Note: This API is only avaliable in [Static Graph] mode
prelu(x, mode, param_attr=None, name=None)
Equation:\[y = \max(0, x) + \alpha * \min(0, x)\]
There are three modes for the activation:
all: All elements share same alpha. channel: Elements in same channel share same alpha. element: All elements do not share alpha. Each element has its own alpha.
x (Variable) – The input Tensor or LoDTensor with data type float32.
mode (str) – The mode for weight sharing.
param_attr (ParamAttr|None) – The parameter attribute for the learnable weight (alpha), it can be create by ParamAttr. None by default. For detailed information, please refer to ParamAttr.
name (str|None) – For detailed information, please refer to Name. Usually name is no need to set and None by default.
output(Variable): The tensor or LoDTensor with the same shape as input. The data type is float32.
- Return type
import paddle.fluid as fluid from paddle.fluid.param_attr import ParamAttr x = fluid.data(name="x", shape=[None,5,10,10], dtype="float32") mode = 'channel' output = fluid.layers.prelu( x,mode,param_attr=ParamAttr(name='alpha'))