fused_elemwise_activation¶

paddle.fluid.contrib.layers.nn. fused_elemwise_activation ( x, y, functor_list, axis=- 1, scale=0.0, save_intermediate_out=True ) [source]

Fused elementwise_add/mul and activation layers

This function computes an elementwise_add/mul cooperated with an activation.

\[out = Unary(Binary(x, y))\]

or

\[out = Binary(x, Unary(y))\]

Unary operators can be: scale, relu, tanh. Binary operators can be: elementwise_add, elementwise_mul.

Parameters

• x (Variable) – left operation of the binary operator.

• y (Variable) – right operator of the binary operator.

• functor_list (list of str) – types of operator which will be executed by this layer. For example, [‘elementwise_add’, ‘relu’] (out = elementwise_add(x, relu(y))), or [‘relu’, ‘elemmentwise_add’] (out = relu(elementwise_add(x, y))).

• axis (int32, default -1) – axis of elementwise op.

• scale (float32, default 0) – parameter of scale op.

• save_intermediate_out (bool, default True) – whether to save the intermediate result, Unary(y) or Binary(x, y).

Returns

The computation result.

Return type

Variable