Layer Class Reference

Inheritance diagram for Layer:

Collaboration diagram for Layer:

Public Member Functions
def	__init__ (self, name, tf_activation_str, dim_input, dim_output, p_bias, p_w, operation_seed=None)
def	initialize (self, layer_input)

Public Attributes
	name
	layer parameters
	tf_activation
	activation function
	seed
	random seed
	shape
	layer shape
	w
	init parameters for uniform distribution
	b
	init parameters for bias
	input
	input
	output
	output
	is_initialized
	check if initialized (input and output are connected)

Private Member Functions
def	_init_bias (self, width, init_val, name=None)
def	_init_weight (self, shape, stddev, operation_seed, name=None)
def	_add_var_to_summary (self, var)
def	_add_all_to_summary (self)

Detailed Description

definition of a layer obj

Definition at line 25 of file tensorflow_dnn_model.py.

Constructor & Destructor Documentation

__init__()

def __init__	(		self,
			name,
			tf_activation_str,
			dim_input,
			dim_output,
			p_bias,
			p_w,
			operation_seed = None
	)

:param name:
:param tf_activation: string, name of an available tensorflow activations function
:param dim_input:
:param dim_output:
:param p_bias: initial constant
:param p_w: stddev of uniform distribution to initialize
:return:

Definition at line 30 of file tensorflow_dnn_model.py.

Member Function Documentation

_add_all_to_summary()

def _add_all_to_summary (   self )

private

adds tuneable parameters to summary

Definition at line 134 of file tensorflow_dnn_model.py.

_add_var_to_summary()

def _add_var_to_summary (   self,   var  )

private

add variables of this layer to tensorboard
:param var: tensorflow variable
:return:

Definition at line 115 of file tensorflow_dnn_model.py.

_init_bias()

def _init_bias (   self,   width,   init_val,   name = None  )

private

define bias variables

Definition at line 81 of file tensorflow_dnn_model.py.

_init_weight()

def _init_weight (   self,   shape,   stddev,   operation_seed,   name = None  )

private

define weight variables

Definition at line 90 of file tensorflow_dnn_model.py.

initialize()

def initialize	(		self,
			layer_input
	)

initialization, requires layer input

Definition at line 99 of file tensorflow_dnn_model.py.

---

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

• analysis/scripts/dft/tensorflow_dnn_model.py