// Cloned by Dheeraj Putta on 26 Nov 2020 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;
let do_training = false;
let restore = !do_training;
// 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;
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?
// 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);
const greenspan = "<span style='font-weight:bold; font-size:x-large; color:darkgreen'> ";
var layer_defs, net, trainer;
var t = layer_defs = [];
layer_defs.push({ type: 'input', out_sx: 24, out_sy: 24, 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 });
var to_train;
var tested = 0;
var to_test;
var trained = 0;
function setup() {
createCanvas(canvaswidth, canvasheight);
doodle = createGraphics(ZOOMPIXELS, ZOOMPIXELS); // doodle on larger canvas
doodle.pixelDensity(1);
doodle.canvas.id = "doodle_canvas";
// 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/djputta/opencv.js", function () {
$.getScript("/uploads/djputta/convnet-min.js", function () {
$.getScript("/uploads/codingtrain/mnist.js", function () {
console.log("All JS loaded");
net = new convnetjs.Net();
loadData();
if (!restore) {
net.makeLayers(layer_defs);
trainer = new convnetjs.SGDTrainer(net, { method: 'adadelta', l2_decay: 0.001 });
}
if (restore) {
$.getJSON("/uploads/djputta/_data.3956514145.json", function (json) {
net.fromJSON(JSON.parse(json)); // this will show the info it in firebug console
});
}
});
});
});
})
});
}
function loadData() {
loadMNIST(function (data) {
mnist = data;
console.log("All data loaded into mnist object:")
console.log(mnist);
to_train = shuffle([...Array(mnist.train_labels.length).keys()]);
to_test = shuffle([...Array(mnist.test_labels.length).keys()]);
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 shuffle(array) {
var currentIndex = array.length, temporaryValue, randomIndex;
// While there remain elements to shuffle...
while (0 !== currentIndex) {
// Pick a remaining element...
randomIndex = Math.floor(Math.random() * currentIndex);
currentIndex -= 1;
// And swap it with the current element.
temporaryValue = array[currentIndex];
array[currentIndex] = array[randomIndex];
array[randomIndex] = temporaryValue;
}
return array;
}
function sample_training_instance() {
var index = to_train.shift();
trained++;
var img = mnist.train_images[index];
var x = new convnetjs.Vol(28, 28, 1, 0.0);
var W = 28 * 28;
for (var i = 0; i < W; i++) {
x.w[i] = img[i] / 255.0;
}
x = convnetjs.augment(x, 24);
return { x: x, label: mnist.train_labels[index], index: index };
}
function sample_test_instance(ind) {
var index;
if (ind !== undefined) {
index = ind;
}
else {
index = to_test.shift();
}
var img = mnist.test_images[index];
var x = new convnetjs.Vol(28, 28, 1, 0.0);
var W = 28 * 28;
for (var i = 0; i < W; i++) {
x.w[i] = img[i] / 255.0;
}
var xs = [];
for (var i = 0; i < 4; i++) {
xs.push(convnetjs.augment(x, 24));
}
return { x: xs, label: mnist.test_labels[index], index: index };
}
function trainit(show) // train the network with a single exemplar, from global var "train_index", show visual on or off
{
let img = sample_training_instance();
// optional - show visual of the image
if (show) {
var theimage = getImage(mnist.train_images[img.index]); // get image from data array
image(theimage, 0, ZOOMPIXELS + 50, ZOOMPIXELS, ZOOMPIXELS); // magnified
image(theimage, ZOOMPIXELS + 50, ZOOMPIXELS + 50, PIXELS, PIXELS); // original
}
step(img)
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++;
AB.saveData(JSON.stringify(net.toJSON()));
}
}
let trainResult = [];
function step(sample) {
var x = sample.x;
var y = sample.label;
var stats = trainer.train(x, y);
var lossx = stats.cost_loss;
var lossw = stats.l2_decay_loss;
var yhat = net.getPrediction();
trainResult.push(yhat === y ? 1.0 : 0.0);
}
function avg(arr) {
return arr.reduce((a, b) => a + b, 0) / arr.length;
}
function testit(ind) {
var num_classes = net.layers[net.layers.length - 1].out_depth;
var sample = sample_test_instance(ind);
var y = sample.label;
var aavg = new convnetjs.Vol(1, 1, num_classes, 0.0);
// ensures we always have a list, regardless if above returns single item or list
var xs = [].concat(sample.x);
var n = xs.length;
for (var i = 0; i < n; i++) {
var a = net.forward(xs[i]);
aavg.addFrom(a);
}
var preds = []
for (var k = 0; k < aavg.w.length; k++) {
preds.push({ k: k, p: aavg.w[k] });
}
preds.sort(function (a, b) { return a.p < b.p ? 1 : -1 });
if (ind === undefined) {
if (test_index < NOTEST) {
total_tests++;
if (preds[0].k == y) 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++;
}
else if (test_index == NOTEST) {
console.log("finished testrun: " + testrun + " score: " + percent.toFixed(2));
testrun++;
test_index = 0;
total_tests = 0;
total_correct = 0;
}
}
return preds;
}
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(DILATE);
// doodle.filter(BLUR, 2);
// doodle.filter (ERODE); // just blur once
// console.log (doodle);
}
}
}
function makeDemo() {
demo_exists = true;
demo = AB.randomIntAtoB(0, NOTEST - 1);
thehtml = "Test image no: " + demo + "<br>" +
"Classification: " + mnist.test_labels[demo] + "<br>";
AB.msg(thehtml, 8);
// type "demo" in console to see raw data
}
function drawDemo() {
var theimage = getImage(mnist.test_images[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 = testit(demo); // array of outputs
let guess = prediction[0].k // the top output
thehtml = " We classify it as: " + greenspan + guess + "</span>";
AB.msg(thehtml, 9);
}
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
var x = new convnetjs.Vol(28, 28, 1, 0.0);
for (let i = 0; i < PIXELSSQUARED; i++) {
x.w[i] = img.pixels[i * 4] / 255;
}
var xs = [];
for (var i = 0; i < 4; i++) {
xs.push(convnetjs.augment(x, 24));
}
doodle_inputs = xs; // can inspect in console
// feed forward to make prediction
var aavg = new convnetjs.Vol(1, 1, 10, 0.0);
// ensures we always have a list, regardless if above returns single item or list
var ys = [].concat(xs);
var n = ys.length;
for (var i = 0; i < n; i++) {
var a = net.forward(ys[i]);
aavg.addFrom(a);
}
var preds = []
for (var k = 0; k < aavg.w.length; k++) {
preds.push({ k: k, p: aavg.w[k] });
}
preds.sort(function (a, b) { return a.p < b.p ? 1 : -1 });
let b = [preds[0].k, preds[1].k];
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');
}