[Docathon][Update Doc No.21] update activation (#7297)

Author: Echo-Nie

docs/api_guides/low_level/layers/activations.rst

@@ -1,28 +1,40 @@
 .. _api_guide_activations:
 
-####
+###################
 激活函数
-####
+###################
 
 激活函数将非线性的特性引入到神经网络当中。
 
-PaddlePaddle Fluid 对大部分的激活函数进行了支持，其中有:
-
-:ref:`cn_api_fluid_layers_relu`, :ref:`cn_api_fluid_layers_tanh`, :ref:`cn_api_fluid_layers_sigmoid`, :ref:`cn_api_fluid_layers_elu`, :ref:`cn_api_fluid_layers_relu6`, :ref:`cn_api_fluid_layers_pow`, :ref:`cn_api_fluid_layers_stanh`, :ref:`cn_api_fluid_layers_hard_sigmoid`, :ref:`cn_api_fluid_layers_swish`, :ref:`cn_api_fluid_layers_prelu`, :ref:`cn_api_fluid_layers_brelu`, :ref:`cn_api_fluid_layers_leaky_relu`, :ref:`cn_api_fluid_layers_soft_relu`, :ref:`cn_api_fluid_layers_thresholded_relu`, :ref:`cn_api_fluid_layers_maxout`, :ref:`cn_api_fluid_layers_logsigmoid`, :ref:`cn_api_fluid_layers_hard_shrink`, :ref:`cn_api_fluid_layers_softsign`, :ref:`cn_api_fluid_layers_softplus`, :ref:`cn_api_fluid_layers_tanh_shrink`, :ref:`cn_api_fluid_layers_softshrink`, :ref:`cn_api_fluid_layers_exp`。
-
-
-**Fluid 提供了两种使用激活函数的方式：**
-
-- 如果一个层的接口提供了 :code:`act` 变量（默认值为 None），我们可以通过该变量指定该层的激活函数类型。该方式支持常见的激活函数: :code:`relu`, :code:`tanh`, :code:`sigmoid`, :code:`identity`。
-
-.. code-block:: python
-
-    conv2d = fluid.layers.conv2d(input=data, num_filters=2, filter_size=3, act="relu")
-
-
-- Fluid 为每个 Activation 提供了接口，我们可以显式的对它们进行调用。
+PaddlePaddle 对大部分的激活函数进行了支持，其中有:
+
+* :ref:`cn_api_paddle_nn_functional_elu`
+* :ref:`cn_api_paddle_exp`
+* :ref:`cn_api_paddle_nn_functional_hardsigmoid`
+* :ref:`cn_api_paddle_nn_functional_hardshrink`
+* :ref:`cn_api_paddle_nn_functional_leaky_relu`
+* :ref:`cn_api_paddle_nn_functional_log_sigmoid`
+* :ref:`cn_api_paddle_nn_functional_maxout`
+* :ref:`cn_api_paddle_pow`
+* :ref:`cn_api_paddle_nn_functional_prelu`
+* :ref:`cn_api_paddle_nn_functional_relu`
+* :ref:`cn_api_paddle_nn_functional_relu6`
+* :ref:`cn_api_paddle_nn_functional_sigmoid`
+* :ref:`cn_api_paddle_nn_functional_softplus`
+* :ref:`cn_api_paddle_nn_functional_softshrink`
+* :ref:`cn_api_paddle_nn_functional_softsign`
+* :ref:`cn_api_paddle_stanh`
+* :ref:`cn_api_paddle_nn_functional_swish`
+* :ref:`cn_api_paddle_tanh`
+* :ref:`cn_api_paddle_nn_functional_thresholded_relu`
+* :ref:`cn_api_paddle_nn_functional_tanhshrink`
+
+
+**PaddlePaddle 应用激活函数的方式如下：**
+
+PaddlePaddle 为每个 Activation 提供了接口，可以显式调用。以下是一个示例，展示如何在卷积操作之后应用 ReLU 激活函数：
 
 .. code-block:: python
 
-    conv2d = fluid.layers.conv2d(input=data, num_filters=2, filter_size=3)
-    relu1 = fluid.layers.relu(conv2d)
+    conv2d = paddle.nn.functional.conv2d(x, weight, stride=1, padding=1) # 卷积
+    relu1 = paddle.nn.functional.relu(conv2d) # 使用 ReLu 激活函数

docs/api_guides/low_level/layers/activations_en.rst

@@ -6,44 +6,35 @@ Activation Function
 
 The activation function incorporates non-linearity properties into the neural network.
 
-PaddlePaddle Fluid supports most of the activation functions, including:
-
-:ref:`api_fluid_layers_relu`,
-:ref:`api_fluid_layers_tanh`,
-:ref:`api_fluid_layers_sigmoid`,
-:ref:`api_fluid_layers_elu`,
-:ref:`api_fluid_layers_relu6`,
-:ref:`api_fluid_layers_pow`,
-:ref:`api_fluid_layers_stanh`,
-:ref:`api_fluid_layers_hard_sigmoid`,
-:ref:`api_fluid_layers_swish`,
-:ref:`api_fluid_layers_prelu`,
-:ref:`api_fluid_layers_brelu`,
-:ref:`api_fluid_layers_leaky_relu`,
-:ref:`api_fluid_layers_soft_relu`,
-:ref:`api_fluid_layers_thresholded_relu`,
-:ref:`api_fluid_layers_maxout`,
-:ref:`api_fluid_layers_logsigmoid`,
-:ref:`api_fluid_layers_hard_shrink`,
-:ref:`api_fluid_layers_softsign`,
-:ref:`api_fluid_layers_softplus`,
-:ref:`api_fluid_layers_tanh_shrink`,
-:ref:`api_fluid_layers_softshrink`,
-:ref:`api_fluid_layers_exp`.
-
-
-**Fluid provides two ways to use the activation function:**
-
-- If a layer interface provides :code:`act` variables (default None), we can specify the type of layer activation function through this parameter. This mode supports common activation functions :code:`relu`, :code:`tanh`, :code:`sigmoid`, :code:`identity`.
+PaddlePaddle supports most of the activation functions, including:
+
+* :ref:`api_paddle_nn_functional_elu`
+* :ref:`api_paddle_exp`
+* :ref:`api_paddle_nn_functional_hardsigmoid`
+* :ref:`api_paddle_nn_functional_hardshrink`
+* :ref:`api_paddle_nn_functional_leaky_relu`
+* :ref:`api_paddle_nn_functional_log_sigmoid`
+* :ref:`api_paddle_nn_functional_maxout`
+* :ref:`api_paddle_pow`
+* :ref:`api_paddle_nn_functional_prelu`
+* :ref:`api_paddle_nn_functional_relu`
+* :ref:`api_paddle_nn_functional_relu6`
+* :ref:`api_paddle_tensor_sigmoid`
+* :ref:`api_paddle_nn_functional_softplus`
+* :ref:`api_paddle_nn_functional_softshrink`
+* :ref:`api_paddle_nn_functional_softsign`
+* :ref:`api_paddle_stanh`
+* :ref:`api_paddle_nn_functional_swish`
+* :ref:`api_paddle_tanh`
+* :ref:`api_paddle_nn_functional_thresholded_relu`
+* :ref:`api_paddle_nn_functional_tanhshrink`
+
+
+**The way to apply activation functions in PaddlePaddle is as follows:**
+
+PaddlePaddle provides a dedicated interface for each activation function, allowing users to explicitly invoke them as needed. Below is an example of applying the ReLU activation function after a convolution operation:
 
 .. code-block:: python
 
-    conv2d = fluid.layers.conv2d(input=data, num_filters=2, filter_size=3, act="relu")
-
-
-- Fluid provides an interface for each Activation, and we can explicitly call it.
-
-.. code-block:: python
-
-    conv2d = fluid.layers.conv2d(input=data, num_filters=2, filter_size=3)
-    relu1 = fluid.layers.relu(conv2d)
+    conv2d = paddle.nn.functional.conv2d(x, weight, stride=1, padding=1)  # Convolution operation
+    relu1 = paddle.nn.functional.relu(conv2d)  # Applying the ReLU activation function