diff --git a/docs/api/api_python/ops/mindspore.ops.func_clip_by_value.rst b/docs/api/api_python/ops/mindspore.ops.func_clip_by_value.rst
index d06954773b0..d43ddea3689 100644
--- a/docs/api/api_python/ops/mindspore.ops.func_clip_by_value.rst
+++ b/docs/api/api_python/ops/mindspore.ops.func_clip_by_value.rst
@@ -17,11 +17,11 @@
 
     .. note::
         - `clip_value_min` 必须小于或等于 `clip_value_max` ；
-        -  :math:`x` ， `clip_value_min` 和 `clip_value_max`的数据类型需支持隐式类型转换，且不能同时为布尔型。
+        -  :math:`x` ， `clip_value_min` 和 `clip_value_max` 的数据类型需支持隐式类型转换，且不能同时为布尔型。
         
 
     参数：
-        - **x** (Tensor) - clip_by_value的输入，任意维度的Tensor。
+        - **x** (Tensor) - `clip_by_value` 的输入，任意维度的Tensor。
         - **clip_value_min** (Tensor) - 指定最小值。
         - **clip_value_max** (Tensor) - 指定最大值。
 
diff --git a/mindspore/python/mindspore/nn/metrics/error.py b/mindspore/python/mindspore/nn/metrics/error.py
index e8b2a534610..6fef606e23f 100644
--- a/mindspore/python/mindspore/nn/metrics/error.py
+++ b/mindspore/python/mindspore/nn/metrics/error.py
@@ -28,7 +28,7 @@ class MAE(Metric):
     in the input: :math:`x` and the target: :math:`y`.
 
     .. math::
-        \text{MAE} = \frac{\sum_{i=1}^n \|y_{pred}_i - y_i\|}{n}
+        \text{MAE} = \frac{\sum_{i=1}^n \|{y\_pred}_i - y_i\|}{n}
 
     where :math:`n` is batch size.
 
@@ -104,7 +104,7 @@ class MSE(Metric):
     each element in the prediction and the ground truth: :math:`x` and: :math:`y`.
 
     .. math::
-        \text{MSE}(x,\ y) = \frac{\sum_{i=1}^n(y_{pred}_i - y_i)^2}{n}
+        \text{MSE}(x,\ y) = \frac{\sum_{i=1}^n({y\_pred}_i - y_i)^2}{n}
 
     where :math:`n` is batch size.
 
diff --git a/mindspore/python/mindspore/nn/metrics/roc.py b/mindspore/python/mindspore/nn/metrics/roc.py
index 02e032c4161..1d3aa0a849c 100644
--- a/mindspore/python/mindspore/nn/metrics/roc.py
+++ b/mindspore/python/mindspore/nn/metrics/roc.py
@@ -169,11 +169,11 @@ class ROC(Metric):
             A tuple, composed of `fpr`, `tpr`, and `thresholds`.
 
             - **fpr** (np.array) - False positive rate. In binary classification case, a fpr numpy array under different
-                    thresholds will be returned, otherwise in multiclass case, a list of
-                    fpr numpy arrays will be returned and each element represents one category.
+              thresholds will be returned, otherwise in multiclass case, a list of
+              fpr numpy arrays will be returned and each element represents one category.
             - **tpr** (np.array) - True positive rates. n binary classification case, a tps numpy array under different
-                    thresholds will be returned, otherwise in multiclass case, a list of tps numpy arrays
-                    will be returned and each element represents one category.
+              thresholds will be returned, otherwise in multiclass case, a list of tps numpy arrays
+              will be returned and each element represents one category.
             - **thresholds** (np.array) - Thresholds used for computing fpr and tpr.
 
         Raises:
diff --git a/mindspore/python/mindspore/nn/probability/distribution/uniform.py b/mindspore/python/mindspore/nn/probability/distribution/uniform.py
index 90a1e1f5982..4029bd2993e 100644
--- a/mindspore/python/mindspore/nn/probability/distribution/uniform.py
+++ b/mindspore/python/mindspore/nn/probability/distribution/uniform.py
@@ -30,7 +30,7 @@ class Uniform(Distribution):
     and the probability density function:
 
     .. math::
-        f(x, a, b) = 1 / b \exp(\exp(-(x - a) / b) - x),
+        f(x, a, b) = 1 / (b - a),
 
     where a and b are the lower and upper bound respectively.