tiny_dnn::weight_init::xavier Class Reference

Use fan-in and fan-out for scaling. More...

#include <weight_init.h>

Inheritance diagram for tiny_dnn::weight_init::xavier:

Collaboration diagram for tiny_dnn::weight_init::xavier:

Public Member Functions
	xavier (float_t value)
void	fill (vec_t *weight, serial_size_t fan_in, serial_size_t fan_out) override
Public Member Functions inherited from tiny_dnn::weight_init::scalable
	scalable (float_t value)
void	scale (float_t value)

Additional Inherited Members
Protected Attributes inherited from tiny_dnn::weight_init::scalable
float_t	scale_

Detailed Description

Use fan-in and fan-out for scaling.

X Glorot, Y Bengio, Understanding the difficulty of training deep feedforward neural networks Proc. AISTATS 10, May 2010, vol.9, pp249-256

Member Function Documentation

fill()

void tiny_dnn::weight_init::xavier::fill ( vec_t *  weight, serial_size_t  fan_in, serial_size_t  fan_out  )

inlineoverridevirtual

Implements tiny_dnn::weight_init::function.

---

The documentation for this class was generated from the following file:

• tiny_dnn/util/weight_init.h