log10

paddle. log10 ( x, name=None ) [源代码]

Log10 激活函数(逐元素计算底为 10 的对数)

\[\begin{split}\\Out=log_{10} x\\\end{split}\]

参数

  • x (Tensor) – 输入的 Tensor。数据类型为 int32、int64、float16、bfloat16、float32、float64。

  • name (str,可选) - 具体用法请参见 Name,一般无需设置,默认值为 None。

返回

Tensor,Log10 算子底为 10 对数输出,数据类型与输入一致。

代码示例

>>> import paddle

>>> # example 1: x is a float
>>> x_i = paddle.to_tensor([[1.0], [10.0]])
>>> res = paddle.log10(x_i)
>>> res
Tensor(shape=[2, 1], dtype=float32, place=Place(cpu), stop_gradient=True,
[[0.],
 [1.]])

>>> # example 2: x is float32
>>> x_i = paddle.full(shape=[1], fill_value=10, dtype='float32')
>>> paddle.to_tensor(x_i)
>>> res = paddle.log10(x_i)
>>> res
Tensor(shape=[1], dtype=float32, place=Place(cpu), stop_gradient=True,
[1.])

>>> # example 3: x is float64
>>> x_i = paddle.full(shape=[1], fill_value=10, dtype='float64')
>>> paddle.to_tensor(x_i)
>>> res = paddle.log10(x_i)
>>> res
Tensor(shape=[1], dtype=float64, place=Place(cpu), stop_gradient=True,
[1.])