Table Of Contents
Table Of Contents

MSRAPrelu

class mxnet.initializer.MSRAPrelu(factor_type='avg', slope=0.25)[source]

Initialize the weight according to a MSRA paper.

This initializer implements Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification, available at https://arxiv.org/abs/1502.01852.

This initializer is proposed for initialization related to ReLu activation, it maked some changes on top of Xavier method.

Parameters:
  • factor_type (str, optional) – Can be 'avg', 'in', or 'out'.
  • slope (float, optional) – initial slope of any PReLU (or similar) nonlinearities.
__init__(factor_type='avg', slope=0.25)[source]

Initialize self. See help(type(self)) for accurate signature.

Methods

__init__([factor_type, slope]) Initialize self.
dumps() Saves the initializer to string
set_verbosity([verbose, print_func]) Switch on/off verbose mode