// Cloned by Ger Gleeson on 8 Dec 2019 from World "Character recognition neural network" by "Coding Train" project
// Please leave this clone trail here.
// Port of Character recognition neural network from here:
// https://github.com/CodingTrain/Toy-Neural-Network-JS/tree/master/examples/mnist
// with many modifications
// --- defined by MNIST - do not change these ---------------------------------------
const PIXELS = 28; // images in data set are tiny
const PIXELSSQUARED = PIXELS * PIXELS;
// number of training and test exemplars in the data set:
const NOTRAIN = 60000;
const NOTEST = 10000;
//--- can modify all these --------------------------------------------------
// no of nodes in network
const noinput = PIXELSSQUARED;
const nohidden = 85;
const nooutput = 10;
const learningrate = 0.1; // default 0.1
// should we train every timestep or not
let do_training = true;
// how many to train and test per timestep
const TRAINPERSTEP = 30;
const TESTPERSTEP = 5;
// multiply it by this to magnify for display
const ZOOMFACTOR = 7;
const ZOOMPIXELS = ZOOMFACTOR * PIXELS;
// 3 rows of
// large image + 50 gap + small image
// 50 gap between rows
const canvaswidth = ( PIXELS + ZOOMPIXELS ) + 50;
const canvasheight = ( ZOOMPIXELS * 3 ) + 100;
const DOODLE_THICK = 18; // thickness of doodle lines
const DOODLE_BLUR = 3; // blur factor applied to doodles
let mnist;
// all data is loaded into this
// mnist.train_images
// mnist.train_labels
// mnist.test_images
// mnist.test_labels
let nn;
let trainrun = 1;
let train_index = 0;
let testrun = 1;
let test_index = 0;
let total_tests = 0;
let total_correct = 0;
// images in LHS:
let doodle, demo;
let doodle_exists = false;
let demo_exists = false;
let mousedrag = false; // are we in the middle of a mouse drag drawing?
// save inputs to global var to inspect
// type these names in console
var train_inputs, test_inputs, demo_inputs, doodle_inputs;
// Matrix.randomize() is changed to point to this. Must be defined by user of Matrix.
function randomWeight()
{
return ( AB.randomFloatAtoB ( -0.5, 0.5 ) );
// Coding Train default is -1 to 1
}
// CSS trick
// make run header bigger
$("#runheaderbox").css ( { "max-height": "95vh" } );
//--- start of AB.msgs structure: ---------------------------------------------------------
// We output a serious of AB.msgs to put data at various places in the run header
var thehtml;
// 1 Doodle header
thehtml = "<hr> <h1> 1. Doodle </h1> Top row: Doodle (left) and shrunk (right). <br> " +
" Draw your doodle in top LHS. <button onclick='wipeDoodle();' class='normbutton' >Clear doodle</button> <br> ";
AB.msg ( thehtml, 1 );
// 2 Doodle variable data (guess)
// 3 Training header
thehtml = "<hr> <h1> 2. Training </h1> Middle row: Training image magnified (left) and original (right). <br> " +
" <button onclick='do_training = false;' class='normbutton' >Stop training</button> <br> ";
AB.msg ( thehtml, 3 );
// 4 variable training data
// 5 Testing header
thehtml = "<h3> Hidden tests </h3> " ;
AB.msg ( thehtml, 5 );
// 6 variable testing data
// 7 Demo header
thehtml = "<hr> <h1> 3. Demo </h1> Bottom row: Test image magnified (left) and original (right). <br>" +
" The network is <i>not</i> trained on any of these images. <br> " +
" <button onclick='makeDemo();' class='normbutton' >Demo test image</button> <br> ";
AB.msg ( thehtml, 7 );
// 8 Demo variable data (random demo ID)
// 9 Demo variable data (changing guess)
const greenspan = "<span style='font-weight:bold; font-size:x-large; color:darkgreen'> " ;
//--- end of AB.msgs structure: ---------------------------------------------------------
function setup()
{
createCanvas ( canvaswidth, canvasheight );
doodle = createGraphics ( ZOOMPIXELS, ZOOMPIXELS ); // doodle on larger canvas
doodle.pixelDensity(1);
// JS load other JS
// maybe have a loading screen while loading the JS and the data set
AB.loadingScreen();
$.getScript ( "/uploads/codingtrain/matrix.js", function()
{
// $.getScript ( "/uploads/codingtrain/nn.js", function()
// {
$.getScript ( "/uploads/codingtrain/mnist.js", function()
{
console.log ("All JS loaded");
nn = new NeuralNetwork( noinput, nohidden, nooutput );
nn.setLearningRate ( learningrate );
loadData();
});
// });
});
}
// load data set from local file (on this server)
function loadData()
{
loadMNIST ( function(data)
{
mnist = data;
console.log ("All data loaded into mnist object:")
console.log(mnist);
AB.removeLoading(); // if no loading screen exists, this does nothing
});
}
function rotateImage ( img ) // make a P5 image object from a raw data array
{
let theimage = createImage (PIXELS, PIXELS); // make blank image, then populate it
theimage.loadPixels();
for (let i = 0; i < PIXELSSQUARED ; i++)
{
let bright = img[i];
let index = i * 4;
theimage.pixels[index + 0] = bright;
theimage.pixels[index + 1] = bright;
theimage.pixels[index + 2] = bright;
theimage.pixels[index + 3] = 255;
}
theimage.updatePixels();
return theimage;
}
function getImage ( img ) // make a P5 image object from a raw data array
{
let theimage = createImage (PIXELS, PIXELS); // make blank image, then populate it
theimage.loadPixels();
for (let i = 0; i < PIXELSSQUARED ; i++)
{
let bright = img[i];
let index = i * 4;
theimage.pixels[index + 0] = bright;
theimage.pixels[index + 1] = bright;
theimage.pixels[index + 2] = bright;
theimage.pixels[index + 3] = 255;
}
theimage.updatePixels();
return theimage;
}
function getInputs ( img ) // convert img array into normalised input array
{
let inputs = [];
for (let i = 0; i < PIXELSSQUARED ; i++)
{
let bright = img[i];
inputs[i] = bright / 255; // normalise to 0 to 1
}
return ( inputs );
}
function trainit (show) // train the network with a single exemplar, from global var "train_index", show visual on or off
{
let img = mnist.train_images[train_index];
let label = mnist.train_labels[train_index];
// optional - show visual of the image
if (show)
{
var theimage = getImage ( img ); // get image from data array
image ( theimage, 0, ZOOMPIXELS+50, ZOOMPIXELS, ZOOMPIXELS ); // magnified
image ( theimage, ZOOMPIXELS+50, ZOOMPIXELS+50, PIXELS, PIXELS ); // original
//rotate image ??
}
// set up the inputs
let inputs = getInputs ( img ); // get inputs from data array
// set up the outputs
let targets = [0, 0, 0, 0, 0, 0, 0, 0, 0, 0];
targets[label] = 1; // change one output location to 1, the rest stay at 0
// console.log(train_index);
// console.log(inputs);
// console.log(targets);
train_inputs = inputs; // can inspect in console
let inputs_copy = []
//console.log("Input = " + inputs);
let num_loop =0;
while(inputs[num_loop]===0){
num_loop++
}
//console.log("num_loop " + num_loop);
for(let i = 0; i < PIXELSSQUARED; i++){
inputs_copy[i] = 0;
}
let y = 0;
for(let i = num_loop; i<PIXELSSQUARED;i++){
inputs_copy[y] = inputs[num_loop];
y++;
}
//fill first 56 places with 0
// let inputs_move_right = [];
// for (let i = 0; i < 56 ; i++) {
// inputs_move_right[i] = 0;
// }
//fill next 56-727 places with 0-672 places from input
// for (let j = 56; j < PIXELSSQUARED ; j++)
// {
// let i = 0;
// inputs_move_right[j] = inputs[i];
// i++;
// }
//fill last 56 places 672-727 with 0
// let inputs_move_left = [];
// for (let i = PIXELSSQUARED - 56; i < PIXELSSQUARED ; i++) {
// inputs_move_left[i] = 0;
// }
// for (let j = 0; j < PIXELSSQUARED - 56 ; j++)
// {
// let i = 56;
// inputs_move_left[j] = inputs[i];
// i++;
// }
nn.train ( inputs_copy, targets );
// nn.train ( inputs_move_right, targets );
// nn.train ( inputs_move_left, targets );
thehtml = " trainrun: " + trainrun + "<br> no: " + train_index ;
AB.msg ( thehtml, 4 );
train_index++;
if ( train_index == NOTRAIN )
{
train_index = 0;
console.log( "finished trainrun: " + trainrun );
trainrun++;
}
}
function testit() // test the network with a single exemplar, from global var "test_index"
{
let img = mnist.test_images[test_index];
let label = mnist.test_labels[test_index];
// set up the inputs
let inputs = getInputs ( img );
test_inputs = inputs; // can inspect in console
let inputs_copy = [];
//console.log("Input = " + inputs);
let num_loop =0;
while(inputs[num_loop]===0){
num_loop++;
}
//console.log("num_loop " + num_loop);
for(let i = 0; i < PIXELSSQUARED; i++){
inputs_copy[i] = 0;
}
let y = 0;
for(let i = num_loop; i<PIXELSSQUARED;i++){
inputs_copy[y] = inputs[num_loop];
y++;
}
let prediction = nn.predict(inputs_copy); // array of outputs
let guess = findMax(prediction); // the top output
total_tests++;
if (guess == label) total_correct++;
let percent = (total_correct / total_tests) * 100 ;
thehtml = " testrun: " + testrun + "<br> no: " + total_tests + " <br> " +
" correct: " + total_correct + "<br>" +
" score: " + greenspan + percent.toFixed(2) + "</span>";
AB.msg ( thehtml, 6 );
test_index++;
if ( test_index == NOTEST )
{
console.log( "finished testrun: " + testrun + " score: " + percent.toFixed(2) );
testrun++;
test_index = 0;
total_tests = 0;
total_correct = 0;
}
}
//--- find no.1 (and maybe no.2) output nodes ---------------------------------------
// (restriction) assumes array values start at 0 (which is true for output nodes)
function find12 (a) // return array showing indexes of no.1 and no.2 values in array
{
let no1 = 0;
let no2 = 0;
let no1value = 0;
let no2value = 0;
for (let i = 0; i < a.length; i++)
{
if (a[i] > no1value)
{
no1 = i;
no1value = a[i];
}
else if (a[i] > no2value)
{
no2 = i;
no2value = a[i];
}
}
var b = [ no1, no2 ];
return b;
}
// just get the maximum - separate function for speed - done many times
// find our guess - the max of the output nodes array
function findMax (a)
{
let no1 = 0;
let no1value = 0;
for (let i = 0; i < a.length; i++)
{
if (a[i] > no1value)
{
no1 = i;
no1value = a[i];
}
}
return no1;
}
function findMaxandValue (a)
{
let no1 = 0;
let no1value = 0;
for (let i = 0; i < a.length; i++)
{
if (a[i] > no1value)
{
no1 = i;
no1value = a[i];
}
}
var b = [ no1, no1value ];
return b;
}
// --- the draw function -------------------------------------------------------------
// every step:
function draw()
{
// check if libraries and data loaded yet:
if ( typeof mnist == 'undefined' ) return;
// how can we get white doodle on black background on yellow canvas?
// background('#ffffcc'); doodle.background('black');
background ('black');
if ( do_training )
{
// do some training per step
for (let i = 0; i < TRAINPERSTEP; i++)
{
if (i === 0) trainit(true); // show only one per step - still flashes by
else trainit(false);
}
// do some testing per step
for (let i = 0; i < TESTPERSTEP; i++)
testit();
}
// keep drawing demo and doodle images
// and keep guessing - we will update our guess as time goes on
if ( demo_exists )
{
drawDemo();
guessDemo();
}
if ( doodle_exists )
{
drawDoodle();
guessDoodle();
}
// detect doodle drawing
// (restriction) the following assumes doodle starts at 0,0
if ( mouseIsPressed ) // gets called when we click buttons, as well as if in doodle corner
{
// console.log ( mouseX + " " + mouseY + " " + pmouseX + " " + pmouseY );
var MAX = ZOOMPIXELS + 20; // can draw up to this pixels in corner
if ( (mouseX < MAX) && (mouseY < MAX) && (pmouseX < MAX) && (pmouseY < MAX) )
{
mousedrag = true; // start a mouse drag
doodle_exists = true;
doodle.stroke('white');
doodle.strokeWeight( DOODLE_THICK );
doodle.line(mouseX, mouseY, pmouseX, pmouseY);
}
}
else
{
// are we exiting a drawing
if ( mousedrag )
{
mousedrag = false;
// console.log ("Exiting draw. Now blurring.");
doodle.filter (BLUR, DOODLE_BLUR); // just blur once
// console.log (doodle);
}
}
}
//--- demo -------------------------------------------------------------
// demo some test image and predict it
// get it from test set so have not used it in training
function makeDemo()
{
demo_exists = true;
var i = AB.randomIntAtoB ( 0, NOTEST - 1 );
demo = mnist.test_images[i];
var label = mnist.test_labels[i];
thehtml = "Test image no: " + i + "<br>" +
"Classification: " + label + "<br>" ;
AB.msg ( thehtml, 8 );
// type "demo" in console to see raw data
}
function drawDemo()
{
var theimage = getImage ( demo );
// console.log (theimage);
image ( theimage, 0, canvasheight - ZOOMPIXELS, ZOOMPIXELS, ZOOMPIXELS ); // magnified
image ( theimage, ZOOMPIXELS+50, canvasheight - ZOOMPIXELS, PIXELS, PIXELS ); // original
}
function guessDemo()
{
let inputs = getInputs ( demo );
demo_inputs = inputs; // can inspect in console
let prediction = nn.predict(inputs); // array of outputs
let guess = findMax(prediction); // the top output
thehtml = " We classify it as: " + greenspan + guess + "</span>" ;
AB.msg ( thehtml, 9 );
}
//--- doodle -------------------------------------------------------------
function drawDoodle()
{
// doodle is createGraphics not createImage
let theimage = doodle.get();
// console.log (theimage);
image ( theimage, 0, 0, ZOOMPIXELS, ZOOMPIXELS ); // original
image ( theimage, ZOOMPIXELS+50, 0, PIXELS, PIXELS ); // shrunk
}
function guessDoodle()
{
// doodle is createGraphics not createImage
let img = doodle.get();
img.resize ( PIXELS, PIXELS );
img.loadPixels();
// set up inputs
let inputs = [];
for (let i = 0; i < PIXELSSQUARED ; i++)
{
inputs[i] = img.pixels[i * 4] / 255;
}
// console.log(inputs);
// let inputs_move_right = [];
// for (let i = 0; i < 56 ; i++) {
// inputs_move_right[i] = 0;
// }
//
//for (let j = 56; j < PIXELSSQUARED ; j++)
//{
// let i = 0;
// inputs_move_right[j] = img.pixels[i * 4] / 255;
// i++;
//}
doodle_inputs = inputs; // can inspect in console
// feed forward to make prediction
let prediction = nn.predict(inputs); // array of outputs
let b = find12(prediction); // get no.1 and no.2 guesses
//let c = findMaxandValue(prediction);
//console.log("Prediction " + c[0] + " " + c[1]);
//let prediction_right = nn.predict(inputs_move_right);
//let b_right = find12(prediction_right);
//
//let d = findMaxandValue(prediction_right);
//console.log("Right Prediction " + d[0] + " " + d[1]);
// if(c[1]>d[1]){
// b[0] = c[0];
// }else{
// b[0] = d[0];
//}
//console.log("Right Prediction " + prediction_right);
thehtml = " We classify it as: " + greenspan + b[0] + "</span> <br>" +
" No.2 guess is: " + greenspan + b[1] + "</span>";
// thehtml_right = " Right " + greenspan + b_right[0] + "</span> <br>" +
// " No.2 Right: " + greenspan + b_right[1] + "</span>";
AB.msg ( thehtml, 2 );
// AB.msg ( thehtml_right, 3 );
}
function wipeDoodle()
{
doodle_exists = false;
doodle.background('black');
}
// --- debugging --------------------------------------------------
// in console
// showInputs(demo_inputs);
// showInputs(doodle_inputs);
function showInputs ( inputs )
// display inputs row by row, corresponding to square of pixels
{
var str = "";
for (let i = 0; i < inputs.length; i++)
{
if ( i % PIXELS == 0 ) str = str + "\n"; // new line for each row of pixels
var value = inputs[i];
str = str + " " + value.toFixed(2) ;
}
console.log (str);
}
class ActivationFunction {
constructor(func, dfunc) {
this.func = func;
this.dfunc = dfunc;
}
}
let sigmoid = new ActivationFunction(
x => 1 / (1 + Math.exp(-x)),
y => y * (1 - y)
);
//function sigmoid(x) {
//return 1 / (1 + Math.exp(-x));
//}
let tanh = new ActivationFunction(
x => Math.tanh(x),
y => 1 - (y * y)
);
let relu = new ActivationFunction(
x => Math.max(0,x),
y => 1 - (y * y)
);
//let dsigmoid = new ActivationFunction(
// x => sigmoid(x) * (1 - sigmoid(x)),
// y => y * (1 - y)
//);
class NeuralNetwork {
/*
* if first argument is a NeuralNetwork the constructor clones it
* USAGE: cloned_nn = new NeuralNetwork(to_clone_nn);
*/
constructor(in_nodes, hid_nodes, out_nodes) {
if (in_nodes instanceof NeuralNetwork) {
let a = in_nodes;
this.input_nodes = a.input_nodes;
this.hidden_nodes = a.hidden_nodes;
this.output_nodes = a.output_nodes;
this.weights_ih = a.weights_ih.copy();
this.weights_ho = a.weights_ho.copy();
this.bias_h = a.bias_h.copy();
this.bias_o = a.bias_o.copy();
} else {
this.input_nodes = in_nodes;
this.hidden_nodes = hid_nodes;
this.output_nodes = out_nodes;
this.weights_ih = new Matrix(this.hidden_nodes, this.input_nodes);
this.weights_ho = new Matrix(this.output_nodes, this.hidden_nodes);
this.weights_ih.randomize();
this.weights_ho.randomize();
this.bias_h = new Matrix(this.hidden_nodes, 1);
this.bias_o = new Matrix(this.output_nodes, 1);
this.bias_h.randomize();
this.bias_o.randomize();
}
// TODO: copy these as well
this.setLearningRate();
this.setActivationFunction();
}
predict(input_array) {
// Generating the Hidden Outputs
let inputs = Matrix.fromArray(input_array);
let hidden = Matrix.multiply(this.weights_ih, inputs);
hidden.add(this.bias_h);
// activation function!
hidden.map(this.activation_function.func);
// Generating the output's output!
let output = Matrix.multiply(this.weights_ho, hidden);
output.add(this.bias_o);
output.map(this.activation_function.func);
// Sending back to the caller!
return output.toArray();
}
setLearningRate(learning_rate = 0.1) {
this.learning_rate = learning_rate;
}
setActivationFunction(func = sigmoid) {
this.activation_function = func;
}
train(input_array, target_array) {
// Generating the Hidden Outputs
let inputs = Matrix.fromArray(input_array);
let hidden = Matrix.multiply(this.weights_ih, inputs);
hidden.add(this.bias_h);
// activation function!
hidden.map(this.activation_function.func);
// Generating the output's output!
let outputs = Matrix.multiply(this.weights_ho, hidden);
outputs.add(this.bias_o);
outputs.map(this.activation_function.func);
// Convert array to matrix object
let targets = Matrix.fromArray(target_array);
// Calculate the error
// ERROR = TARGETS - OUTPUTS
let output_errors = Matrix.subtract(targets, outputs);
// let gradient = outputs * (1 - outputs);
// Calculate gradient
let gradients = Matrix.map(outputs, this.activation_function.dfunc);
gradients.multiply(output_errors);
gradients.multiply(this.learning_rate);
// Calculate deltas
let hidden_T = Matrix.transpose(hidden);
let weight_ho_deltas = Matrix.multiply(gradients, hidden_T);
// Adjust the weights by deltas
this.weights_ho.add(weight_ho_deltas);
// Adjust the bias by its deltas (which is just the gradients)
this.bias_o.add(gradients);
// Calculate the hidden layer errors
let who_t = Matrix.transpose(this.weights_ho);
let hidden_errors = Matrix.multiply(who_t, output_errors);
// Calculate hidden gradient
let hidden_gradient = Matrix.map(hidden, this.activation_function.dfunc);
hidden_gradient.multiply(hidden_errors);
hidden_gradient.multiply(this.learning_rate);
// Calcuate input->hidden deltas
let inputs_T = Matrix.transpose(inputs);
let weight_ih_deltas = Matrix.multiply(hidden_gradient, inputs_T);
this.weights_ih.add(weight_ih_deltas);
// Adjust the bias by its deltas (which is just the gradients)
this.bias_h.add(hidden_gradient);
// outputs.print();
// targets.print();
// error.print();
}
serialize() {
return JSON.stringify(this);
}
static deserialize(data) {
if (typeof data == 'string') {
data = JSON.parse(data);
}
let nn = new NeuralNetwork(data.input_nodes, data.hidden_nodes, data.output_nodes);
nn.weights_ih = Matrix.deserialize(data.weights_ih);
nn.weights_ho = Matrix.deserialize(data.weights_ho);
nn.bias_h = Matrix.deserialize(data.bias_h);
nn.bias_o = Matrix.deserialize(data.bias_o);
nn.learning_rate = data.learning_rate;
return nn;
}
// Adding function for neuro-evolution
copy() {
return new NeuralNetwork(this);
}
// Accept an arbitrary function for mutation
mutate(func) {
this.weights_ih.map(func);
this.weights_ho.map(func);
this.bias_h.map(func);
this.bias_o.map(func);
}
}