Merge pull request #5487 from ranqiu92/doc

Update annotations of layers.py.

python/paddle/trainer_config_helpers/layers.py

@@ -789,10 +789,9 @@ class MixedLayerType(LayerOutput):
         :type size: int
         :param act: Activation type.
         :type act: BaseActivation
-        :param bias_attr: The Bias Attribute. If the parameter is set to
-                          False or something not type of ParameterAttribute,
-                          no bias is defined. If the parameter is set to
-                          True, the bias is initialized to zero.
+        :param bias_attr: The bias attribute. If the parameter is set to False or an object
+                          whose type is not ParameterAttribute, no bias is defined. If the
+                          parameter is set to True, the bias is initialized to zero.
         :type bias_attr: ParameterAttribute | None | bool | Any
         :param layer_attr: Extra Layer Attribute.
         :type layer_attr: ExtraLayerAttribute or None
@@ -889,10 +888,9 @@ def mixed_layer(size=0,
                   then this function will just return layer's name.
     :param act: Activation Type. LinearActivation is the default.
     :type act: BaseActivation
-    :param bias_attr: The Bias Attribute. If the parameter is set to
-                      False or something not type of ParameterAttribute,
-                      no bias is defined. If the parameter is set to
-                      True, the bias is initialized to zero.
+    :param bias_attr: The bias attribute. If the parameter is set to False or an object
+                      whose type is not ParameterAttribute, no bias is defined. If the
+                      parameter is set to True, the bias is initialized to zero.
     :type bias_attr: ParameterAttribute | None | bool | Any
     :param layer_attr: The extra layer config. Default is None.
     :type layer_attr: ExtraLayerAttribute
@@ -1034,10 +1032,9 @@ def fc_layer(input,
     :type act: BaseActivation
     :param param_attr: The Parameter Attribute|list.
     :type param_attr: ParameterAttribute
-    :param bias_attr: The Bias Attribute. If the parameter is set to
-                      False or something not type of ParameterAttribute,
-                      no bias is defined. If the parameter is set to
-                      True, the bias is initialized to zero.
+    :param bias_attr: The bias attribute. If the parameter is set to False or an object
+                      whose type is not ParameterAttribute, no bias is defined. If the
+                      parameter is set to True, the bias is initialized to zero.
     :type bias_attr: ParameterAttribute | None | bool | Any
     :param layer_attr: Extra Layer config.
     :type layer_attr: ExtraLayerAttribute | None
@@ -1390,10 +1387,9 @@ def pooling_layer(input,
     :type pooling_type: BasePoolingType | None
     :param stride: The step size between successive pooling regions.
     :type stride: Int
-    :param bias_attr: The Bias Attribute. If the parameter is set to
-                      False or something not type of ParameterAttribute,
-                      no bias is defined. If the parameter is set to
-                      True, the bias is initialized to zero.
+    :param bias_attr: The bias attribute. If the parameter is set to False or an object
+                      whose type is not ParameterAttribute, no bias is defined. If the
+                      parameter is set to True, the bias is initialized to zero.
     :type bias_attr: ParameterAttribute | None | bool | Any
     :param layer_attr: The Extra Attributes for layer, such as dropout.
     :type layer_attr: ExtraLayerAttribute | None
@@ -1491,10 +1487,9 @@ def lstmemory(input,
     :type gate_act: BaseActivation
     :param state_act: state activation type, TanhActivation by default.
     :type state_act: BaseActivation
-    :param bias_attr: The Bias Attribute. If the parameter is set to
-                      False or something not type of ParameterAttribute,
-                      no bias is defined. If the parameter is set to
-                      True, the bias is initialized to zero.
+    :param bias_attr: The bias attribute. If the parameter is set to False or an object
+                      whose type is not ParameterAttribute, no bias is defined. If the
+                      parameter is set to True, the bias is initialized to zero.
     :type bias_attr: ParameterAttribute | None | bool | Any
     :param param_attr: Parameter Attribute.
     :type param_attr: ParameterAttribute | None | False
@@ -1617,10 +1612,9 @@ def grumemory(input,
                      This activation affects the :math:`z_t` and :math:`r_t`. It is the
                      :math:`\\sigma` in the above formula.
     :type gate_act: BaseActivation
-    :param bias_attr: The Bias Attribute. If the parameter is set to
-                      False or something not type of ParameterAttribute,
-                      no bias is defined. If the parameter is set to
-                      True, the bias is initialized to zero.
+    :param bias_attr: The bias attribute. If the parameter is set to False or an object
+                      whose type is not ParameterAttribute, no bias is defined. If the
+                      parameter is set to True, the bias is initialized to zero.
     :type bias_attr: ParameterAttribute | None | bool | Any
     :param param_attr: Parameter Attribute.
     :type param_attr: ParameterAttribute | None | False
@@ -1817,10 +1811,9 @@ def expand_layer(input,
     :type expand_as: LayerOutput
     :param name: The name of this layer. It is optional.
     :type name: basestring
-    :param bias_attr: The Bias Attribute. If the parameter is set to
-                      False or something not type of ParameterAttribute,
-                      no bias is defined. If the parameter is set to
-                      True, the bias is initialized to zero.
+    :param bias_attr: The bias attribute. If the parameter is set to False or an object
+                      whose type is not ParameterAttribute, no bias is defined. If the
+                      parameter is set to True, the bias is initialized to zero.
     :type bias_attr: ParameterAttribute | None | bool | Any
     :param expand_level: whether input layer is timestep(default) or sequence.
     :type expand_level: ExpandLevel
@@ -1939,10 +1932,9 @@ def seq_reshape_layer(input,
     :type act: BaseActivation
     :param layer_attr: extra layer attributes.
     :type layer_attr: ExtraLayerAttribute.
-    :param bias_attr: The Bias Attribute. If the parameter is set to
-                      False or something not type of ParameterAttribute,
-                      no bias is defined. If the parameter is set to
-                      True, the bias is initialized to zero.
+    :param bias_attr: The bias attribute. If the parameter is set to False or an object
+                      whose type is not ParameterAttribute, no bias is defined. If the
+                      parameter is set to True, the bias is initialized to zero.
     :type bias_attr: ParameterAttribute | None | bool | Any
     :return: LayerOutput object.
     :rtype: LayerOutput
@@ -2326,10 +2318,9 @@ def hsigmoid(input,
     :type num_classes: int | None
     :param name: The name of this layer. It is optional.
     :type name: basestring
-    :param bias_attr: The Bias Attribute. If the parameter is set to
-                      False or something not type of ParameterAttribute,
-                      no bias is defined. If the parameter is set to
-                      True, the bias is initialized to zero.
+    :param bias_attr: The bias attribute. If the parameter is set to False or an object
+                      whose type is not ParameterAttribute, no bias is defined. If the
+                      parameter is set to True, the bias is initialized to zero.
     :type bias_attr: ParameterAttribute | None | bool | Any
     :param param_attr: Parameter Attribute. None means default parameter.
     :type param_attr: ParameterAttribute | None
@@ -2469,10 +2460,9 @@ def img_conv_layer(input,
     :type dilation: int | tuple | list
     :param dilation_y: The y dimension of the dilation.
     :type dilation_y: int
-    :param bias_attr: The Bias Attribute. If the parameter is set to
-                      False or something not type of ParameterAttribute,
-                      no bias is defined. If the parameter is set to
-                      True, the bias is initialized to zero.
+    :param bias_attr: The bias attribute. If the parameter is set to False or an object
+                      whose type is not ParameterAttribute, no bias is defined. If the
+                      parameter is set to True, the bias is initialized to zero.
     :type bias_attr: ParameterAttribute | None | bool | Any
     :param num_channels: number of input channels. If None will be set
                         automatically from previous output.
@@ -3219,10 +3209,9 @@ def addto_layer(input, act=None, name=None, bias_attr=None, layer_attr=None):
     :type input: LayerOutput | list | tuple
     :param act: Activation Type. LinearActivation is the default.
     :type act: BaseActivation
-    :param bias_attr: The Bias Attribute. If the parameter is set to
-                      False or something not type of ParameterAttribute,
-                      no bias is defined. If the parameter is set to
-                      True, the bias is initialized to zero.
+    :param bias_attr: The bias attribute. If the parameter is set to False or an object
+                      whose type is not ParameterAttribute, no bias is defined. If the
+                      parameter is set to True, the bias is initialized to zero.
     :type bias_attr: ParameterAttribute | None | bool | Any
     :param layer_attr: Extra Layer attribute.
     :type layer_attr: ExtraLayerAttribute
@@ -3375,10 +3364,9 @@ def seq_concat_layer(a, b, act=None, name=None, layer_attr=None,
     :type act: BaseActivation
     :param layer_attr: Extra Layer Attribute.
     :type layer_attr: ExtraLayerAttribute
-    :param bias_attr: The Bias Attribute. If the parameter is set to
-                      False or something not type of ParameterAttribute,
-                      no bias is defined. If the parameter is set to
-                      True, the bias is initialized to zero.
+    :param bias_attr: The bias attribute. If the parameter is set to False or an object
+                      whose type is not ParameterAttribute, no bias is defined. If the
+                      parameter is set to True, the bias is initialized to zero.
     :type bias_attr: ParameterAttribute | None | bool | Any
     :return: LayerOutput object.
     :rtype: LayerOutput
@@ -3558,10 +3546,9 @@ def lstm_step_layer(input,
     :type gate_act: BaseActivation
     :param state_act: State Activation Type. TanhActivation is the default.
     :type state_act: BaseActivation
-    :param bias_attr: The Bias Attribute. If the parameter is set to
-                      False or something not type of ParameterAttribute,
-                      no bias is defined. If the parameter is set to
-                      True, the bias is initialized to zero.
+    :param bias_attr: The bias attribute. If the parameter is set to False or an object
+                      whose type is not ParameterAttribute, no bias is defined. If the
+                      parameter is set to True, the bias is initialized to zero.
     :type bias_attr: ParameterAttribute | None | bool | Any
     :param layer_attr: layer's extra attribute.
     :type layer_attr: ExtraLayerAttribute
@@ -3617,10 +3604,9 @@ def gru_step_layer(input,
     :param name: The name of this layer. It is optional.
     :param gate_act: Activation type of this layer's two gates. Default is Sigmoid.
     :type gate_act: BaseActivation
-    :param bias_attr: The Bias Attribute. If the parameter is set to
-                      False or something not type of ParameterAttribute,
-                      no bias is defined. If the parameter is set to
-                      True, the bias is initialized to zero.
+    :param bias_attr: The bias attribute. If the parameter is set to False or an object
+                      whose type is not ParameterAttribute, no bias is defined. If the
+                      parameter is set to True, the bias is initialized to zero.
     :type bias_attr: ParameterAttribute | None | bool | Any
     :param param_attr: the parameter_attribute for transforming the output_mem
                        from previous step.
@@ -3680,10 +3666,9 @@ def gru_step_naive_layer(input,
     :type act: BaseActivation
     :param gate_act: Activation type of this layer's two gates. Default is Sigmoid.
     :type gate_act: BaseActivation
-    :param bias_attr: The Bias Attribute. If the parameter is set to
-                      False or something not type of ParameterAttribute,
-                      no bias is defined. If the parameter is set to
-                      True, the bias is initialized to zero.
+    :param bias_attr: The bias attribute. If the parameter is set to False or an object
+                      whose type is not ParameterAttribute, no bias is defined. If the
+                      parameter is set to True, the bias is initialized to zero.
     :type bias_attr: ParameterAttribute | None | bool | Any
     :param param_attr:
     :param layer_attr:
@@ -3813,10 +3798,9 @@ def recurrent_layer(input,
     :type input: LayerOutput
     :param act: Activation type. TanhActivation is the default.
     :type act: BaseActivation
-    :param bias_attr: The Bias Attribute. If the parameter is set to
-                      False or something not type of ParameterAttribute,
-                      no bias is defined. If the parameter is set to
-                      True, the bias is initialized to zero.
+    :param bias_attr: The bias attribute. If the parameter is set to False or an object
+                      whose type is not ParameterAttribute, no bias is defined. If the
+                      parameter is set to True, the bias is initialized to zero.
     :type bias_attr: ParameterAttribute | None | bool | Any
     :param param_attr: parameter attribute.
     :type param_attr: ParameterAttribute
@@ -4806,10 +4790,9 @@ def tensor_layer(a,
     :type act: BaseActivation
     :param param_attr: The Parameter Attribute.
     :type param_attr: ParameterAttribute
-    :param bias_attr: The Bias Attribute. If the parameter is set to
-                      False or something not type of ParameterAttribute,
-                      no bias is defined. If the parameter is set to
-                      True, the bias is initialized to zero.
+    :param bias_attr: The bias attribute. If the parameter is set to False or an object
+                      whose type is not ParameterAttribute, no bias is defined. If the
+                      parameter is set to True, the bias is initialized to zero.
     :type bias_attr: ParameterAttribute | None | bool | Any
     :param layer_attr: Extra Layer config.
     :type layer_attr: ExtraLayerAttribute | None
@@ -4871,10 +4854,9 @@ def selective_fc_layer(input,
     :type act: BaseActivation
     :param param_attr: The Parameter Attribute.
     :type param_attr: ParameterAttribute
-    :param bias_attr: The Bias Attribute. If the parameter is set to
-                      False or something not type of ParameterAttribute,
-                      no bias is defined. If the parameter is set to
-                      True, the bias is initialized to zero.
+    :param bias_attr: The bias attribute. If the parameter is set to False or an object
+                      whose type is not ParameterAttribute, no bias is defined. If the
+                      parameter is set to True, the bias is initialized to zero.
     :type bias_attr: ParameterAttribute | None | bool | Any
     :param layer_attr: Extra Layer config.
     :type layer_attr: ExtraLayerAttribute | None
@@ -5546,10 +5528,9 @@ def nce_layer(input,
                              A uniform distribution will be used if not provided.
                              If not None, its length must be equal to num_classes.
     :type neg_distribution: list | tuple | collections.Sequence | None
-    :param bias_attr: The Bias Attribute. If the parameter is set to
-                      False or something not type of ParameterAttribute,
-                      no bias is defined. If the parameter is set to
-                      True, the bias is initialized to zero.
+    :param bias_attr: The bias attribute. If the parameter is set to False or an object
+                      whose type is not ParameterAttribute, no bias is defined. If the
+                      parameter is set to True, the bias is initialized to zero.
     :type bias_attr: ParameterAttribute | None | bool | Any
     :param layer_attr: Extra Layer Attribute.
     :type layer_attr: ExtraLayerAttribute
@@ -5773,20 +5754,21 @@ def cross_entropy(input,
     :param input: The first input layer.
     :type input: LayerOutput.
     :param label: The input label.
-    :type input: LayerOutput.
+    :type input: LayerOutput
     :param name: The name of this layer. It is optional.
-    :type name: None | basestring.
-    :param coeff: The cost is multiplied with coeff.
-                  The coefficient affects the gradient in the backward.
-    :type coeff: float.
+    :type name: basestring
+    :param coeff: The weight of the gradient in the back propagation.
+                  1.0 is the default.
+    :type coeff: float
     :param weight: The cost of each sample is multiplied with each weight.
                    The weight should be a layer with size=1. Note that gradient
                    will not be calculated for weight.
     :type weight: LayerOutout
-    :param layer_attr: Extra Layer Attribute.
+    :param layer_attr: The extra layer attribute. See ExtraLayerAttribute for
+                       details.
     :type layer_attr: ExtraLayerAttribute
     :return: LayerOutput object.
-    :rtype: LayerOutput.
+    :rtype: LayerOutput
     """
 
     ipts, parents = __cost_input__(input, label, weight)
@@ -5819,19 +5801,21 @@ def cross_entropy_with_selfnorm(input,
                                           label=label_layer)
 
     :param input: The first input layer.
-    :type input: LayerOutput.
+    :type input: LayerOutput
     :param label: The input label.
-    :type input: LayerOutput.
+    :type input: LayerOutput
     :param name: The name of this layer. It is optional.
-    :type name: None | basestring.
-    :param coeff: The coefficient affects the gradient in the backward.
-    :type coeff: float.
+    :type name: basestring
+    :param coeff: The weight of the gradient in the back propagation.
+                  1.0 is the default.
+    :type coeff: float
     :param softmax_selfnorm_alpha: The scale factor affects the cost.
-    :type softmax_selfnorm_alpha: float.
-    :param layer_attr: Extra Layer Attribute.
+    :type softmax_selfnorm_alpha: float
+    :param layer_attr: The extra layer attribute. See ExtraLayerAttribute for
+                       details.
     :type layer_attr: ExtraLayerAttribute
     :return: LayerOutput object.
-    :rtype: LayerOutput.
+    :rtype: LayerOutput
     """
     Layer(
         name=name,
@@ -5852,7 +5836,7 @@ def cross_entropy_with_selfnorm(input,
 @layer_support()
 def sum_cost(input, name=None, layer_attr=None):
     """
-    A loss layer which calculate the sum of the input as loss
+    A loss layer which calculates the sum of the input as loss.
 
     The example usage is:
 
@@ -5861,10 +5845,11 @@ def sum_cost(input, name=None, layer_attr=None):
        cost = sum_cost(input=input_layer)
 
     :param input: The input of this layer.
-    :type input: LayerOutput.
+    :type input: LayerOutput
     :param name: The name of this layer. It is optional.
-    :type name: None | basestring.
-    :param layer_attr: Extra Layer Attribute.
+    :type name: basestring
+    :param layer_attr: The extra layer attribute. See ExtraLayerAttribute for
+                       details.
     :type layer_attr: ExtraLayerAttribute
     :return: LayerOutput object.
     :rtype: LayerOutput.
@@ -5904,16 +5889,18 @@ def huber_regression_cost(input,
        cost = huber_regression_cost(input=input_layer, label=label_layer)
 
     :param input: The first input layer.
-    :type input: LayerOutput.
+    :type input: LayerOutput
     :param label: The input label.
-    :type input: LayerOutput.
+    :type input: LayerOutput
     :param name: The name of this layer. It is optional.
-    :type name: None | basestring.
+    :type name: basestring
     :param delta: The difference between the observed and predicted values.
-    :type delta: float.
-    :param coeff: The coefficient affects the gradient in the backward.
-    :type coeff: float.
-    :param layer_attr: Extra Layer Attribute.
+    :type delta: float
+    :param coeff: The weight of the gradient in the back propagation.
+                  1.0 is the default.
+    :type coeff: float
+    :param layer_attr: The extra layer attribute. See ExtraLayerAttribute for
+                       details.
     :type layer_attr: ExtraLayerAttribute
     :return: LayerOutput object.
     :rtype: LayerOutput.
@@ -5954,17 +5941,19 @@ def huber_classification_cost(input,
        cost = huber_classification_cost(input=input_layer, label=label_layer)
 
     :param input: The first input layer.
-    :type input: LayerOutput.
+    :type input: LayerOutput
     :param label: The input label.
-    :type input: LayerOutput.
+    :type input: LayerOutput
     :param name: The name of this layer. It is optional.
-    :type name: None | basestring.
-    :param coeff: The coefficient affects the gradient in the backward.
-    :type coeff: float.
-    :param layer_attr: Extra Layer Attribute.
+    :type name: basestring
+    :param coeff: The weight of the gradient in the back propagation.
+                  1.0 is the default.
+    :type coeff: float
+    :param layer_attr: The extra layer attribute. See ExtraLayerAttribute for
+                       details.
     :type layer_attr: ExtraLayerAttribute
     :return: LayerOutput object.
-    :rtype: LayerOutput.
+    :rtype: LayerOutput
     """
     assert isinstance(input, LayerOutput)
     if input.size is not None:
@@ -6001,10 +5990,12 @@ def multi_binary_label_cross_entropy(input,
     :param label: The input label.
     :type input: LayerOutput
     :param name: The name of this layer. It is optional.
-    :type name: None | basestring
-    :param coeff: The coefficient affects the gradient in the backward.
+    :type name: basestring
+    :param coeff: The weight of the gradient in the back propagation.
+                  1.0 is the default.
     :type coeff: float
-    :param layer_attr: Extra Layer Attribute.
+    :param layer_attr: The extra layer attribute. See ExtraLayerAttribute for
+                       details.
     :type layer_attr: ExtraLayerAttribute
     :return: LayerOutput object.
     :rtype: LayerOutput
@@ -6107,7 +6098,7 @@ def cross_entropy_over_beam(input, name=None):
 
     :param input: Input beams for this layer.
     :type input: BeamInput
-    :param name: The name of this layer.
+    :param name: The name of this layer. It is optional.
     :type name: basestring
     :return: LayerOutput object.
     :rtype: LayerOutput
@@ -6142,7 +6133,7 @@ def cross_entropy_over_beam(input, name=None):
 def smooth_l1_cost(input, label, name=None, coeff=1.0, layer_attr=None):
     """
     This is a L1 loss but more smooth. It requires that the
-    size of input and label are equal. The formula is as follows,
+    sizes of input and label are equal. The formula is as follows,
 
     .. math::
 
@@ -6154,8 +6145,9 @@ def smooth_l1_cost(input, label, name=None, coeff=1.0, layer_attr=None):
 
         smooth_{L1}(x) = \\begin{cases} 0.5x^2& \\text{if}  \\ |x| < 1 \\\\ |x|-0.5& \\text{otherwise} \end{cases}
 
-    More details can be found by referring to `Fast R-CNN
-    <https://arxiv.org/pdf/1504.08083v2.pdf>`_
+    Reference:
+        Fast R-CNN
+        https://arxiv.org/pdf/1504.08083v2.pdf
 
     The example usage is:
 
@@ -6169,10 +6161,12 @@ def smooth_l1_cost(input, label, name=None, coeff=1.0, layer_attr=None):
     :param label: The input label.
     :type input: LayerOutput
     :param name: The name of this layer. It is optional.
-    :type name: None | basestring
-    :param coeff: The coefficient affects the gradient in the backward.
+    :type name: basestring
+    :param coeff: The weight of the gradient in the back propagation.
+                  1.0 is the default.
     :type coeff: float
-    :param layer_attr: Extra Layer Attribute.
+    :param layer_attr: The extra layer attribute. See ExtraLayerAttribute for
+                       details.
     :type layer_attr: ExtraLayerAttribute
     :return: LayerOutput object.
     :rtype: LayerOutput
@@ -6194,12 +6188,12 @@ def smooth_l1_cost(input, label, name=None, coeff=1.0, layer_attr=None):
 @wrap_name_default()
 def multiplex_layer(input, name=None, layer_attr=None):
     """
-    This layer multiplex multiple layers according to the index,
-    which is provided by the first input layer.
-    inputs[0]: the index of the layer to output of size batchSize.
+    This layer multiplex multiple layers according to the indexes,
+    which are provided by the first input layer.
+    inputs[0]: the indexes of the layers to form the output of size batchSize.
     inputs[1:N]; the candidate output data.
-    For each index i from 0 to batchSize -1, the output is the i-th row of the
-    (index[i] + 1)-th layer.
+    For each index i from 0 to batchSize - 1, the i-th row of the output is the
+    the same to the i-th row of the (index[i] + 1)-th layer.
 
     For each i-th row of output:
     .. math::
@@ -6218,7 +6212,8 @@ def multiplex_layer(input, name=None, layer_attr=None):
     :type input: list of LayerOutput
     :param name: The name of this layer. It is optional.
     :type name: basestring
-    :param layer_attr: extra layer attributes.
+    :param layer_attr: The extra layer attribute. See ExtraLayerAttribute for
+                       details.
     :type layer_attr: ExtraLayerAttribute.
     :return: LayerOutput object.
     :rtype: LayerOutput
@@ -6322,14 +6317,14 @@ def row_conv_layer(input,
     :type context_len: int
     :param act: Activation Type. LinearActivation is the default.
     :type act: BaseActivation
-    :param param_attr: The Parameter Attribute. If None, the parameter will be
-                       initialized smartly. It's better to set it by yourself.
+    :param param_attr: The parameter attribute. See ParameterAttribute for
+                       details.
     :type param_attr: ParameterAttribute
-    :param layer_attr: Extra Layer config.
+    :param layer_attr: The extra layer attribute. See ExtraLayerAttribute for
+                       details.
     :type layer_attr: ExtraLayerAttribute | None
     :return: LayerOutput object.
     :rtype: LayerOutput
-
     """
     assert isinstance(input, LayerOutput)
     assert context_len > 0, "the context_len must be greatet than 0."
@@ -6354,7 +6349,7 @@ def prelu_layer(input,
                 param_attr=None,
                 layer_attr=None):
     """
-    The Parameter Relu activation that actives outputs with a learnable weight.
+    The Parametric Relu activation that actives outputs with a learnable weight.
 
     Reference:
         Delving Deep into Rectifiers: Surpassing Human-Level Performance on
@@ -6374,16 +6369,17 @@ def prelu_layer(input,
     :type name: basestring
     :param input: The input of this layer.
     :type input: LayerOutput
-    :param partial_sum: this parameter makes a group of inputs share a same weight.
+    :param partial_sum: this parameter makes a group of inputs share the same weight.
 
         - partial_sum = 1, indicates the element-wise activation: each element has a weight.
-        - partial_sum = number of elements in one channel, indicates the channel-wise activation, elements in a channel share a same weight.
-        - partial_sum = number of outputs, indicates all elements share a same weight.
+        - partial_sum = number of elements in one channel, indicates the channel-wise activation, elements in a channel share the same weight.
+        - partial_sum = number of outputs, indicates all elements share the same weight.
 
     :type partial_sum: int
     :param param_attr: The parameter attribute. See ParameterAttribute for details.
-    :type param_attr: ParameterAttribute | None
-    :param layer_attr: Extra layer configurations. Default is None.
+    :type param_attr: ParameterAttribute
+    :param layer_attr: The extra layer attribute. See ExtraLayerAttribute for
+                       details.
     :type layer_attr: ExtraLayerAttribute | None
     :return: LayerOutput object.
     :rtype: LayerOutput
@@ -6439,34 +6435,34 @@ def gated_unit_layer(input,
 
     :param input: The input of this layer.
     :type input: LayerOutput
-    :param size: output size of the gated unit.
+    :param size: The dimension of this layer's output.
     :type size: int
-    :param act: Activation type of the projected input. LinearActivation is the default.
+    :param act: Activation type of the projection. LinearActivation is the default.
     :type act: BaseActivation
     :param name: The name of this layer. It is optional.
     :type name: basestring
-    :param gate_attr: Attributes to tune the gate output, for example, error
-        clipping threshold, dropout and so on. See ExtraLayerAttribute for
-        more details.
+    :param gate_attr: The extra layer attribute of the gate. See ExtraLayerAttribute for
+                      details.
     :type gate_attr: ExtraLayerAttribute | None
-    :param gate_param_attr: Attributes to tune the learnable projected matrix
-        parameter of the gate.
-    :type gate_param_attr: ParameterAttribute | None
-    :param gate_bias_attr: Attributes to tune the learnable bias of the gate.
-    :type gate_bias_attr: ParameterAttribute | None
-    :param inproj_attr: Attributes to the tune the projected input, for
-        example, error clipping threshold, dropout and so on. See
-        ExtraLayerAttribute for more details.
+    :param gate_param_attr: The parameter attribute of the gate. See ParameterAttribute
+                            for details.
+    :type gate_param_attr: ParameterAttribute
+    :param gate_bias_attr: The bias attribute of the gate. If the parameter is set to False or
+                           an object whose type is not ParameterAttribute, no bias is defined.
+                           If the parameter is set to True, the bias is initialized to zero.
+    :type gate_bias_attr: ParameterAttribute | bool | None | Any
+    :param inproj_attr: Extra layer attributes of the projection. See ExtraLayerAttribute for
+                        details.
     :type inproj_attr: ExtraLayerAttribute | None
-    :param inproj_param_attr: Attributes to tune the learnable parameter of
-        the projection of input.
-    :type inproj_param_attr: ParameterAttribute | None
-    :param inproj_bias_attr: Attributes to tune the learnable bias of
-        projection of the input.
-    :type inproj_bias_attr: ParameterAttribute | None
-    :param layer_attr: Attributes to tune the final output of the gated unit,
-        for example, error clipping threshold, dropout and so on. See
-        ExtraLayerAttribute for more details.
+    :param inproj_param_attr: The parameter attribute of the projection. See ParameterAttribute
+                              for details.
+    :type inproj_param_attr: ParameterAttribute
+    :param inproj_bias_attr: The bias attribute of the projection. If the parameter is set to False
+                             or an object whose type is not ParameterAttribute, no bias is defined.
+                             If the parameter is set to True, the bias is initialized to zero.
+    :type inproj_bias_attr: ParameterAttribute | bool | None | Any
+    :param layer_attr: Extra layer attribute of the product. See ExtraLayerAttribute for
+                       details.
     :type layer_attr: ExtraLayerAttribute | None
     :return: LayerOutput object.
     :rtype: LayerOutput
@@ -6662,9 +6658,9 @@ def clip_layer(input, min, max, name=None):
     :param input: The input of this layer.
     :type input: LayerOutput.
     :param min: The lower threshold for clipping.
-    :type min: double
+    :type min: float
     :param max: The upper threshold for clipping.
-    :type max: double
+    :type max: float
     :return: LayerOutput object.
     :rtype: LayerOutput
     """
@@ -6712,7 +6708,6 @@ def seq_slice_layer(input, starts, ends, name=None):
     :type ends: LayerOutput | None
     :return: LayerOutput object.
     :rtype: LayerOutput
-
     """
 
     assert isinstance(input, LayerOutput), (
@@ -6833,20 +6828,21 @@ def img_conv3d_layer(input,
     :param padding: The numbers of padding along three axises. If the parameter is set to
                     one integer, they will be same.
     :type padding: int | tuple | list
-    :param bias_attr: The Bias Attribute. If the parameter is set to
-                      False or something not type of ParameterAttribute,
-                      no bias is defined. If the parameter is set to
-                      True, the bias is initialized to zero.
+    :param bias_attr: The bias attribute. If the parameter is set to False or an object
+                      whose type is not ParameterAttribute, no bias is defined. If the
+                      parameter is set to True, the bias is initialized to zero.
     :type bias_attr: ParameterAttribute | None | bool | Any
     :param num_channels: The number of input channels. If the parameter is not set or
                          set to None,  its actual value will be automatically set to
                          the channels number of the input .
     :type num_channels: int
-    :param param_attr: The parameter attribute of the convolution.
+    :param param_attr: The parameter attribute of the convolution. See ParameterAttribute for
+                       details.
     :type param_attr: ParameterAttribute
     :param shared_biases: Whether biases will be shared between filters or not.
     :type shared_biases: bool
-    :param layer_attr: Extra layer attributes.
+    :param layer_attr: The extra layer attributes. See ExtraLayerAttribute for
+                       details.
     :type layer_attr: ExtraLayerAttribute
     :param trans: True if it is a convTransLayer, False if it is a convLayer
     :type trans: bool
@@ -6953,12 +6949,12 @@ def scale_shift_layer(input, name=None, param_attr=None, bias_attr=None):
     :type name: basestring
     :param input: The input of this layer.
     :type input: LayerOutput
-    :param param_attr: The parameter attribute of scaling.
+    :param param_attr: The parameter attribute of scaling. See ParameterAttribute for
+                      details.
     :type param_attr: ParameterAttribute
-    :param bias_attr: The Bias Attribute. If the parameter is set to
-                      False or something not type of ParameterAttribute,
-                      no bias is defined. If the parameter is set to
-                      True, the bias is initialized to zero.
+    :param bias_attr: The bias attribute. If the parameter is set to False or an object
+                      whose type is not ParameterAttribute, no bias is defined. If the
+                      parameter is set to True, the bias is initialized to zero.
     :type bias_attr: ParameterAttribute | None | bool | Any
     :return: LayerOutput object.
     :rtype: LayerOutput
@@ -7016,10 +7012,9 @@ def sub_seq_layer(input, offsets, sizes, act=None, bias_attr=None, name=None):
     :type sizes: LayerOutput
     :param act: Activation type, LinearActivation is the default.
     :type act: BaseActivation.
-    :param bias_attr: The Bias Attribute. If the parameter is set to
-                      False or something not type of ParameterAttribute,
-                      no bias is defined. If the parameter is set to
-                      True, the bias is initialized to zero.
+    :param bias_attr: The bias attribute. If the parameter is set to False or an object
+                      whose type is not ParameterAttribute, no bias is defined. If the
+                      parameter is set to True, the bias is initialized to zero.
     :type bias_attr: ParameterAttribute | None | bool | Any
     :return: LayerOutput object.
     :rtype: LayerOutput