keraflow.models.Sequential Class Reference

Model with single input and single output. More...

Inheritance diagram for keraflow.models.Sequential:

Public Member Functions
def	__init__
def	compile
	Configure the model and prepare inner utilized tensors. More...
def	predict
	Returns the output values given the input data. More...
Public Member Functions inherited from keraflow.models.Model
def	__init__
def	compile
	Configure the model and prepare inner utilized tensors. More...
def	fit
	Adjust model parameters to fit input data and true answers. More...
def	predict
	Returns the output values given the input data. More...
def	evaluate
	Returns the loss value and metrics values given the input data and true answer. More...
def	save_to_file
	Save the model to disk for later use. More...
def	save_arch
def	save_weights

Additional Inherited Members
Static Public Member Functions inherited from keraflow.models.Model
def	load_from_file
	Load model from disk. More...

Detailed Description

Model with single input and single output.

Also severs a Layer (inheriting SequentialLayer) for squeezing a sequence of layer into a single one.

Constructor & Destructor Documentation

def keraflow.models.Sequential.__init__	(		self,
			layers = [],
			kwargs
	)

Parameters

layers	a list of layer instance.
kwargs	see Layer.__init__. This is the common args for Layer. For Sequential, you could set name and trainable.

Member Function Documentation

def keraflow.models.Sequential.compile	(		self,
			optimizer,
			loss,
			metrics = []
	)

Configure the model and prepare inner utilized tensors.

Parameters

optimizer	str(name of optimizer class)/optimizer object. See keraflow.optimizers
loss	objective function/str(name of objective function). Objective for the output. See Objectives for a list of predefined objective functions.
metrics	objective function/str(name of objective function). Extra objective for the output. See Objectives for a list of predefined objective functions. Note that you could only pass one objective since Sequential has only one output.

def keraflow.models.Sequential.predict	(		self,
			x,
			batch_size = 32,
			train_mode = False
	)

Returns the output values given the input data.

Parameters

x	numpy array/list. Input data.
batch_size	int. The batch size to predict the testing data. Might cause memorage error if set too large.
train_mode	boolean. For debugging usage. Do not use this flag in your code.

Returns

numpy array. Output value.