!48885 fixed_huber_loss_master

Merge pull request !48885 from yide12/ops_threshold_leaky_relu_master

docs/api/api_python/ops/mindspore.ops.func_einsum.rst

@@ -3,10 +3,10 @@ mindspore.ops.einsum
 
 .. py:function:: mindspore.ops.einsum(equation, *operands)
 
-    基于爱因斯坦求和约定（Einsum）符号，指定维度对输入Tensor元素的乘积求和。你可以使用这个运算符来执行对角线、减法、转置、矩阵乘法、乘法、内积运算等等。
+    基于爱因斯坦求和约定（Einsum）符号，沿着指定维度对输入Tensor元素的乘积求和。你可以使用这个运算符来执行对角线、减法、转置、矩阵乘法、乘法、内积运算等等。
 
     .. note::
-        现在支持子列表模式。例如，ops.einsum(op1, sublist1, op2, sublist2, ..., sublist_out)。在子列表模式中，`equation` 由子列表推导得到，Python的省略号和介于[0, 52)的整数list组成子列表。每个操作数后面都有一个子列表，并且最后有一个表示输出的子列表。
+        现在支持子列表模式。例如，ops.einsum(op1, sublist1, op2, sublist2, ..., sublist_out)。在子列表模式中， `equation` 由子列表推导得到，Python的省略号和介于[0, 52)的整数list组成子列表。每个操作数后面都有一个子列表，并且最后有一个表示输出的子列表。
 
     参数：
         - **equation** (str) - 基于爱因斯坦求和约定的符号，表示想要执行的操作。符号只能包含字母、逗号、省略号和箭头。字母表示输入Tensor维数，逗号表示单独的Tensor，省略号表示忽略的Tensor维数，箭头的左边表示输入Tensor，右边表示期望输出的维度。

docs/api/api_python/ops/mindspore.ops.func_huber_loss.rst

@@ -31,9 +31,9 @@ mindspore.ops.huber_loss
 
     参数：
         - **x** (Tensor) - 输入预测值，任意维度的Tensor。
-        - **target** (Tensor) - 目标值，与 `x` 的shape和dtype相同。
+        - **target** (Tensor) - 目标值，通常情况下与 `x` 的shape和dtype相同。但是当 `target` 和 `x` 的shape不同时，需要保证他们之间可以互相广播。
         - **reduction** (str) - 应用于loss的reduction类型。取值为"mean"，"sum"或"none"。默认值："mean"。
-        - **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。
+        - **delta** (Union[int, float]) - 两种损失之间变化的阈值。该值必须大于零。默认值：1.0。
 
     返回：
         Tensor，和 `x` 具有相同的dtype和shape。
@@ -43,4 +43,4 @@ mindspore.ops.huber_loss
         - **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"。
-        - **ValueError** - `x` 和 `target` 有不同的shape。
+        - **ValueError** - `x` 和 `target` 有不同的shape，且不能互相广播。

mindspore/python/mindspore/ops/function/math_func.py

@@ -9172,8 +9172,8 @@ def _einsum_convert_num_to_char(num):
 
 def einsum(equation, *operands):
     r"""
-    Sums the product of the elements of the input Tensor along
-    dimensions specified notation based on the Einstein summation convention(Einsum).
+    According to the Einstein summation Convention (Einsum),
+    the product of the input tensor elements is summed along the specified dimension.
     You can use this operator to perform diagonal, reducesum, transpose, matmul, mul, inner product operations, etc.
 
     Note::

mindspore/python/mindspore/ops/function/nn_func.py

@@ -4464,7 +4464,7 @@ def hardtanh(x, min_val=-1.0, max_val=1.0):
 def huber_loss(x, target, reduction='mean', delta=1.0):
     r"""
     huber_loss calculates the error between the predicted value and the target value.
-    It has the advantages of both l1_loss and mse_loss.
+    It has the best of both the loss of l1 and the loss of mse.
 
     Assuming that the :math:`x` and :math:`y` are 1-D Tensor, length :math:`N`, the reduction parameter is set to "none"
     then calculate the loss of :math:`x` and :math:`y` without dimensionality reduction. The formula is as follows:
@@ -4493,11 +4493,13 @@ def huber_loss(x, target, reduction='mean', delta=1.0):
 
     Args:
         x (Tensor): Predicted value, Tensor of any dimension.
-        target (Tensor): Target value, same dtype and shape as the `x`.
-        reduction (str): Type of reduction to be applied to loss. The optional values are "mean", "sum", and "none".
+        target (Tensor): Target value, has same dtype and shape as the `x` in common cases.
+            However, when the shape of `target` is different from the shape of `x`,
+            and they should be broadcasted to each other.
+        reduction (str): Type of reduction to be applied to loss. The optional values are "mean", "sum" and "none".
             Default: "mean".
         delta (Union[int, float]): The threshold to change between two type of loss.
-            The value must be positive. Default: 1.0.
+            The value must be greater than zero. Default: 1.0.
 
     Returns:
         Tensor, with the same dtype and shape as `x`.
@@ -4507,7 +4509,7 @@ def huber_loss(x, target, reduction='mean', delta=1.0):
         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 `x` and `target` have different shapes.
+        ValueError: If `x` and `target` have different shapes and cannot be broadcasted to each other.
 
     Supported Platforms:
         ``Ascend`` ``GPU`` ``CPU``
@@ -4523,8 +4525,6 @@ def huber_loss(x, target, reduction='mean', delta=1.0):
     _check_is_tensor('target', target, "huber_loss")
     _check_value_type("delta", delta, [int, float], "huber_loss")
     _check_number_gt_value("delta", delta, 0.0, "huber_loss")
-    if x.shape != target.shape:
-        raise ValueError(f"For huber_loss, x and target must be the same shape, but got {x.shape} and {target.shape}")
     sub = _get_cache_prim(P.Sub)()
     multi = _get_cache_prim(P.Mul)()
     z = sub(x, target)