// Cloned by yilin li on 18 Nov 2021 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;
const PIXELS_CENTER_SQ_LEN = 20;
const PIXELS_PADDING_LEN = 4;
//--- can modify all these --------------------------------------------------
// no of nodes in network
const noinput = PIXELSSQUARED;
const nohidden = 64;
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 = 10; // thickness of doodle lines
const DOODLE_BLUR = 5; // 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?
let cnn_model;
let cnn_trainer;
let cnn_train_time = 0;
let cnn_total_correct = 0;
let cnn_test_time = 0;
let train_time = 0;
let test_time = 0;
// 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
}
// make run header bigger
AB.headerCSS ( { "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();
});
});
});
//
$.getScript("/uploads/lin123/convnet-min.js",function()
{
layer_defs = [],
layer_defs.push({
type: "input",
out_sx: 28,
out_sy: 28,
out_depth: 1
}),
layer_defs.push({
type: "conv",
sx: 5,
filters: 8,
stride: 1,
pad: 2,
activation: "relu"
}),
layer_defs.push({
type: "pool",
sx: 2,
stride: 2
}),
layer_defs.push({
type: "conv",
sx: 5,
filters: 16,
stride: 1,
pad: 2,
activation: "relu"
}),
layer_defs.push({
type: "pool",
sx: 3,
stride: 3
}),
layer_defs.push({
type: "softmax",
num_classes: 10
}),
AB.restoreData(function(dt){
if(dt !== undefined){
cnn_model.fromJSON(dt);
}
});
(cnn_model = new convnetjs.Net).makeLayers(layer_defs),
cnn_trainer = new convnetjs.SGDTrainer(cnn_model, {
method: "adadelta",
batch_size: 20,
l2_decay: .001
})
})
}
// 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 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 getCnnInputs( img ) {
for (var t = new convnetjs.Vol(PIXELS, PIXELS, 1, 0), n = 0; n < PIXELSSQUARED; n++) t.w[n] = img[n];
return t
}
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
}
// set up the inputs
let inputs = getInputs ( img ); // get inputs from data array
//
let s = getCnnInputs( inputs );
// 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 a = (new Date).getTime();
nn.train ( inputs, targets );
//
train_time += (new Date).getTime() - a;
let l = (new Date).getTime();
cnn_trainer.train(s, label),
cnn_train_time += (new Date).getTime() - l,
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 );
AB.saveData(cnn_model.toJSON());
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 i = (new Date).getTime();
let prediction = nn.predict(inputs); // array of outputs
//
test_time += (new Date).getTime() - i;
let guess = findMax(prediction); // the top output
//
let o = getCnnInputs(inputs);
let a = (new Date).getTime();
let l = cnn_model.forward(o);
cnn_test_time += (new Date).getTime() - a;
let d = findMax(l.w);
total_tests++;
if (guess == label) total_correct++;
//
if (d == label) cnn_total_correct++;
let percent = (total_correct / total_tests) * 100 ;
//
let c = cnn_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 );
//
thehtml = " Testrun: " + testrun + " No: " + total_tests + " <br> NN Correct: " + total_correct + " CNN Correct: " + cnn_total_correct +
"<br> NN Train Time(ms): " + train_time + " CNN Train Time(ms): " + cnn_train_time + "<br> NN Predict Time(ms): "
+ test_time + " CNN Predict Time(ms): " + cnn_test_time + "<br> NN Score(%): " + greenspan + percent.toFixed(2)
+ " </span> CNN Score(%): " + greenspan + c.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;
cnn_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) // new no1
{
// old no1 becomes no2
no2 = no1;
no2value = no1value;
// now put in the new no1
no1 = i;
no1value = a[i];
}
else if (a[i] > no2value) // new no2
{
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;
}
// --- 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 );
//
let t = getCnnInputs( inputs );
demo_inputs = inputs; // can inspect in console
let prediction = nn.predict(inputs); // array of outputs
let guess = findMax(prediction); // the top output
//
let o = findMax(cnn_model.forward(t).w);
thehtml = " NN classify it as: " + greenspan + guess + "</span> <br> CNN classify it as: " + greenspan + o + "</span> <br>";
// 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 printImg(e) { //print image debug
let t = [];
for (let x = 0; x < e.width * e.height; x++) t[x] = e.pixels[4 * x];
showInputs(PIXELS, inputs.width)
}
function preProcessDoodleImage(e) { //improve doole
let t = []; //create an array where can store our pictures
for (let x = 0; x < PIXELSSQUARED; x++) t[x] = e.pixels[4 * x];
let n = Number.MAX_VALUE;
let o = Number.MIN_VALUE;
for (let e = 0; e < PIXELS; e++) {
let i = Number.MAX_VALUE;
let s = Number.MIN_VALUE;
for (let n = 0; n < PIXELS; n++) {
t[e * PIXELS + n] > 0 && (s = n, i == Number.MAX_VALUE && (i = n))
}
n = Math.min(n, i), // can be used to find the lowest or highest value in a list of arguments
o = Math.max(o, s)
}
let i = Number.MAX_VALUE;
let s = Number.MIN_VALUE;
for (let e = 0; e < PIXELS; e++) {
let n = Number.MAX_VALUE;
let o = Number.MIN_VALUE;
for (let i = 0; i < PIXELS; i++) {
t[i * PIXELS + e] > 0 && (o = i, n == Number.MAX_VALUE && (n = i))
}
i = Math.min(i, n),
s = Math.max(s, o)
}
let r = o - n + 1;
let a = s - i + 1;
let l = createImage(r, a);
l.loadPixels();
for (let e = 0; e < a; e++)
for (let o = 0; o < r; o++) {
let s = t[(e + i) * PIXELS + (o + n)];
l.set(o, e, color(s, s, s))
}
//resize the image,fit the images into this 20x20 pixel box
l.updatePixels(),
r >= a ? l.resize(PIXELS_CENTER_SQ_LEN, 0) : l.resize(0, PIXELS_CENTER_SQ_LEN),
l.loadPixels();
let d = 0;
let m = 0;
let c = 0;
for (let e = 0; e < l.height; e++)
for (let t = 0; t < l.width; t++) {
let n = l.pixels[4 * (e * l.width + t)];
d += n,
m += (t + 1) * n
c += (e + 1) * n
}
// is to shift the inner box so that it is centered
let k = 0 == d ? 0 : Math.round(m / d);
let u = 0 == d ? 0 : Math.round(c / d);
let g = PIXELS_PADDING_LEN + (PIXELS_CENTER_SQ_LEN / 2 - u);
let E = PIXELS_PADDING_LEN + (PIXELS_CENTER_SQ_LEN / 2 - k);
//create new image and new pixels
//need a 28x28 pixel image
shiftImg = createImage(PIXELS, PIXELS);
shiftImg.loadPixels();
for (let e = 0; e < PIXELS; e++)
for (let t = 0; t < PIXELS; t++)
if (e >= PIXELS_PADDING_LEN && t >= PIXELS_PADDING_LEN && e < PIXELS - PIXELS_PADDING_LEN && t < PIXELS - PIXELS_PADDING_LEN)
if (t >= E && e >= g && t <= E + l.width - 1 && e <= g + l.height - 1) {
let n = l.pixels[4 * (l.width * (e - g) + (t - E))];
shiftImg.set(t, e, color(n, n, n))
}
else shiftImg.set(t, e, color(0, 0, 0));
else shiftImg.set(t, e, color(0, 0, 0));
return shiftImg.updatePixels(), shiftImg
}
function guessDoodle()
{
// doodle is createGraphics not createImage
let img = doodle.get();
img.resize ( PIXELS, PIXELS );
img.loadPixels();
//cnn
let t = preProcessDoodleImage(img);
// set up inputs
let inputs = [];
for (let i = 0; i < PIXELSSQUARED ; i++)
{
inputs[i] = t.pixels[i * 4] / 255;
}
doodle_inputs = inputs; // can inspect in console
//cnn
let o = getCnnInputs( inputs );
// 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 s = find12(cnn_model.forward(o).w);
thehtml = " NN classify it as: " + greenspan + b[0] + "</span> No.2 guess is: " + greenspan + b[1] +
"</span> <br> CNN classify it as: " + greenspan + s[0] + "</span> No.2 guess is: " + greenspan + s[1] + "</span>",
AB.msg(thehtml, 2)
// thehtml = " We classify it as: " + greenspan + b[0] + "</span> <br>" +
// " No.2 guess is: " + greenspan + b[1] + "</span>";
// AB.msg ( thehtml, 2 );
}
function wipeDoodle()
{
doodle_exists = false;
doodle.background('black');
}
// --- debugging --------------------------------------------------
// in console
// showInputs(demo_inputs);
// showInputs(doodle_inputs);
/*function showInputs(e, t) {
var n = "";
for (let i = 0; i < e.length; i++) {
i % t == 0 && (n += "\n");
var o = "" + e[i].toFixed(2);
o.length < 6 && (o = new Array(6 - o.length + 1).join("0") + o),
"000.00" == o ? n += " ------": n = n + " " + o
}
console.log(n)
}*/
function showInputs ( inputs,PIXELS)
// 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);
}