Home Manual Reference Source Test
import {BaseNeuralNetwork} from 'tensorscript/lib/deep_learning.mjs'
public class | source

BaseNeuralNetwork

Extends:

lib/model_interface.js~TensorScriptModelInterface → BaseNeuralNetwork

Indirect Implemented:

Deep Learning with Tensorflow

Test:

Constructor Summary

Public Constructor
public

constructor(options: {layers: Array<Object>, compile: Object, fit: Object}, properties: *)

Member Summary

Public Members
public
public
public

Method Summary

Public Methods
public

calculate(matrix: Array<Array<number>>|Array<number>, options: Object): {data: Promise}

Predicts new dependent variables

public abstract

generateLayers(x_matrix: Array<Array<number>>, y_matrix: Array<Array<number>>, layers: Array<Object>)

Adds dense layers to tensorflow model

public

async train(x_matrix: Array<Array<number>>, y_matrix: Array<Array<number>>, layers: Array<Object>, x_text: Array<Array<number>>, y_text: Array<Array<number>>): Object

Asynchronously trains tensorflow model

Public Constructors

public constructor(options: {layers: Array<Object>, compile: Object, fit: Object}, properties: *) source

Params:

NameTypeAttributeDescription
options {layers: Array<Object>, compile: Object, fit: Object}

neural network configuration and tensorflow model hyperparameters

properties *

extra instance properties

Test:

Public Members

public model source

public xShape source

public yShape source

Public Methods

public calculate(matrix: Array<Array<number>>|Array<number>, options: Object): {data: Promise} source

Predicts new dependent variables

Params:

NameTypeAttributeDescription
matrix Array<Array<number>>|Array<number>

new test independent variables

options Object

model prediction options

Return:

{data: Promise}

returns tensorflow prediction

Test:

public abstract generateLayers(x_matrix: Array<Array<number>>, y_matrix: Array<Array<number>>, layers: Array<Object>) source

Adds dense layers to tensorflow model

Params:

NameTypeAttributeDescription
x_matrix Array<Array<number>>

independent variables

y_matrix Array<Array<number>>

dependent variables

layers Array<Object>

model dense layer parameters

Test:

public async train(x_matrix: Array<Array<number>>, y_matrix: Array<Array<number>>, layers: Array<Object>, x_text: Array<Array<number>>, y_text: Array<Array<number>>): Object source

Asynchronously trains tensorflow model

Params:

NameTypeAttributeDescription
x_matrix Array<Array<number>>

independent variables

y_matrix Array<Array<number>>

dependent variables

layers Array<Object>

array of model dense layer parameters

x_text Array<Array<number>>

validation data independent variables

y_text Array<Array<number>>

validation data dependent variables

Return:

Object

returns trained tensorflow model

Test: