power=0.,
                  name='PowerTransform'):
         param = dict(locals())
         param['param_dict'] = {'power': power}
diff --git a/mindspore/nn/probability/distribution/_utils/utils.py b/mindspore/nn/probability/distribution/_utils/utils.py
index be6b506624..1336e9fd1d 100644
--- a/mindspore/nn/probability/distribution/_utils/utils.py
+++ b/mindspore/nn/probability/distribution/_utils/utils.py
@@ -159,6 +159,15 @@ def check_prob(p):
         raise ValueError('Probabilities should be less than one')
 
 def check_sum_equal_one(probs):
+    """
+    Used in categorical distribution. check if probabilities of each category sum to 1.
+    """
+    if probs is None:
+        raise ValueError(f'input value cannot be None in check_sum_equal_one')
+    if isinstance(probs, Parameter):
+        if not isinstance(probs.data, Tensor):
+            return
+        probs = probs.data
     prob_sum = np.sum(probs.asnumpy(), axis=-1)
     comp = np.equal(np.ones(prob_sum.shape), prob_sum)
     if not comp.all():
@@ -168,6 +177,12 @@ def check_rank(probs):
     """
     Used in categorical distribution. check Rank >=1.
     """
+    if probs is None:
+        raise ValueError(f'input value cannot be None in check_rank')
+    if isinstance(probs, Parameter):
+        if not isinstance(probs.data, Tensor):
+            return
+        probs = probs.data
     if probs.asnumpy().ndim == 0:
         raise ValueError('probs for Categorical distribution must have rank >= 1.')
 
diff --git a/mindspore/nn/probability/distribution/bernoulli.py b/mindspore/nn/probability/distribution/bernoulli.py
index c97ea84d83..c851609021 100644
--- a/mindspore/nn/probability/distribution/bernoulli.py
+++ b/mindspore/nn/probability/distribution/bernoulli.py
@@ -44,7 +44,7 @@ class Bernoulli(Distribution):
         >>> # The following creates two independent Bernoulli distributions.
         >>> b = msd.Bernoulli([0.5, 0.5], dtype=mstype.int32)
         >>>
-        >>> # A Bernoulli distribution can be initilized without arguments.
+        >>> # A Bernoulli distribution can be initialized without arguments.
         >>> # In this case, `probs` must be passed in through arguments during function calls.
         >>> b = msd.Bernoulli(dtype=mstype.int32)
         >>>
@@ -106,7 +106,6 @@ class Bernoulli(Distribution):
         ...         ans = self.b1.sample((2,3))
         ...         ans = self.b1.sample((2,3), probs_b)
         ...         ans = self.b2.sample((2,3), probs_a)
-        ...
     """
 
     def __init__(self,
diff --git a/mindspore/nn/probability/distribution/categorical.py b/mindspore/nn/probability/distribution/categorical.py
index ce451f16ce..40ac3b7ef2 100644
--- a/mindspore/nn/probability/distribution/categorical.py
+++ b/mindspore/nn/probability/distribution/categorical.py
@@ -99,7 +99,6 @@ class Categorical(Distribution):
         ...         ans = self.ca.sample((2,3))
         ...         ans = self.ca.sample((2,3), probs_b)
         ...         ans = self.ca1.sample((2,3), probs_a)
-        ...
     """
 
     def __init__(self,
diff --git a/mindspore/nn/probability/distribution/cauchy.py b/mindspore/nn/probability/distribution/cauchy.py
index fc523cf80f..1726c515d4 100644
--- a/mindspore/nn/probability/distribution/cauchy.py
+++ b/mindspore/nn/probability/distribution/cauchy.py
@@ -48,70 +48,70 @@ class Cauchy(Distribution):
         >>> # The following creates two independent Cauchy distributions.
         >>> cauchy = msd.Cauchy([3.0, 3.0], [4.0, 4.0], dtype=mstype.float32)
         >>>
-        >>> # A Cauchy distribution can be initilize without arguments.
+        >>> # A Cauchy distribution can be initialized without arguments.
         >>> # In this case, 'loc' and `scale` must be passed in through arguments.
         >>> cauchy = msd.Cauchy(dtype=mstype.float32)
         >>>
         >>> # To use a Cauchy distribution in a network.
         >>> class net(Cell):
-        >>>     def __init__(self):
-        >>>         super(net, self).__init__():
-        >>>         self.cau1 = msd.Cauchy(0.0, 1.0, dtype=mstype.float32)
-        >>>         self.cau2 = msd.Cauchy(dtype=mstype.float32)
-        >>>
-        >>>     # The following calls are valid in construct.
-        >>>     def construct(self, value, loc_b, scale_b, loc_a, scale_a):
-        >>>
-        >>>         # Private interfaces of probability functions corresponding to public interfaces, including
-        >>>         # `prob`, `log_prob`, `cdf`, `log_cdf`, `survival_function`, and `log_survival`, have the same arguments as follows.
-        >>>         # Args:
-        >>>         #     value (Tensor): the value to be evaluated.
-        >>>         #     loc (Tensor): the location of the distribution. Default: self.loc.
-        >>>         #     scale (Tensor): the scale of the distribution. Default: self.scale.
-        >>>
-        >>>         # Examples of `prob`.
-        >>>         # Similar calls can be made to other probability functions
-        >>>         # by replacing 'prob' by the name of the function
-        >>>         ans = self.cau1.prob(value)
-        >>>         # Evaluate with respect to distribution b.
-        >>>         ans = self.cau1.prob(value, loc_b, scale_b)
-        >>>         # `loc` and `scale` must be passed in during function calls
-        >>>         ans = self.cau2.prob(value, loc_a, scale_a)
-        >>>
-        >>>         # Functions `mode` and `entropy` have the same arguments.
-        >>>         # Args:
-        >>>         #     loc (Tensor): the location of the distribution. Default: self.loc.
-        >>>         #     scale (Tensor): the scale of the distribution. Default: self.scale.
-        >>>
-        >>>         # Example of `mode`.
-        >>>         ans = self.cau1.mode() # return 0.0
-        >>>         ans = self.cau1.mode(loc_b, scale_b) # return loc_b
-        >>>         # `loc` and `scale` must be passed in during function calls.
-        >>>         ans = self.cau2.mode(loc_a, scale_a)
-        >>>
-        >>>         # Interfaces of 'kl_loss' and 'cross_entropy' are the same:
-        >>>         # Args:
-        >>>         #     dist (str): the type of the distributions. Only "Cauchy" is supported.
-        >>>         #     loc_b (Tensor): the loc of distribution b.
-        >>>         #     scale_b (Tensor): the scale distribution b.
-        >>>         #     loc (Tensor): the loc of distribution a. Default: self.loc.
-        >>>         #     scale (Tensor): the scale distribution a. Default: self.scale.
-        >>>
-        >>>         # Examples of `kl_loss`. `cross_entropy` is similar.
-        >>>         ans = self.cau1.kl_loss('Cauchy', loc_b, scale_b)
-        >>>         ans = self.cau1.kl_loss('Cauchy', loc_b, scale_b, loc_a, scale_a)
-        >>>         # Additional `loc` and `scale` must be passed in.
-        >>>         ans = self.cau2.kl_loss('Cauchy', loc_b, scale_b, loc_a, scale_a)
-        >>>
-        >>>         # Examples of `sample`.
-        >>>         # Args:
-        >>>         #     shape (tuple): the shape of the sample. Default: ()
-        >>>         #     loc (Tensor): the location of the distribution. Default: self.loc.
-        >>>         #     scale (Tensor): the scale of the distribution. Default: self.scale.
-        >>>         ans = self.cau1.sample()
-        >>>         ans = self.cau1.sample((2,3))
-        >>>         ans = self.cau1.sample((2,3), loc_b, s_b)
-        >>>         ans = self.cau2.sample((2,3), loc_a, s_a)
+        ...     def __init__(self):
+        ...         super(net, self).__init__():
+        ...         self.cau1 = msd.Cauchy(0.0, 1.0, dtype=mstype.float32)
+        ...         self.cau2 = msd.Cauchy(dtype=mstype.float32)
+        ...
+        ...     # The following calls are valid in construct.
+        ...     def construct(self, value, loc_b, scale_b, loc_a, scale_a):
+        ...
+        ...         # Private interfaces of probability functions corresponding to public interfaces, including
+        ...         # `prob`, `log_prob`, `cdf`, `log_cdf`, `survival_function`, and `log_survival`, have the same arguments as follows.
+        ...         # Args:
+        ...         #     value (Tensor): the value to be evaluated.
+        ...         #     loc (Tensor): the location of the distribution. Default: self.loc.
+        ...         #     scale (Tensor): the scale of the distribution. Default: self.scale.
+        ...
+        ...         # Examples of `prob`.
+        ...         # Similar calls can be made to other probability functions
+        ...         # by replacing 'prob' by the name of the function
+        ...         ans = self.cau1.prob(value)
+        ...         # Evaluate with respect to distribution b.
+        ...         ans = self.cau1.prob(value, loc_b, scale_b)
+        ...         # `loc` and `scale` must be passed in during function calls
+        ...         ans = self.cau2.prob(value, loc_a, scale_a)
+        ...
+        ...         # Functions `mode` and `entropy` have the same arguments.
+        ...         # Args:
+        ...         #     loc (Tensor): the location of the distribution. Default: self.loc.
+        ...         #     scale (Tensor): the scale of the distribution. Default: self.scale.
+        ...
+        ...         # Example of `mode`.
+        ...         ans = self.cau1.mode() # return 0.0
+        ...         ans = self.cau1.mode(loc_b, scale_b) # return loc_b
+        ...         # `loc` and `scale` must be passed in during function calls.
+        ...         ans = self.cau2.mode(loc_a, scale_a)
+        ...
+        ...         # Interfaces of 'kl_loss' and 'cross_entropy' are the same:
+        ...         # Args:
+        ...         #     dist (str): the type of the distributions. Only "Cauchy" is supported.
+        ...         #     loc_b (Tensor): the loc of distribution b.
+        ...         #     scale_b (Tensor): the scale distribution b.
+        ...         #     loc (Tensor): the loc of distribution a. Default: self.loc.
+        ...         #     scale (Tensor): the scale distribution a. Default: self.scale.
+        ...
+        ...         # Examples of `kl_loss`. `cross_entropy` is similar.
+        ...         ans = self.cau1.kl_loss('Cauchy', loc_b, scale_b)
+        ...         ans = self.cau1.kl_loss('Cauchy', loc_b, scale_b, loc_a, scale_a)
+        ...         # Additional `loc` and `scale` must be passed in.
+        ...         ans = self.cau2.kl_loss('Cauchy', loc_b, scale_b, loc_a, scale_a)
+        ...
+        ...         # Examples of `sample`.
+        ...         # Args:
+        ...         #     shape (tuple): the shape of the sample. Default: ()
+        ...         #     loc (Tensor): the location of the distribution. Default: self.loc.
+        ...         #     scale (Tensor): the scale of the distribution. Default: self.scale.
+        ...         ans = self.cau1.sample()
+        ...         ans = self.cau1.sample((2,3))
+        ...         ans = self.cau1.sample((2,3), loc_b, s_b)
+        ...         ans = self.cau2.sample((2,3), loc_a, s_a)
     """
 
     def __init__(self,
diff --git a/mindspore/nn/probability/distribution/exponential.py b/mindspore/nn/probability/distribution/exponential.py
index 0c349ba228..54e7ba366d 100644
--- a/mindspore/nn/probability/distribution/exponential.py
+++ b/mindspore/nn/probability/distribution/exponential.py
@@ -46,7 +46,7 @@ class Exponential(Distribution):
         >>> # The following creates two independent Exponential distributions.
         >>> e = msd.Exponential([0.5, 0.5], dtype=mstype.float32)
         >>>
-        >>> # An Exponential distribution can be initilized without arguments.
+        >>> # An Exponential distribution can be initialized without arguments.
         >>> # In this case, `rate` must be passed in through `args` during function calls.
         >>> e = msd.Exponential(dtype=mstype.float32)
         >>>
@@ -108,7 +108,6 @@ class Exponential(Distribution):
         ...         ans = self.e1.sample((2,3))
         ...         ans = self.e1.sample((2,3), rate_b)
         ...         ans = self.e2.sample((2,3), rate_a)
-        ...
     """
 
     def __init__(self,
@@ -187,7 +186,7 @@ class Exponential(Distribution):
     def _sd(self, rate=None):
         r"""
         .. math::
-            sd(EXP) = \frac{1.0}{\lambda}.
+            SD(EXP) = \frac{1.0}{\lambda}.
         """
         rate = self._check_param_type(rate)
         return 1.0 / rate
diff --git a/mindspore/nn/probability/distribution/geometric.py b/mindspore/nn/probability/distribution/geometric.py
index 1f1677a0ae..e09474019a 100644
--- a/mindspore/nn/probability/distribution/geometric.py
+++ b/mindspore/nn/probability/distribution/geometric.py
@@ -47,7 +47,7 @@ class Geometric(Distribution):
         >>> # The following creates two independent Geometric distributions.
         >>> n = msd.Geometric([0.5, 0.5], dtype=mstype.int32)
         >>>
-        >>> # A Geometric distribution can be initilized without arguments.
+        >>> # A Geometric distribution can be initialized without arguments.
         >>> # In this case, `probs` must be passed in through arguments during function calls.
         >>> n = msd.Geometric(dtype=mstype.int32)
         >>>
@@ -109,7 +109,6 @@ class Geometric(Distribution):
         ...         ans = self.g1.sample((2,3))
         ...         ans = self.g1.sample((2,3), probs_b)
         ...         ans = self.g2.sample((2,3), probs_a)
-        ...
     """
 
     def __init__(self,
diff --git a/mindspore/nn/probability/distribution/gumbel.py b/mindspore/nn/probability/distribution/gumbel.py
index a8135f185c..86078777e8 100644
--- a/mindspore/nn/probability/distribution/gumbel.py
+++ b/mindspore/nn/probability/distribution/gumbel.py
@@ -91,7 +91,6 @@ class Gumbel(TransformedDistribution):
         ...
         ...         ans = self.g1.sample()
         ...         ans = self.g1.sample((2,3))
-        ...
     """
 
     def __init__(self,
diff --git a/mindspore/nn/probability/distribution/log_normal.py b/mindspore/nn/probability/distribution/log_normal.py
index c6c9f518b9..a72d866adb 100644
--- a/mindspore/nn/probability/distribution/log_normal.py
+++ b/mindspore/nn/probability/distribution/log_normal.py
@@ -47,7 +47,7 @@ class LogNormal(msd.TransformedDistribution):
         >>> # The following creates two independent LogNormal distributions.
         >>> n = msd.LogNormal([3.0, 3.0], [4.0, 4.0], dtype=mstype.float32)
         >>>
-        >>> # A LogNormal distribution can be initilize without arguments.
+        >>> # A LogNormal distribution can be initialized without arguments.
         >>> # In this case, `loc` and `scale` must be passed in during function calls.
         >>> n = msd.LogNormal(dtype=mstype.float32)
         >>>
@@ -122,7 +122,6 @@ class LogNormal(msd.TransformedDistribution):
         ...         ans = self.n1.sample((2,3))
         ...         ans = self.n1.sample((2,3), loc_b, scale_b)
         ...         ans = self.n2.sample((2,3), loc_a, scale_a)
-        ...
     """
 
     def __init__(self,
diff --git a/mindspore/nn/probability/distribution/logistic.py b/mindspore/nn/probability/distribution/logistic.py
index 3fb4232e60..c63b6c3e9b 100644
--- a/mindspore/nn/probability/distribution/logistic.py
+++ b/mindspore/nn/probability/distribution/logistic.py
@@ -47,7 +47,7 @@ class Logistic(Distribution):
         >>> # The following creates two independent Logistic distributions.
         >>> n = msd.Logistic([3.0, 3.0], [4.0, 4.0], dtype=mstype.float32)
         >>>
-        >>> # A Logistic distribution can be initilize without arguments.
+        >>> # A Logistic distribution can be initialized without arguments.
         >>> # In this case, `loc` and `scale` must be passed in through arguments.
         >>> n = msd.Logistic(dtype=mstype.float32)
         >>>
@@ -97,7 +97,6 @@ class Logistic(Distribution):
         ...         ans = self.l1.sample((2,3))
         ...         ans = self.l1.sample((2,3), loc_b, scale_b)
         ...         ans = self.l2.sample((2,3), loc_a, scale_a)
-        ...
     """
 
     def __init__(self,
diff --git a/mindspore/nn/probability/distribution/normal.py b/mindspore/nn/probability/distribution/normal.py
index f37aeacde4..74159fad9f 100644
--- a/mindspore/nn/probability/distribution/normal.py
+++ b/mindspore/nn/probability/distribution/normal.py
@@ -47,7 +47,7 @@ class Normal(Distribution):
         >>> # The following creates two independent Normal distributions.
         >>> n = msd.Normal([3.0, 3.0], [4.0, 4.0], dtype=mstype.float32)
         >>>
-        >>> # A Normal distribution can be initilize without arguments.
+        >>> # A Normal distribution can be initialized without arguments.
         >>> # In this case, `mean` and `sd` must be passed in through arguments.
         >>> n = msd.Normal(dtype=mstype.float32)
         >>>
@@ -55,7 +55,7 @@ class Normal(Distribution):
         >>> class net(Cell):
         ...     def __init__(self):
         ...         super(net, self).__init__():
-        ...         self.n1 = msd.Nomral(0.0, 1.0, dtype=mstype.float32)
+        ...         self.n1 = msd.Normal(0.0, 1.0, dtype=mstype.float32)
         ...         self.n2 = msd.Normal(dtype=mstype.float32)
         ...
         ...     # The following calls are valid in construct.
@@ -65,14 +65,14 @@ class Normal(Distribution):
         ...         # `prob`, `log_prob`, `cdf`, `log_cdf`, `survival_function`, and `log_survival`, have the same arguments as follows.
         ...         # Args:
         ...         #     value (Tensor): the value to be evaluated.
-        ...         #     mean (Tensor): the mean of distribution. Default: self._mean_value.
-        ...         #     sd (Tensor): the standard deviation of distribution. Default: self._sd_value.
+        ...         #     mean (Tensor): the mean of the distribution. Default: self._mean_value.
+        ...         #     sd (Tensor): the standard deviation of the distribution. Default: self._sd_value.
         ...
         ...         # Examples of `prob`.
         ...         # Similar calls can be made to other probability functions
         ...         # by replacing 'prob' by the name of the function
         ...         ans = self.n1.prob(value)
-        ...         # Evaluate with respect to distribution b.
+        ...         # Evaluate with respect to the distribution b.
         ...         ans = self.n1.prob(value, mean_b, sd_b)
         ...         # `mean` and `sd` must be passed in during function calls
         ...         ans = self.n2.prob(value, mean_a, sd_a)
@@ -80,8 +80,8 @@ class Normal(Distribution):
         ...
         ...         # Functions `mean`, `sd`, `var`, and `entropy` have the same arguments.
         ...         # Args:
-        ...         #     mean (Tensor): the mean of distribution. Default: self._mean_value.
-        ...         #     sd (Tensor): the standard deviation of distribution. Default: self._sd_value.
+        ...         #     mean (Tensor): the mean of the distribution. Default: self._mean_value.
+        ...         #     sd (Tensor): the standard deviation of the distribution. Default: self._sd_value.
         ...
         ...         # Example of `mean`. `sd`, `var`, and `entropy` are similar.
         ...         ans = self.n1.mean() # return 0.0
@@ -94,9 +94,9 @@ class Normal(Distribution):
         ...         # Args:
         ...         #     dist (str): the type of the distributions. Only "Normal" is supported.
         ...         #     mean_b (Tensor): the mean of distribution b.
-        ...         #     sd_b (Tensor): the standard deviation distribution b.
+        ...         #     sd_b (Tensor): the standard deviation of distribution b.
         ...         #     mean_a (Tensor): the mean of distribution a. Default: self._mean_value.
-        ...         #     sd_a (Tensor): the standard deviation distribution a. Default: self._sd_value.
+        ...         #     sd_a (Tensor): the standard deviation of distribution a. Default: self._sd_value.
         ...
         ...         # Examples of `kl_loss`. `cross_entropy` is similar.
         ...         ans = self.n1.kl_loss('Normal', mean_b, sd_b)
@@ -113,7 +113,6 @@ class Normal(Distribution):
         ...         ans = self.n1.sample((2,3))
         ...         ans = self.n1.sample((2,3), mean_b, sd_b)
         ...         ans = self.n2.sample((2,3), mean_a, sd_a)
-        ...
     """
 
     def __init__(self,
diff --git a/mindspore/nn/probability/distribution/transformed_distribution.py b/mindspore/nn/probability/distribution/transformed_distribution.py
index 6602f12758..dbd1e36f86 100644
--- a/mindspore/nn/probability/distribution/transformed_distribution.py
+++ b/mindspore/nn/probability/distribution/transformed_distribution.py
@@ -67,7 +67,6 @@ class TransformedDistribution(Distribution):
         ...         # Similar calls can be made to other functions
         ...         # by replacing 'sample' by the name of the function.
         ...         ans = self.ln.sample(shape=(2, 3))
-        ...
     """
 
     def __init__(self,
diff --git a/mindspore/nn/probability/distribution/uniform.py b/mindspore/nn/probability/distribution/uniform.py
index e94deeac3e..8b30ebb59a 100644
--- a/mindspore/nn/probability/distribution/uniform.py
+++ b/mindspore/nn/probability/distribution/uniform.py
@@ -46,7 +46,7 @@ class Uniform(Distribution):
         >>> # The following creates two independent Uniform distributions.
         >>> u = msd.Uniform([0.0, 0.0], [1.0, 2.0], dtype=mstype.float32)
         >>>
-        >>> # A Uniform distribution can be initilized without arguments.
+        >>> # A Uniform distribution can be initialized without arguments.
         >>> # In this case, `high` and `low` must be passed in through arguments during function calls.
         >>> u = msd.Uniform(dtype=mstype.float32)
         >>>
@@ -64,8 +64,8 @@ class Uniform(Distribution):
         ...         # `prob`, `log_prob`, `cdf`, `log_cdf`, `survival_function`, and `log_survival`, have the same arguments.
         ...         # Args:
         ...         #     value (Tensor): the value to be evaluated.
-        ...         #     low (Tensor): the lower bound of distribution. Default: self.low.
-        ...         #     high (Tensor): the higher bound of distribution. Default: self.high.
+        ...         #     low (Tensor): the lower bound of the distribution. Default: self.low.
+        ...         #     high (Tensor): the higher bound of the distribution. Default: self.high.
         ...
         ...         # Examples of `prob`.
         ...         # Similar calls can be made to other probability functions
@@ -79,8 +79,8 @@ class Uniform(Distribution):
         ...
         ...         # Functions `mean`, `sd`, `var`, and `entropy` have the same arguments.
         ...         # Args:
-        ...         #     low (Tensor): the lower bound of distribution. Default: self.low.
-        ...         #     high (Tensor): the higher bound of distribution. Default: self.high.
+        ...         #     low (Tensor): the lower bound of the distribution. Default: self.low.
+        ...         #     high (Tensor): the higher bound of the distribution. Default: self.high.
         ...
         ...         # Examples of `mean`. `sd`, `var`, and `entropy` are similar.
         ...         ans = self.u1.mean() # return 0.5
@@ -112,7 +112,6 @@ class Uniform(Distribution):
         ...         ans = self.u1.sample((2,3))
         ...         ans = self.u1.sample((2,3), low_b, high_b)
         ...         ans = self.u2.sample((2,3), low_a, high_a)
-        ...
     """
 
     def __init__(self,
diff --git a/tests/st/probability/bijector/test_power_transform.py b/tests/st/probability/bijector/test_power_transform.py
index d76b67a8ee..d1137610e9 100644
--- a/tests/st/probability/bijector/test_power_transform.py
+++ b/tests/st/probability/bijector/test_power_transform.py
@@ -35,7 +35,7 @@ class Net(nn.Cell):
         return forward
 
 def test_forward():
-    power = 2
+    power = 2.
     x = np.array([2.0, 3.0, 4.0, 5.0], dtype=np.float32)
     tx = Tensor(x, dtype=dtype.float32)
     forward = Net(power=power)
@@ -57,7 +57,7 @@ class Net1(nn.Cell):
         return inverse
 
 def test_inverse():
-    power = 2
+    power = 2.
     y = np.array([2.0, 3.0, 4.0, 5.0], dtype=np.float32)
     ty = Tensor(y, dtype=dtype.float32)
     inverse = Net1(power=power)
@@ -78,7 +78,7 @@ class Net2(nn.Cell):
         return self.bijector.forward_log_jacobian(x_)
 
 def test_forward_jacobian():
-    power = 2
+    power = 2.
     x = np.array([2.0, 3.0, 4.0, 5.0], dtype=np.float32)
     tx = Tensor(x, dtype=dtype.float32)
     forward_jacobian = Net2(power=power)
@@ -99,7 +99,7 @@ class Net3(nn.Cell):
         return self.bijector.inverse_log_jacobian(y_)
 
 def test_inverse_jacobian():
-    power = 2
+    power = 2.
     y = np.array([2.0, 3.0, 4.0, 5.0], dtype=np.float32)
     ty = Tensor(y, dtype=dtype.float32)
     inverse_jacobian = Net3(power=power)
diff --git a/tests/ut/python/nn/probability/bijector/test_bijector.py b/tests/ut/python/nn/probability/bijector/test_bijector.py
index f3ae926c5b..0932b15a71 100644
--- a/tests/ut/python/nn/probability/bijector/test_bijector.py
+++ b/tests/ut/python/nn/probability/bijector/test_bijector.py
@@ -1,4 +1,4 @@
-# Copyright 2019 Huawei Technologies Co., Ltd
+# Copyright 2020 Huawei Technologies Co., Ltd
 #
 # Licensed under the Apache License, Version 2.0 (the "License");
 # you may not use this file except in compliance with the License.
@@ -99,6 +99,14 @@ def test_arguments_same_type():
     assert isinstance(bijector, msb.Bijector)
     bijector = MyBijector(1.0, 2.0)
     assert isinstance(bijector, msb.Bijector)
+    with pytest.raises(TypeError):
+        MyBijector(1, 2)
+    with pytest.raises(TypeError):
+        MyBijector([1, 2], [2, 4])
+    with pytest.raises(TypeError):
+        MyBijector(np.array([1, 2]).astype(np.int32), np.array([1, 2]).astype(np.int32))
+    with pytest.raises(TypeError):
+        MyBijector(Tensor([1, 2], dtype=dtype.int32), Tensor([1, 2], dtype=dtype.int32))
 
 def test_arguments_with_dtype_specified():
     """
@@ -118,12 +126,20 @@ def test_arguments_with_dtype_specified():
         MySecondBijector(None, param2_2)
     param1_3 = Tensor(1.0, dtype=dtype.float32)
     param2_3 = Tensor(2.0, dtype=dtype.float32)
-    bijector = MyBijector(param1_3, param2_3)
+    bijector = MySecondBijector(param1_3, param2_3)
     assert isinstance(bijector, msb.Bijector)
     param1_4 = np.array(2.0).astype(np.float32)
     param2_4 = np.array(1.0).astype(np.float32)
-    bijector = MyBijector(param1_4, param2_4)
+    bijector = MySecondBijector(param1_4, param2_4)
     assert isinstance(bijector, msb.Bijector)
+    with pytest.raises(TypeError):
+        MySecondBijector(1, 2)
+    with pytest.raises(TypeError):
+        MySecondBijector([1, 2], [2, 4])
+    with pytest.raises(TypeError):
+        MySecondBijector(np.array([1, 2]).astype(np.int32), np.array([1, 2]).astype(np.int32))
+    with pytest.raises(TypeError):
+        MySecondBijector(Tensor([1, 2], dtype=dtype.int32), Tensor([1, 2], dtype=dtype.int32))
 
 class Net1(nn.Cell):
     """
diff --git a/tests/ut/python/nn/probability/bijector/test_exp.py b/tests/ut/python/nn/probability/bijector/test_exp.py
index 98f6315a5f..6ac558d6df 100644
--- a/tests/ut/python/nn/probability/bijector/test_exp.py
+++ b/tests/ut/python/nn/probability/bijector/test_exp.py
@@ -1,4 +1,4 @@
-# Copyright 2019 Huawei Technologies Co., Ltd
+# Copyright 2020 Huawei Technologies Co., Ltd
 #
 # Licensed under the Apache License, Version 2.0 (the "License");
 # you may not use this file except in compliance with the License.
diff --git a/tests/ut/python/nn/probability/bijector/test_gumbel_cdf.py b/tests/ut/python/nn/probability/bijector/test_gumbel_cdf.py
index 7d9d8da4da..390ada913a 100644
--- a/tests/ut/python/nn/probability/bijector/test_gumbel_cdf.py
+++ b/tests/ut/python/nn/probability/bijector/test_gumbel_cdf.py
@@ -1,4 +1,4 @@
-# Copyright 2019 Huawei Technologies Co., Ltd
+# Copyright 2020 Huawei Technologies Co., Ltd
 #
 # Licensed under the Apache License, Version 2.0 (the "License");
 # you may not use this file except in compliance with the License.
diff --git a/tests/ut/python/nn/probability/bijector/test_invert_bijector.py b/tests/ut/python/nn/probability/bijector/test_invert_bijector.py
index 7eb49ea646..5e86c08249 100644
--- a/tests/ut/python/nn/probability/bijector/test_invert_bijector.py
+++ b/tests/ut/python/nn/probability/bijector/test_invert_bijector.py
@@ -1,4 +1,4 @@
-# Copyright 2019 Huawei Technologies Co., Ltd
+# Copyright 2020 Huawei Technologies Co., Ltd
 #
 # Licensed under the Apache License, Version 2.0 (the "License");
 # you may not use this file except in compliance with the License.
diff --git a/tests/ut/python/nn/probability/bijector/test_power_transform.py b/tests/ut/python/nn/probability/bijector/test_power_transform.py
index e5ed5cd271..0ea1e38d6a 100644
--- a/tests/ut/python/nn/probability/bijector/test_power_transform.py
+++ b/tests/ut/python/nn/probability/bijector/test_power_transform.py
@@ -1,4 +1,4 @@
-# Copyright 2019 Huawei Technologies Co., Ltd
+# Copyright 2020 Huawei Technologies Co., Ltd
 #
 # Licensed under the Apache License, Version 2.0 (the "License");
 # you may not use this file except in compliance with the License.
@@ -22,7 +22,7 @@ from mindspore import dtype
 def test_init():
     b = msb.PowerTransform()
     assert isinstance(b, msb.Bijector)
-    b = msb.PowerTransform(1)
+    b = msb.PowerTransform(1.)
     assert isinstance(b, msb.Bijector)
 
 def test_type():
@@ -37,7 +37,7 @@ class Net(nn.Cell):
     """
     def __init__(self):
         super(Net, self).__init__()
-        self.b1 = msb.PowerTransform(power=0)
+        self.b1 = msb.PowerTransform(power=0.)
         self.b2 = msb.PowerTransform()
 
     def construct(self, x_):
@@ -60,7 +60,7 @@ class Jacobian(nn.Cell):
     """
     def __init__(self):
         super(Jacobian, self).__init__()
-        self.b1 = msb.PowerTransform(power=0)
+        self.b1 = msb.PowerTransform(power=0.)
         self.b2 = msb.PowerTransform()
 
     def construct(self, x_):
diff --git a/tests/ut/python/nn/probability/bijector/test_scalar_affine.py b/tests/ut/python/nn/probability/bijector/test_scalar_affine.py
index eab0946c7e..c661191b33 100644
--- a/tests/ut/python/nn/probability/bijector/test_scalar_affine.py
+++ b/tests/ut/python/nn/probability/bijector/test_scalar_affine.py
@@ -1,4 +1,4 @@
-# Copyright 2019 Huawei Technologies Co., Ltd
+# Copyright 2020 Huawei Technologies Co., Ltd
 #
 # Licensed under the Apache License, Version 2.0 (the "License");
 # you may not use this file except in compliance with the License.
diff --git a/tests/ut/python/nn/probability/bijector/test_softplus.py b/tests/ut/python/nn/probability/bijector/test_softplus.py
index 4255751a78..6ed17e67b5 100644
--- a/tests/ut/python/nn/probability/bijector/test_softplus.py
+++ b/tests/ut/python/nn/probability/bijector/test_softplus.py
@@ -1,4 +1,4 @@
-# Copyright 2019 Huawei Technologies Co., Ltd
+# Copyright 2020 Huawei Technologies Co., Ltd
 #
 # Licensed under the Apache License, Version 2.0 (the "License");
 # you may not use this file except in compliance with the License.
diff --git a/tests/ut/python/nn/probability/distribution/test_distribution.py b/tests/ut/python/nn/probability/distribution/test_distribution.py
index 8542343c1a..6962fefcc8 100644
--- a/tests/ut/python/nn/probability/distribution/test_distribution.py
+++ b/tests/ut/python/nn/probability/distribution/test_distribution.py
@@ -1,4 +1,4 @@
-# Copyright 2019 Huawei Technologies Co., Ltd
+# Copyright 2020 Huawei Technologies Co., Ltd
 #
 # Licensed under the Apache License, Version 2.0 (the "License");
 # you may not use this file except in compliance with the License.