diff --git a/develop/doc/api/v2/config/layer.html b/develop/doc/api/v2/config/layer.html index 880901bf6e7e99f39aa7e6288fed4defc73fb040..5f78f5798f0f417a8134aebe82c481dfd48ce87a 100644 --- a/develop/doc/api/v2/config/layer.html +++ b/develop/doc/api/v2/config/layer.html @@ -208,7 +208,7 @@

The example usage is:

fc = fc(input=layer,
               size=1024,
-              act=paddle.v2.Activation.Linear(),
+              act=paddle.v2.activation.Linear(),
               bias_attr=False)
@@ -225,7 +225,7 @@
  • name (basestring) – The Layer Name.
  • input (paddle.v2.config_base.Layer|list|tuple) – The input layer. Could be a list/tuple of input layer.
  • size (int) – The layer dimension.
    • -
  • act (paddle.v2.Activation.Base) – Activation Type. Default is tanh.
    • +
  • act (paddle.v2.activation.Base) – Activation Type. Default is tanh.
  • param_attr (paddle.v2.attr.ParameterAttribute) – The Parameter Attribute|list.
  • bias_attr (paddle.v2.attr.ParameterAttribute|None|Any) – The Bias Attribute. If no bias, then pass False or something not type of paddle.v2.attr.ParameterAttribute. None will get a @@ -255,7 +255,7 @@ of this layer maybe sparse. It requires an additional input to indicate several selected columns for output. If the selected columns is not specified, selective_fc acts exactly like fc.

    The simple usage is:

    -
    sel_fc = selective_fc(input=input, size=128, act=paddle.v2.Activation.Tanh())
+
    sel_fc = selective_fc(input=input, size=128, act=paddle.v2.activation.Tanh())
 
    
 
    
 
@@ -269,7 +269,7 @@ specified, selective_fc acts exactly like fc.
    
 sparse binary matrix, and treat as the mask of selective fc.
 If is None, acts exactly like fc.
  • size (int) – The layer dimension.
    • 
-
  • act (paddle.v2.Activation.Base) – Activation Type. Default is tanh.
    • 
+
  • act (paddle.v2.activation.Base) – Activation Type. Default is tanh.
  • param_attr (paddle.v2.attr.ParameterAttribute) – The Parameter Attribute.
  • bias_attr (paddle.v2.attr.ParameterAttribute|None|Any) – The Bias Attribute. If no bias, then pass False or
 something not type of paddle.v2.attr.ParameterAttribute. None will get a
@@ -469,7 +469,7 @@ rest channels will be processed by rest group of filters.
    
                       num_channels=8,
                       num_filters=16, stride=1,
                       bias_attr=False,
-                      act=paddle.v2.Activation.Relu())
+                      act=paddle.v2.activation.Relu())
 
 
 
    • 
 
 
 
    
@@ -485,7 +485,7 @@ two image dimension.
 currently supports rectangular filters, the filter’s
 shape will be (filter_size, filter_size_y).
  • num_filters – Each filter group’s number of filter
    • 
-
  • act (paddle.v2.Activation.Base) – Activation type. Default is tanh
    • 
+
  • act (paddle.v2.activation.Base) – Activation type. Default is tanh
  • groups (int) – Group size of filters.
  • stride (int|tuple|list) – The x dimension of the stride. Or input a tuple for two image
 dimension.
    • 
@@ -780,7 +780,7 @@ y_i &\gets \gamma \hat{x_i} + \beta \qquad &//\ scale\ and\ shift\end{sp
 
    The details of batch normalization please refer to this
 paper.
    The example usage is:
    
-
    norm = batch_norm(input=net, act=paddle.v2.Activation.Relu())
+
    norm = batch_norm(input=net, act=paddle.v2.activation.Relu())
 
    
 
    
 
    
 
 
 
 
    
@@ -800,7 +800,7 @@ automaticly select cudnn_batch_norm for GPU and
 batch_norm for CPU. Otherwise, select batch norm
 type based on the specified type. If you use cudnn_batch_norm,
 we suggested you use latest version, such as v5.1.
-
  • act (paddle.v2.Activation.Base) – Activation Type. Better be relu. Because batch
+
  • act (paddle.v2.activation.Base) – Activation Type. Better be relu. Because batch
 normalization will normalize input near zero.
  • num_channels (int) – num of image channels or previous layer’s number of
 filters. None will automatically get from layer’s
@@ -923,7 +923,7 @@ out_{i} = act(in_{i} + out_{i+1} * W) \ \ \text{for} \ start <= i < end\en
 
    • 
@@ -1130,7 +1130,7 @@ Neural Turning Machine like models.
    def step(input):
     output = fc(input=layer,
                       size=1024,
-                      act=paddle.v2.Activation.Linear(),
+                      act=paddle.v2.activation.Linear(),
                       bias_attr=False)
     return output
 
@@ -1223,10 +1223,10 @@ output is \(o_t\), which name is ‘state’ a
 state.size.
 
  • input (paddle.v2.config_base.Layer) – input layer. \(Wx_t + Wh_{t-1}\)
    • 
 
  • state (paddle.v2.config_base.Layer) – State Layer. \(c_{t-1}\)
    • 
-
  • act (paddle.v2.Activation.Base) – Activation type. Default is tanh
    • 
-
  • gate_act (paddle.v2.Activation.Base) – Gate Activation Type. Default is sigmoid, and should
+
  • act (paddle.v2.activation.Base) – Activation type. Default is tanh
    • 
+
  • gate_act (paddle.v2.activation.Base) – Gate Activation Type. Default is sigmoid, and should
 be sigmoid only.
    • 
-
  • state_act (paddle.v2.Activation.Base) – State Activation Type. Default is sigmoid, and should
+
  • state_act (paddle.v2.activation.Base) – State Activation Type. Default is sigmoid, and should
 be sigmoid only.
    • 
 
  • bias_attr (paddle.v2.attr.ParameterAttribute) – Bias Attribute.
    • 
 
  • layer_attr (paddle.v2.attr.ExtraAttribute) – layer’s extra attribute.
    • 
@@ -1428,7 +1428,7 @@ Each inputs is a projection or operator.
    
 
  • size (int) – layer size.
    • 
 
  • input – inputs layer. It is an optional parameter. If set,
 then this function will just return layer’s name.
    • 
-
  • act (paddle.v2.Activation.Base) – Activation Type.
    • 
+
  • act (paddle.v2.activation.Base) – Activation Type.
    • 
 
  • bias_attr (paddle.v2.attr.ParameterAttribute or None or bool) – The Bias Attribute. If no bias, then pass False or
 something not type of paddle.v2.attr.ParameterAttribute. None will get a
 default Bias.
    • 
@@ -1925,7 +1925,7 @@ Inputs can be list of paddle.v2.config_base.Layer or list of projection.
    
 
    
@@ -1969,7 +1969,7 @@ Inputs can be list of paddle.v2.config_base.Layer or list of projection.
  • name (basestring) – Layer name.
  • a (paddle.v2.config_base.Layer) – input sequence layer
  • b (paddle.v2.config_base.Layer) – input sequence layer
    • 
-
  • act (paddle.v2.Activation.Base) – Activation type.
    • 
+
  • act (paddle.v2.activation.Base) – Activation type.
  • layer_attr (paddle.v2.attr.ExtraAttribute) – Extra Layer Attribute.
  • bias_attr (paddle.v2.attr.ParameterAttribute or None or bool) – The Bias Attribute. If no bias, then pass False or
 something not type of paddle.v2.attr.ParameterAttribute. None will get a
@@ -2202,7 +2202,7 @@ output sequence has T*M/N instances, the dimension of each instance is N.
    
 
  • input (paddle.v2.config_base.Layer) – Input layer.
  • reshape_size (int) – the size of reshaped sequence.
  • name (basestring) – Layer name.
    • 
-
  • act (paddle.v2.Activation.Base) – Activation type.
    • 
+
  • act (paddle.v2.activation.Base) – Activation type.
  • layer_attr (paddle.v2.attr.ExtraAttribute) – extra layer attributes.
  • bias_attr (paddle.v2.attr.ParameterAttribute or None or bool) – The Bias Attribute. If no bias, then pass False or
 something not type of paddle.v2.attr.ParameterAttribute. None will get a
@@ -2236,7 +2236,7 @@ default Bias.
    • 
 and \(f\) is activation function.
    The example usage is:
    addto = addto(input=[layer1, layer2],
-                    act=paddle.v2.Activation.Relu(),
+                    act=paddle.v2.activation.Relu(),
                     bias_attr=False)
 
    
 
    
@@ -2258,7 +2258,7 @@ Please refer to dropout for details.
  • name (basestring) – Layer name.
  • input (paddle.v2.config_base.Layer|list|tuple) – Input layers. It could be a paddle.v2.config_base.Layer or list/tuple of
 paddle.v2.config_base.Layer.
    • 
-
  • act (paddle.v2.Activation.Base) – Activation Type, default is tanh.
    • 
+
  • act (paddle.v2.activation.Base) – Activation Type, default is tanh.
  • bias_attr (paddle.v2.attr.ParameterAttribute|bool) – Bias attribute. If False, means no bias. None is default
 bias.
  • layer_attr (paddle.v2.attr.ExtraAttribute) – Extra Layer attribute.
    • 
@@ -2560,7 +2560,7 @@ For example, each sample:
  • a (paddle.v2.config_base.Layer) – Input layer a.
  • b (paddle.v2.config_base.Layer) – input layer b.
  • size (int.) – the layer dimension.
    • 
-
  • act (paddle.v2.Activation.Base) – Activation Type. Default is tanh.
    • 
+
  • act (paddle.v2.activation.Base) – Activation Type. Default is tanh.
  • param_attr (paddle.v2.attr.ParameterAttribute) – The Parameter Attribute.
  • bias_attr (paddle.v2.attr.ParameterAttribute|None|Any) – The Bias Attribute. If no bias, then pass False or
 something not type of paddle.v2.attr.ParameterAttribute. None will get a
@@ -3342,7 +3342,7 @@ A fast and simple algorithm for training neural probabilistic language models.label (paddle.v2.config_base.Layer) – label layer
  • weight (paddle.v2.config_base.Layer) – weight layer, can be None(default)
  • num_classes (int) – number of classes.
    • 
-
  • act (paddle.v2.Activation.Base) – Activation, default is Sigmoid.
    • 
+
  • act (paddle.v2.activation.Base) – Activation, default is Sigmoid.
  • param_attr (paddle.v2.attr.ParameterAttribute) – The Parameter Attribute|list.
  • num_neg_samples (int) – number of negative samples. Default is 10.
  • neg_distribution (list|tuple|collections.Sequence|None) – The distribution for generating the random negative labels.
diff --git a/develop/doc_cn/api/v2/config/layer.html b/develop/doc_cn/api/v2/config/layer.html
index 7871764e0638de634f9917d3c698a2e16fff4e85..28f21a2ebfa21b60ab090ec43bf537daae62f494 100644
--- a/develop/doc_cn/api/v2/config/layer.html
+++ b/develop/doc_cn/api/v2/config/layer.html
@@ -215,7 +215,7 @@
 
    The example usage is:
    
 
    fc = fc(input=layer,
               size=1024,
-              act=paddle.v2.Activation.Linear(),
+              act=paddle.v2.activation.Linear(),
               bias_attr=False)
 
    
 
    
@@ -232,7 +232,7 @@
 
  • name (basestring) – The Layer Name.
  • input (paddle.v2.config_base.Layer|list|tuple) – The input layer. Could be a list/tuple of input layer.
  • size (int) – The layer dimension.
    • 
-
  • act (paddle.v2.Activation.Base) – Activation Type. Default is tanh.
    • 
+
  • act (paddle.v2.activation.Base) – Activation Type. Default is tanh.
  • param_attr (paddle.v2.attr.ParameterAttribute) – The Parameter Attribute|list.
  • bias_attr (paddle.v2.attr.ParameterAttribute|None|Any) – The Bias Attribute. If no bias, then pass False or
 something not type of paddle.v2.attr.ParameterAttribute. None will get a
@@ -262,7 +262,7 @@ of this layer maybe sparse. It requires an additional input to indicate
 several selected columns for output. If the selected columns is not
 specified, selective_fc acts exactly like fc.
    
 
    The simple usage is:
    
-
    sel_fc = selective_fc(input=input, size=128, act=paddle.v2.Activation.Tanh())
+
    sel_fc = selective_fc(input=input, size=128, act=paddle.v2.activation.Tanh())
 
    
 
    
 
    • 
 
 
    Parameters:
      
 
    • input (paddle.v2.config_base.Layer) – Input Layer
      • 
-
    • act (paddle.v2.Activation.Base) – activation.
      • 
+
    • act (paddle.v2.activation.Base) – activation.
      • 
 
    • bias_attr (paddle.v2.attr.ParameterAttribute) – bias attribute.
      • 
 
    • param_attr (paddle.v2.attr.ParameterAttribute) – parameter attribute.
      • 
 
    • name (basestring) – name of the layer
      • 
@@ -970,9 +970,9 @@ more details about LSTM.
      
 
    • name (basestring) – The lstmemory layer name.
      • 
 
    • input (paddle.v2.config_base.Layer) – input layer name.
      • 
 
    • reverse (bool) – is sequence process reversed or not.
      • 
-
    • act (paddle.v2.Activation.Base) – activation type, paddle.v2.Activation.Tanh by default. \(h_t\)
      • 
-
    • gate_act (paddle.v2.Activation.Base) – gate activation type, paddle.v2.Activation.Sigmoid by default.
      • 
-
    • state_act (paddle.v2.Activation.Base) – state activation type, paddle.v2.Activation.Tanh by default.
      • 
+
    • act (paddle.v2.activation.Base) – activation type, paddle.v2.activation.Tanh by default. \(h_t\)
      • 
+
    • gate_act (paddle.v2.activation.Base) – gate activation type, paddle.v2.activation.Sigmoid by default.
      • 
+
    • state_act (paddle.v2.activation.Base) – state activation type, paddle.v2.activation.Tanh by default.
      • 
 
    • bias_attr (paddle.v2.attr.ParameterAttribute|None|False) – Bias attribute. None means default bias. False means no
 bias.
      • 
 
    • param_attr (paddle.v2.attr.ParameterAttribute|None|False) – Parameter Attribute.
      • 
@@ -1035,9 +1035,9 @@ Recurrent Neural Networks on Sequence Modeling.
      
 
    • name (None|basestring) – The gru layer name.
      • 
 
    • input (paddle.v2.config_base.Layer.) – input layer.
      • 
 
    • reverse (bool) – Whether sequence process is reversed or not.
      • 
-
    • act (paddle.v2.Activation.Base) – activation type, paddle.v2.Activation.Tanh by default. This activation
+
    • act (paddle.v2.activation.Base) – activation type, paddle.v2.activation.Tanh by default. This activation
 affects the \({\tilde{h_t}}\).
      • 
-
    • gate_act (paddle.v2.Activation.Base) – gate activation type, paddle.v2.Activation.Sigmoid by default.
+
    • gate_act (paddle.v2.activation.Base) – gate activation type, paddle.v2.activation.Sigmoid by default.
 This activation affects the \(z_t\) and \(r_t\). It is the
 \(\sigma\) in the above formula.
      • 
 
    • bias_attr (paddle.v2.attr.ParameterAttribute|None|False) – Bias attribute. None means default bias. False means no
@@ -1100,7 +1100,7 @@ It is ignored when name is provided.
      • 
 
    • is_seq (bool) – is sequence for boot
      • 
 
    • boot (paddle.v2.config_base.Layer|None) – boot layer of memory.
      • 
 
    • boot_bias (paddle.v2.attr.ParameterAttribute|None) – boot layer’s bias
      • 
-
    • boot_bias_active_type (paddle.v2.Activation.Base) – boot layer’s active type.
      • 
+
    • boot_bias_active_type (paddle.v2.activation.Base) – boot layer’s active type.
      • 
 
    • boot_with_const_id (int) – boot layer’s id.
      • 
 
    
     		
 
    Parameters:
      
 
    • name (basestring) – Layer name.
      • 
 
    • input (list|tuple|collections.Sequence) – input layers or projections
      • 
-
    • act (paddle.v2.Activation.Base) – Activation type.
      • 
+
    • act (paddle.v2.activation.Base) – Activation type.
      • 
 
    • layer_attr (paddle.v2.attr.ExtraAttribute) – Extra Layer Attribute.
      • 
 
    
     		
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
    
@@ -276,7 +276,7 @@ specified, selective_fc acts exactly like fc.
    
 sparse binary matrix, and treat as the mask of selective fc.
 If is None, acts exactly like fc.
  • size (int) – The layer dimension.
    • 
-
  • act (paddle.v2.Activation.Base) – Activation Type. Default is tanh.
    • 
+
  • act (paddle.v2.activation.Base) – Activation Type. Default is tanh.
  • param_attr (paddle.v2.attr.ParameterAttribute) – The Parameter Attribute.
  • bias_attr (paddle.v2.attr.ParameterAttribute|None|Any) – The Bias Attribute. If no bias, then pass False or
 something not type of paddle.v2.attr.ParameterAttribute. None will get a
@@ -476,7 +476,7 @@ rest channels will be processed by rest group of filters.
    
                       num_channels=8,
                       num_filters=16, stride=1,
                       bias_attr=False,
-                      act=paddle.v2.Activation.Relu())
+                      act=paddle.v2.activation.Relu())
 
 
 
    • 
 
 
 
    
@@ -492,7 +492,7 @@ two image dimension.
 currently supports rectangular filters, the filter’s
 shape will be (filter_size, filter_size_y).
  • num_filters – Each filter group’s number of filter
    • 
-
  • act (paddle.v2.Activation.Base) – Activation type. Default is tanh
    • 
+
  • act (paddle.v2.activation.Base) – Activation type. Default is tanh
  • groups (int) – Group size of filters.
  • stride (int|tuple|list) – The x dimension of the stride. Or input a tuple for two image
 dimension.
    • 
@@ -787,7 +787,7 @@ y_i &\gets \gamma \hat{x_i} + \beta \qquad &//\ scale\ and\ shift\end{sp
 
    The details of batch normalization please refer to this
 paper.
    The example usage is:
    
-
    norm = batch_norm(input=net, act=paddle.v2.Activation.Relu())
+
    norm = batch_norm(input=net, act=paddle.v2.activation.Relu())
 
    
 
    
 
    
 
 
 
 
    
@@ -807,7 +807,7 @@ automaticly select cudnn_batch_norm for GPU and
 batch_norm for CPU. Otherwise, select batch norm
 type based on the specified type. If you use cudnn_batch_norm,
 we suggested you use latest version, such as v5.1.
-
  • act (paddle.v2.Activation.Base) – Activation Type. Better be relu. Because batch
+
  • act (paddle.v2.activation.Base) – Activation Type. Better be relu. Because batch
 normalization will normalize input near zero.
  • num_channels (int) – num of image channels or previous layer’s number of
 filters. None will automatically get from layer’s
@@ -930,7 +930,7 @@ out_{i} = act(in_{i} + out_{i+1} * W) \ \ \text{for} \ start <= i < end\en
 
    • 
@@ -1137,7 +1137,7 @@ Neural Turning Machine like models.
    def step(input):
     output = fc(input=layer,
                       size=1024,
-                      act=paddle.v2.Activation.Linear(),
+                      act=paddle.v2.activation.Linear(),
                       bias_attr=False)
     return output
 
@@ -1230,10 +1230,10 @@ output is \(o_t\), which name is ‘state’ a
 state.size.
 
  • input (paddle.v2.config_base.Layer) – input layer. \(Wx_t + Wh_{t-1}\)
    • 
 
  • state (paddle.v2.config_base.Layer) – State Layer. \(c_{t-1}\)
    • 
-
  • act (paddle.v2.Activation.Base) – Activation type. Default is tanh
    • 
-
  • gate_act (paddle.v2.Activation.Base) – Gate Activation Type. Default is sigmoid, and should
+
  • act (paddle.v2.activation.Base) – Activation type. Default is tanh
    • 
+
  • gate_act (paddle.v2.activation.Base) – Gate Activation Type. Default is sigmoid, and should
 be sigmoid only.
    • 
-
  • state_act (paddle.v2.Activation.Base) – State Activation Type. Default is sigmoid, and should
+
  • state_act (paddle.v2.activation.Base) – State Activation Type. Default is sigmoid, and should
 be sigmoid only.
    • 
 
  • bias_attr (paddle.v2.attr.ParameterAttribute) – Bias Attribute.
    • 
 
  • layer_attr (paddle.v2.attr.ExtraAttribute) – layer’s extra attribute.
    • 
@@ -1435,7 +1435,7 @@ Each inputs is a projection or operator.
    
 
  • size (int) – layer size.
    • 
 
  • input – inputs layer. It is an optional parameter. If set,
 then this function will just return layer’s name.
    • 
-
  • act (paddle.v2.Activation.Base) – Activation Type.
    • 
+
  • act (paddle.v2.activation.Base) – Activation Type.
    • 
 
  • bias_attr (paddle.v2.attr.ParameterAttribute or None or bool) – The Bias Attribute. If no bias, then pass False or
 something not type of paddle.v2.attr.ParameterAttribute. None will get a
 default Bias.
    • 
@@ -1932,7 +1932,7 @@ Inputs can be list of paddle.v2.config_base.Layer or list of projection.
    
 
    
@@ -1976,7 +1976,7 @@ Inputs can be list of paddle.v2.config_base.Layer or list of projection.
  • name (basestring) – Layer name.
  • a (paddle.v2.config_base.Layer) – input sequence layer
  • b (paddle.v2.config_base.Layer) – input sequence layer
    • 
-
  • act (paddle.v2.Activation.Base) – Activation type.
    • 
+
  • act (paddle.v2.activation.Base) – Activation type.
  • layer_attr (paddle.v2.attr.ExtraAttribute) – Extra Layer Attribute.
  • bias_attr (paddle.v2.attr.ParameterAttribute or None or bool) – The Bias Attribute. If no bias, then pass False or
 something not type of paddle.v2.attr.ParameterAttribute. None will get a
@@ -2209,7 +2209,7 @@ output sequence has T*M/N instances, the dimension of each instance is N.
    
 
  • input (paddle.v2.config_base.Layer) – Input layer.
  • reshape_size (int) – the size of reshaped sequence.
  • name (basestring) – Layer name.
    • 
-
  • act (paddle.v2.Activation.Base) – Activation type.
    • 
+
  • act (paddle.v2.activation.Base) – Activation type.
  • layer_attr (paddle.v2.attr.ExtraAttribute) – extra layer attributes.
  • bias_attr (paddle.v2.attr.ParameterAttribute or None or bool) – The Bias Attribute. If no bias, then pass False or
 something not type of paddle.v2.attr.ParameterAttribute. None will get a
@@ -2243,7 +2243,7 @@ default Bias.
    • 
 and \(f\) is activation function.
    The example usage is:
    addto = addto(input=[layer1, layer2],
-                    act=paddle.v2.Activation.Relu(),
+                    act=paddle.v2.activation.Relu(),
                     bias_attr=False)
 
    
 
    
@@ -2265,7 +2265,7 @@ Please refer to dropout for details.
  • name (basestring) – Layer name.
  • input (paddle.v2.config_base.Layer|list|tuple) – Input layers. It could be a paddle.v2.config_base.Layer or list/tuple of
 paddle.v2.config_base.Layer.
    • 
-
  • act (paddle.v2.Activation.Base) – Activation Type, default is tanh.
    • 
+
  • act (paddle.v2.activation.Base) – Activation Type, default is tanh.
  • bias_attr (paddle.v2.attr.ParameterAttribute|bool) – Bias attribute. If False, means no bias. None is default
 bias.
  • layer_attr (paddle.v2.attr.ExtraAttribute) – Extra Layer attribute.
    • 
@@ -2567,7 +2567,7 @@ For example, each sample:
  • a (paddle.v2.config_base.Layer) – Input layer a.
  • b (paddle.v2.config_base.Layer) – input layer b.
  • size (int.) – the layer dimension.
    • 
-
  • act (paddle.v2.Activation.Base) – Activation Type. Default is tanh.
    • 
+
  • act (paddle.v2.activation.Base) – Activation Type. Default is tanh.
  • param_attr (paddle.v2.attr.ParameterAttribute) – The Parameter Attribute.
  • bias_attr (paddle.v2.attr.ParameterAttribute|None|Any) – The Bias Attribute. If no bias, then pass False or
 something not type of paddle.v2.attr.ParameterAttribute. None will get a
@@ -3349,7 +3349,7 @@ A fast and simple algorithm for training neural probabilistic language models.label (paddle.v2.config_base.Layer) – label layer
  • weight (paddle.v2.config_base.Layer) – weight layer, can be None(default)
  • num_classes (int) – number of classes.
    • 
-
  • act (paddle.v2.Activation.Base) – Activation, default is Sigmoid.
    • 
+
  • act (paddle.v2.activation.Base) – Activation, default is Sigmoid.
  • param_attr (paddle.v2.attr.ParameterAttribute) – The Parameter Attribute|list.
  • num_neg_samples (int) – number of negative samples. Default is 10.
  • neg_distribution (list|tuple|collections.Sequence|None) – The distribution for generating the random negative labels.

    • 
 
 
    参数:
      
 
    • input (paddle.v2.config_base.Layer) – Input Layer
      • 
-
    • act (paddle.v2.Activation.Base) – activation.
      • 
+
    • act (paddle.v2.activation.Base) – activation.
      • 
 
    • bias_attr (paddle.v2.attr.ParameterAttribute) – bias attribute.
      • 
 
    • param_attr (paddle.v2.attr.ParameterAttribute) – parameter attribute.
      • 
 
    • name (basestring) – name of the layer
      • 
@@ -977,9 +977,9 @@ more details about LSTM.
      
 
    • name (basestring) – The lstmemory layer name.
      • 
 
    • input (paddle.v2.config_base.Layer) – input layer name.
      • 
 
    • reverse (bool) – is sequence process reversed or not.
      • 
-
    • act (paddle.v2.Activation.Base) – activation type, paddle.v2.Activation.Tanh by default. \(h_t\)
      • 
-
    • gate_act (paddle.v2.Activation.Base) – gate activation type, paddle.v2.Activation.Sigmoid by default.
      • 
-
    • state_act (paddle.v2.Activation.Base) – state activation type, paddle.v2.Activation.Tanh by default.
      • 
+
    • act (paddle.v2.activation.Base) – activation type, paddle.v2.activation.Tanh by default. \(h_t\)
      • 
+
    • gate_act (paddle.v2.activation.Base) – gate activation type, paddle.v2.activation.Sigmoid by default.
      • 
+
    • state_act (paddle.v2.activation.Base) – state activation type, paddle.v2.activation.Tanh by default.
      • 
 
    • bias_attr (paddle.v2.attr.ParameterAttribute|None|False) – Bias attribute. None means default bias. False means no
 bias.
      • 
 
    • param_attr (paddle.v2.attr.ParameterAttribute|None|False) – Parameter Attribute.
      • 
@@ -1042,9 +1042,9 @@ Recurrent Neural Networks on Sequence Modeling.
      
 
    • name (None|basestring) – The gru layer name.
      • 
 
    • input (paddle.v2.config_base.Layer.) – input layer.
      • 
 
    • reverse (bool) – Whether sequence process is reversed or not.
      • 
-
    • act (paddle.v2.Activation.Base) – activation type, paddle.v2.Activation.Tanh by default. This activation
+
    • act (paddle.v2.activation.Base) – activation type, paddle.v2.activation.Tanh by default. This activation
 affects the \({\tilde{h_t}}\).
      • 
-
    • gate_act (paddle.v2.Activation.Base) – gate activation type, paddle.v2.Activation.Sigmoid by default.
+
    • gate_act (paddle.v2.activation.Base) – gate activation type, paddle.v2.activation.Sigmoid by default.
 This activation affects the \(z_t\) and \(r_t\). It is the
 \(\sigma\) in the above formula.
      • 
 
    • bias_attr (paddle.v2.attr.ParameterAttribute|None|False) – Bias attribute. None means default bias. False means no
@@ -1107,7 +1107,7 @@ It is ignored when name is provided.
      • 
 
    • is_seq (bool) – is sequence for boot
      • 
 
    • boot (paddle.v2.config_base.Layer|None) – boot layer of memory.
      • 
 
    • boot_bias (paddle.v2.attr.ParameterAttribute|None) – boot layer’s bias
      • 
-
    • boot_bias_active_type (paddle.v2.Activation.Base) – boot layer’s active type.
      • 
+
    • boot_bias_active_type (paddle.v2.activation.Base) – boot layer’s active type.
      • 
 
    • boot_with_const_id (int) – boot layer’s id.
      • 
 
    
     		
 
    参数:
      
 
    • name (basestring) – Layer name.
      • 
 
    • input (list|tuple|collections.Sequence) – input layers or projections
      • 
-
    • act (paddle.v2.Activation.Base) – Activation type.
      • 
+
    • act (paddle.v2.activation.Base) – Activation type.
      • 
 
    • layer_attr (paddle.v2.attr.ExtraAttribute) – Extra Layer Attribute.
      •