未验证 提交 82a9850f 编写于 作者: W WangXi 提交者: GitHub

【doc】sign & tanh (#2402)

* refine sign tanh api, test=develop

* Add Tanh, test=develop

* fix en, test=develop
上级 9cfbc979
......@@ -8,8 +8,9 @@ activation
activation/ELU.rst
activation/GELU.rst
activation/Hardshrink.rst
activation/Tanh.rst
activation/Hardtanh.rst
activation/PReLU.rst
activation/ReLU.rst
activation/LogSigmoid.rst
activation/Softmax.rst
activation/Softmax.rst
\ No newline at end of file
.. THIS FILE IS GENERATED BY `gen_doc.{py|sh}`
!DO NOT EDIT THIS FILE MANUALLY!
.. _api_nn_activation_Tanh:
Tanh
---------
.. autoclass:: paddle.nn.layer.activation.Tanh
:members:
:inherited-members:
:noindex:
......@@ -23,6 +23,7 @@ math
math/mm.rst
math/mul.rst
math/pow.rst
math/sign.rst
math/sin.rst
math/sqrt.rst
math/sum.rst
......
.. THIS FILE IS GENERATED BY `gen_doc.{py|sh}`
!DO NOT EDIT THIS FILE MANUALLY!
.. _api_tensor_math_sign:
sign
------
.. autofunction:: paddle.tensor.math.sign
:noindex:
......@@ -5,12 +5,6 @@ sign
.. py:function:: paddle.fluid.layers.sign(x)
:alias_main: paddle.sign
:alias: paddle.sign,paddle.tensor.sign,paddle.tensor.math.sign
:old_api: paddle.fluid.layers.sign
此OP对输入x中每个元素进行正负判断,并且输出正负判断值:1代表正,-1代表负,0代表零。
参数:
......
......@@ -11,6 +11,7 @@ activation
activation_cn/ELU_cn.rst
activation_cn/GELU_cn.rst
activation_cn/Hardshrink_cn.rst
activation_cn/Tanh_cn.rst
activation_cn/Hardtanh_cn.rst
activation_cn/PRelu_cn.rst
activation_cn/ReLU_cn.rst
......@@ -18,4 +19,4 @@ activation
activation_cn/Softmax_cn.rst
activation_cn/LogSoftmax_cn.rst
activation_cn/Sigmoid_cn.rst
activation_cn/LogSigmoid_cn.rst
activation_cn/LogSigmoid_cn.rst
\ No newline at end of file
.. _cn_api_nn_Tanh:
Tanh
-------------------------------
.. py:class:: paddle.nn.Tanh(name=None)
Tanh激活层
.. math::
Tanh(x) = \frac{e^{x} - e^{-x}}{e^{x} + e^{-x}}
参数
::::::::::
- name (str, 可选) - 操作的名称(可选,默认值为None)。更多信息请参见 :ref:`api_guide_Name`。
形状:
- input: 任意形状的Tensor。
- output: 和input具有相同形状的Tensor。
代码示例
:::::::::
.. code-block:: python
import paddle
import numpy as np
paddle.disable_static()
x = paddle.to_tensor(np.array([-0.4, -0.2, 0.1, 0.3]))
m = paddle.nn.Tanh()
out = m(x)
print(out.numpy())
# [-0.37994896 -0.19737532 0.09966799 0.29131261]
\ No newline at end of file
.. _cn_api_tensor_cn_sign:
.. _cn_api_tensor_sign:
sign
-------------------------------
:doc_source: paddle.fluid.layers.sign
.. py:function:: paddle.sign(x, name=None)
此OP对输入x中每个元素进行正负判断,并且输出正负判断值:1代表正,-1代表负,0代表零。
参数:
- **x** (Tensor) – 进行正负值判断的多维Tensor,数据类型为 float16, float32或float64。
- **name** (str,可选) – 具体用法请参见 :ref:`api_guide_Name` ,一般无需设置,默认值为None。
返回:输出正负号Tensor,数据的shape大小及数据类型和输入 ``x`` 一致。
返回类型:Tensor
**代码示例**
.. code-block:: python
import numpy as np
import paddle
data = np.array([3.0, 0.0, -2.0, 1.7], dtype='float32')
paddle.disable_static()
x = paddle.to_tensor(data)
out = paddle.sign(x=x)
print(out) # [1.0, 0.0, -1.0, 1.0]
......@@ -3,44 +3,35 @@
tanh
-------------------------------
.. py:function:: paddle.tanh(x, name=None, out=None)
:alias_main: paddle.tanh
:alias: paddle.tanh,paddle.tensor.tanh,paddle.tensor.math.tanh
:update_api: paddle.fluid.layers.tanh
.. py:function:: paddle.tanh(x, name=None)
tanh 激活函数
.. math::
out = \frac{e^{x} - e^{-x}}{e^{x} + e^{-x}}
out = \frac{e^{x} - e^{-x}}{e^{x} + e^{-x}}
参数:
- **x** (Variable) - 支持任意维度的Tensor。数据类型为float32,float64或float16。
- **name** (str,可选) – 具体用法请参见 :ref:`api_guide_Name` ,一般无需设置,默认值为None。
- **out** (Variable, 可选) – 指定存储运算结果的Tensor。如果设置为None或者不设置,将创建新的Tensor存储运算结果,默认值为None。
- **x** (Tensor) - Tanh算子的输入, 多维Tensor,数据类型为 float16,float32或float64。
- **name** (str, 可选) - 该层名称(可选,默认为None)。具体用法请参见 :ref:`api_guide_Name`。
返回:返回类型为Variable(Tensor|LoDTensor), 数据类型同输入一致。
返回: tanh的输出Tensor,和输入有着相同类型和shape。
返回类型: Tensor
**代码示例**:
.. code-block:: python
import numpy as np
import paddle
import paddle.fluid as fluid
inputs = fluid.layers.data(name="x", shape = [3], dtype='float32')
output = paddle.tanh(inputs)
import paddle
import numpy as np
exe = fluid.Executor(fluid.CPUPlace())
exe.run(fluid.default_startup_program())
paddle.disable_static()
img = np.array([0, 0.5, 0.3]).astype(np.float32)
x_data = np.array([-0.4, -0.2, 0.1, 0.3])
x = paddle.to_tensor(x_data)
out = paddle.tanh(x)
print(out.numpy())
# [-0.37994896 -0.19737532 0.09966799 0.29131261]
res = exe.run(fluid.default_main_program(), feed={'x':img}, fetch_list=[output])
print(res)
# [array([0., 0.46211717, 0.2913126], dtype=float32)]
Markdown is supported
0% .
You are about to add 0 people to the discussion. Proceed with caution.
先完成此消息的编辑!
想要评论请 注册