fix I60Q6L
This commit is contained in:
parent
1a14ff5c87
commit
f84ce5d871
|
@ -7,12 +7,12 @@ mindspore.ops.igamma
|
|||
如果我们将 `input` 比作 `a` , `other` 比作 `x` ,则正规化的下层不完全伽马函数可以表示成:
|
||||
|
||||
.. math::
|
||||
P(a, x) = gamma(a, x) / Gamma(a) = 1 - Q(a, x)
|
||||
P(a, x) = Gamma(a, x) / Gamma(a) = 1 - Q(a, x)
|
||||
|
||||
其中,
|
||||
|
||||
.. math::
|
||||
gamma(a, x) = \int_0^x t^{a-1} \exp^{-t} dt
|
||||
Gamma(a, x) = \int_0^x t^{a-1} \exp^{-t} dt
|
||||
|
||||
为下层不完全伽马函数。
|
||||
|
||||
|
|
|
@ -7,12 +7,12 @@ mindspore.ops.igammac
|
|||
如果我们将 `input` 比作 `a` , `other` 比作 `x` ,则正规化的下层不完全伽马函数可以表示成:
|
||||
|
||||
.. math::
|
||||
\(Q(a, x) = Gamma(a, x) / Gamma(a) = 1 - P(a, x)\)
|
||||
Q(a, x) = Gamma(a, x) / Gamma(a) = 1 - P(a, x)
|
||||
|
||||
其中,
|
||||
|
||||
.. math::
|
||||
\(Gamma(a, x) = int_{x}^{\infty} t^{a-1} exp(-t) dt\)
|
||||
Gamma(a, x) = int_{x}^{\infty} t^{a-1} exp(-t) dt
|
||||
|
||||
为上层不完全伽马函数。
|
||||
|
||||
|
|
|
@ -11,7 +11,7 @@ mindspore.ops.mse_loss
|
|||
- **input_x** (Tensor) - 任意维度的Tensor。
|
||||
- **target** (Tensor) - 输入标签,任意维度的Tensor。大多数场景下与 `input_x` 具有相同的shape。
|
||||
但是,也支持在两者shape不相同的情况下,通过广播保持一致。
|
||||
- **reduction** (str,可选) - 对loss应用特定的缩减方法。可选"mean"、"none"、"sum"。默认值:"mean"
|
||||
- **reduction** (str,可选) - 对loss应用特定的缩减方法。可选"mean"、"none"、"sum"。默认值:"mean"。
|
||||
|
||||
返回:
|
||||
Tensor,数据类型为float,如果 `reduction` 为 'mean'或'sum'时,shape为0;如果 `reduction` 为 'none',输入的shape则是广播之后的shape。
|
||||
|
|
|
@ -7110,12 +7110,12 @@ def igamma(input, other):
|
|||
If we define `input` as `a` and `other` as `x`, the lower regularized incomplete Gamma function is defined as:
|
||||
|
||||
.. math::
|
||||
\(P(a, x) = Gamma(a, x) / Gamma(a) = 1 - Q(a, x)\)
|
||||
P(a, x) = Gamma(a, x) / Gamma(a) = 1 - Q(a, x)
|
||||
|
||||
where
|
||||
|
||||
.. math::
|
||||
\(Gamma(a, x) = \int_0^x t^{a-1} \exp^{-t} dt\)
|
||||
Gamma(a, x) = \int_0^x t^{a-1} \exp^{-t} dt
|
||||
|
||||
is the lower incomplete Gamma function.
|
||||
|
||||
|
@ -7159,12 +7159,12 @@ def igammac(input, other):
|
|||
If we define `input` as `a` and `other` as `x`, the upper regularized incomplete Gamma function is defined as:
|
||||
|
||||
.. math::
|
||||
\(Q(a, x) = Gamma(a, x) / Gamma(a) = 1 - P(a, x)\)
|
||||
Q(a, x) = Gamma(a, x) / Gamma(a) = 1 - P(a, x)
|
||||
|
||||
where
|
||||
|
||||
.. math::
|
||||
\(Gamma(a, x) = int_{x}^{\infty} t^{a-1} exp(-t) dt\)
|
||||
Gamma(a, x) = int_{x}^{\infty} t^{a-1} exp(-t) dt
|
||||
|
||||
is the upper incomplete Gama function.
|
||||
|
||||
|
|
Loading…
Reference in New Issue