diff --git a/develop/doc/api/v1/trainer_config_helpers/layers.html b/develop/doc/api/v1/trainer_config_helpers/layers.html index 989dee056d66090c54770713b4b925ba2f6dc8eb..2c4e82f4c3928ba93cb80b00e0cfef024ab01417 100644 --- a/develop/doc/api/v1/trainer_config_helpers/layers.html +++ b/develop/doc/api/v1/trainer_config_helpers/layers.html @@ -3520,8 +3520,7 @@ This idea is from “F. Morin, Y. Bengio (AISTATS 05): Hierarchical Probabilistic Neural Network Language Model.”

The example usage is:

cost = hsigmoid(input=[layer1, layer2],
-                label=data_layer,
-                num_classes=3)
+                label=data_layer)
@@ -3532,10 +3531,11 @@ Hierarchical Probabilistic Neural Network Language Model.”

  • input (LayerOutput|list|tuple) – Input layers. It could be a LayerOutput or list/tuple of LayerOutput.
  • label (LayerOutput) – Label layer.
    • -
  • num_classes (int) – number of classes.
    • +
  • num_classes (int|None) – number of classes.
  • name (basestring) – layer name
  • bias_attr (ParameterAttribute|False) – Bias attribute. None means default bias. False means no bias.
    • +
  • param_attr (ParameterAttribute|None) – Parameter Attribute. None means default parameter.
  • layer_attr (ExtraLayerAttribute) – Extra Layer Attribute.
    • diff --git a/develop/doc/api/v2/config/layer.html b/develop/doc/api/v2/config/layer.html index 65c26eb16bada9244a9561423da37da86c9f07c1..a441b2f5a4b75e663fedf7bfd2734736b3fe2b19 100644 --- a/develop/doc/api/v2/config/layer.html +++ b/develop/doc/api/v2/config/layer.html @@ -4187,8 +4187,7 @@ This idea is from “F. Morin, Y. Bengio (AISTATS 05): Hierarchical Probabilistic Neural Network Language Model.”

    The example usage is:

    cost = hsigmoid(input=[layer1, layer2],
-                label=data,
-                num_classes=3)
+                label=data)
    @@ -4199,10 +4198,11 @@ Hierarchical Probabilistic Neural Network Language Model.”

  • 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.
  • label (paddle.v2.config_base.Layer) – Label layer.
    • -
  • num_classes (int) – number of classes.
    • +
  • num_classes (int|None) – number of classes.
  • name (basestring) – layer name
  • bias_attr (paddle.v2.attr.ParameterAttribute|False) – Bias attribute. None means default bias. False means no bias.
    • +
  • param_attr (paddle.v2.attr.ParameterAttribute|None) – Parameter Attribute. None means default parameter.
  • layer_attr (paddle.v2.attr.ExtraAttribute) – Extra Layer Attribute.
    • diff --git a/develop/doc_cn/api/v1/trainer_config_helpers/layers.html b/develop/doc_cn/api/v1/trainer_config_helpers/layers.html index 8108ce920c3b382f509facd8323d5d8aced8dfa7..ecfddf7ce433d734d69ab991cc7d490d315d8c81 100644 --- a/develop/doc_cn/api/v1/trainer_config_helpers/layers.html +++ b/develop/doc_cn/api/v1/trainer_config_helpers/layers.html @@ -3527,8 +3527,7 @@ This idea is from “F. Morin, Y. Bengio (AISTATS 05): Hierarchical Probabilistic Neural Network Language Model.”

    The example usage is:

    cost = hsigmoid(input=[layer1, layer2],
-                label=data_layer,
-                num_classes=3)
+                label=data_layer)
    @@ -3539,10 +3538,11 @@ Hierarchical Probabilistic Neural Network Language Model.”

  • input (LayerOutput|list|tuple) – Input layers. It could be a LayerOutput or list/tuple of LayerOutput.
  • label (LayerOutput) – Label layer.
    • -
  • num_classes (int) – number of classes.
    • +
  • num_classes (int|None) – number of classes.
  • name (basestring) – layer name
  • bias_attr (ParameterAttribute|False) – Bias attribute. None means default bias. False means no bias.
    • +
  • param_attr (ParameterAttribute|None) – Parameter Attribute. None means default parameter.
  • layer_attr (ExtraLayerAttribute) – Extra Layer Attribute.
    • diff --git a/develop/doc_cn/api/v2/config/layer.html b/develop/doc_cn/api/v2/config/layer.html index 0ee55275501115283365a2c3e2779d6ad7c62995..28e753e1270bff09e4d464d5793047a1e72cbc34 100644 --- a/develop/doc_cn/api/v2/config/layer.html +++ b/develop/doc_cn/api/v2/config/layer.html @@ -4194,8 +4194,7 @@ This idea is from “F. Morin, Y. Bengio (AISTATS 05): Hierarchical Probabilistic Neural Network Language Model.”

    The example usage is:

    cost = hsigmoid(input=[layer1, layer2],
-                label=data,
-                num_classes=3)
+                label=data)
    @@ -4206,10 +4205,11 @@ Hierarchical Probabilistic Neural Network Language Model.”

  • 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.
  • label (paddle.v2.config_base.Layer) – Label layer.
    • -
  • num_classes (int) – number of classes.
    • +
  • num_classes (int|None) – number of classes.
  • name (basestring) – layer name
  • bias_attr (paddle.v2.attr.ParameterAttribute|False) – Bias attribute. None means default bias. False means no bias.
    • +
  • param_attr (paddle.v2.attr.ParameterAttribute|None) – Parameter Attribute. None means default parameter.
  • layer_attr (paddle.v2.attr.ExtraAttribute) – Extra Layer Attribute.