diff --git a/doc/ui/api/trainer_config_helpers/layers.html b/doc/ui/api/trainer_config_helpers/layers.html index af7e54886b185af163e37b0f93bec8addc99b90a..cbfbe0b74a3b0c3e277af25e252bef5f02cb25b4 100644 --- a/doc/ui/api/trainer_config_helpers/layers.html +++ b/doc/ui/api/trainer_config_helpers/layers.html @@ -1130,7 +1130,7 @@ for details.
paddle.trainer_config_helpers.layers.dotmul_projection(*args, **kwargs)
-

1. DotMulProjection if input is a layer. +

DotMulProjection with a layer as input. It performs element-wise multiplication with weight.

\[out.row[i] += in.row[i] .* weight\]
@@ -1139,32 +1139,21 @@ It performs element-wise multiplication with weight.

proj = dotmul_projection(input=layer)
 
-

2. DotMulOperator if input is a list or tuple. -It takes two inputs, performs element-wise multiplication:

-
-\[out.row[i] += scale * (in1.row[i] .* in2.row[i])\]
-

where \(.*\) means element-wise multiplication, and -scale is a config scalar, its default value is one.

-

The example usage is:

-
op = dotmul_projection(input=[layer1, layer2],
-                       scale=2.0)
-
-
- -
Parameters:
    -
  • input (LayerOutput|list|tuple) – Input layer.
  • +
  • input (LayerOutput) – Input layer.
  • param_attr (ParameterAttribute) – Parameter config, None if use default.
  • scale (float) – config scalar, default value is one.
Returns:

A DotMulProjection or DotMulOperator Object.

+
Returns:

A DotMulProjection Object.

Return type:

DotMulProjection or DotMulOperator

+
Return type:

DotMulProjection