!35146 update doc of nn.HuberLoss

Merge pull request !35146 from fujianzhao/code_docs

docs/api/api_python/nn/mindspore.nn.HuberLoss.rst

@@ -1,7 +1,7 @@
 mindspore.nn.HuberLoss
 =============================
 
-.. py:class:: mindspore.nn.HuberLoss(reduction='mean', delta=1.0)
+.. py:class:: mindspore.nn.HuberLoss(reduction="mean", delta=1.0)
 
     HuberLoss计算预测值和目标值之间的误差。它兼有L1Loss和MSELoss的优点。
 
@@ -23,13 +23,13 @@ mindspore.nn.HuberLoss
     .. math::
         \ell(x, y) =
         \begin{cases}
-            \operatorname{mean}(L), & \text{if reduction} = \text{'mean';}\\
-            \operatorname{sum}(L),  & \text{if reduction} = \text{'sum'.}
+            \operatorname{mean}(L), & \text{if reduction} = \text{"mean";}\\
+            \operatorname{sum}(L),  & \text{if reduction} = \text{"sum".}
         \end{cases}
 
     **参数：**
 
-    - **reduction** (str) - 应用于loss的reduction类型。取值为"mean"，"sum"，或"none"。默认值："mean"。如果 `reduction` 为'mean'或'sum'，则输出一个标量Tensor；如果 `reduction` 为'none'，则输出Tensor的shape为广播后的shape。
+    - **reduction** (str) - 应用于loss的reduction类型。取值为"mean"，"sum"，或"none"。默认值："mean"。如果 `reduction` 为"mean"或"sum"，则输出一个标量Tensor；如果 `reduction` 为"none"，则输出Tensor的shape为广播后的shape。
     - **delta** (Union[int, float]) - 两种损失之间变化的阈值。 该值必须为正。 默认值：1.0。
 
     **输入：**
@@ -39,11 +39,12 @@ mindspore.nn.HuberLoss
 
     **输出：**
 
-    Tensor或Scalar，如果 `reduction` 为'none'，则为shape和数据类型与输入'logits'相的Tensor。否则，输出为Scalar。
+    Tensor或Scalar，如果 `reduction` 为"none"，返回与 `logits` 具有相同shape和dtype的Tensor。否则，将返回一个Scalar。
 
     **异常：**
 
     - **TypeError** - `logits` 或 `labels` 的数据类型既不是float16也不是float32。
+    - **TypeError** - `logits` 和 `labels` 的数据类型不同。
     - **TypeError** - `delta` 不是float或int。
     - **ValueError** - `delta` 的值小于或等于0。
     - **ValueError** - `reduction` 不为"mean"、"sum"或"none"。

mindspore/python/mindspore/nn/loss/loss.py

@@ -1504,13 +1504,13 @@ class HuberLoss(LossBase):
             delta * (|x_n - y_n| - 0.5 * delta), & \text{otherwise. }
         \end{cases}
 
-    where :math:`N` is the batch size. If `reduction` is not 'none', then:
+    where :math:`N` is the batch size. If `reduction` is not "none", then:
 
     .. math::
         \ell(x, y) =
         \begin{cases}
-            \operatorname{mean}(L), & \text{if reduction} = \text{'mean';}\\
-            \operatorname{sum}(L),  & \text{if reduction} = \text{'sum'.}
+            \operatorname{mean}(L), & \text{if reduction} = \text{"mean";}\\
+            \operatorname{sum}(L),  & \text{if reduction} = \text{"sum".}
         \end{cases}
 
     Args:
@@ -1521,27 +1521,30 @@ class HuberLoss(LossBase):
             The value must be positive. Default: 1.0.
 
     Inputs:
-        - **logits** (Tensor) - Input logits with shape :math:`(N, *)` where :math:`*` means, any number
-          of additional dimensions. The data type must be float16 or float32.
-        - **labels** (Tensor) - Ground truth label with shape :math:`(N, *)`, same dtype as `logits`.
-          It supports the shape of `logits` is different from the shape of `labels` and they should be
-          broadcasted to each other.
+        - **logits** (Tensor) - Predicted value, Tensor of any dimension. The data type must be float16 or float32.
+        - **labels** (Tensor) - Target value, same dtype and shape as the `logits` in common cases.
+          However, it supports the shape of `logits` is different from the shape of `labels`
+          and they should be broadcasted to each other.
 
     Outputs:
-        Tensor or Scalar, if `reduction` is "none", its shape is the same as `logits`.
+        Tensor or Scalar, if `reduction` is "none", return a Tensor with same shape and dtype as `logits`.
         Otherwise, a scalar value will be returned.
 
     Raises:
         TypeError: If data type of `logits` or `labels` is neither float16 nor float32.
+        TypeError: If data type of `logits` or `labels` are not the same.
         TypeError: If dtype of `delta` is neither float nor int.
         ValueError: If `delta` is less than or equal to 0.
-        ValueError: If `reduction` is not one of 'none', 'mean', 'sum'.
+        ValueError: If `reduction` is not one of "none", "mean", "sum".
         ValueError: If `logits` and `labels` have different shapes and cannot be broadcasted to each other.
 
     Supported Platforms:
         ``Ascend`` ``GPU`` ``CPU``
 
     Examples:
+        >>> import mindspore
+        >>> from mindspore import Tensor, nn
+        >>> import numpy as np
         >>> # Case 1: logits.shape = labels.shape = (3,)
         >>> loss = nn.HuberLoss()
         >>> logits = Tensor(np.array([1, 2, 3]), mindspore.float32)
@@ -1550,7 +1553,7 @@ class HuberLoss(LossBase):
         >>> print(output)
         0.16666667
         >>> # Case 2: logits.shape = (3,), labels.shape = (2, 3)
-        >>> loss = nn.HuberLoss(reduction='none')
+        >>> loss = nn.HuberLoss(reduction="none")
         >>> logits = Tensor(np.array([1, 2, 3]), mindspore.float32)
         >>> labels = Tensor(np.array([[1, 1, 1], [1, 2, 2]]), mindspore.float32)
         >>> output = loss(logits, labels)