// Cloned by Karl Murphy on 26 Nov 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 = 60;
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;
const ZOOMPIXELSSQUARED = ZOOMPIXELS * ZOOMPIXELS
// 3 rows of
// large image + 50 gap + small image
// 50 gap between rows
const canvaswidth = ( PIXELS + ZOOMPIXELS ) + 50;
//console.log("CANVAS WI " + canvaswidth);
const canvasheight = ( ZOOMPIXELS * 3 ) + 100;
//console.log("CANVAS hI " + canvas);
const DOODLE_THICK = 18; // thickness of doodle lines
const DOODLE_BLUR = 2; // 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;
//doodle_finished = 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 );
//https://p5js.org/reference/#/p5/createGraphics
doodle = createGraphics ( ZOOMPIXELS , ZOOMPIXELS ); // doodle on larger canvas
doodle.pixelDensity(1);
//Karl Murphy code
doodle.canvas.id = "doodle_canvas";
// JS load other JS
// maybe have a loading screen while loading the JS and the data set
AB.loadingScreen();
//Karl Murphy code
$.getScript ( "/uploads/codingtrain/matrix.js", function()
{
$.getScript ( "uploads/kmurfi/opencv.js", function()
{
$.getScript ( "uploads/kmurfi/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 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
}
// 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
nn.train ( inputs, 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 prediction = nn.predict(inputs); // 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;
}
// --- the draw function -------------------------------------------------------------
// every step:
// function mouseReleased() {
// console.log("suc");
// }
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();
}
// if (doodle_finished){
// 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.textAlign(CENTER);
doodle.stroke('white');
doodle.strokeWeight( DOODLE_THICK );
doodle.line(mouseX, mouseY, pmouseX, pmouseY);
}
}
else
{
// are we exiting a drawing
if ( mousedrag )
{
mousedrag = false;
//doodle_finished = true;
// 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
}
//Karl Murphy code
function centerOfMass (img)
{
sum_x = 0;
sum_y = 0;
num = 0;
for (i=0; i<PIXELS; i++)
{
for (j=0; j<PIXELS; j++)
{
if (img[i + (j * PIXELS)] == 1)
{
sum_x = sum_x + i;
sum_x = sum_y + j;
num = num+1;
}
}
}
sum_x = sum_x / num;
sum_y = sum_y / num;
return {"x": sum_x, "y": sum_y};
}
//Karl Murphy code
function oned_to_2d_array(oned_array, elements_per_each_array) {
var matrix = [], i, k;
for (i = 0, k = -1; i < oned_array.length; i++) {
if (i % elements_per_each_array === 0) {
k++;
matrix[k] = [];
}
matrix[k].push(oned_array[i]);
}
return matrix;
}
//Karl Murphy code
function oned_to_2d_array_with_padding(oned_array, elements_per_each_array, factors, matrix) {
top_rows_with_zeros = Math.ceil((28 - factors.rows) / 2);
bottom_rows_with_zeros = Math.ceil(28 - ((28 - factors.rows) / 2)) ;
left_cols_with_zeros = Math.ceil((28 - factors.cols) / 2);
right_cols_with_zeros = Math.ceil(28 - ((28 - factors.cols) / 2));
console.log("bottom_rows_with_zeros" + bottom_rows_with_zeros);
console.log("left_cols_with_zeros" + left_cols_with_zeros);
for (var i = 0;i<28;i++){
for (var j = 0;j<28;i++){
// matrix[i][j] = 0;
}
}
// index = 0;
// for (var x = top_rows_with_zeros;i<bottom_rows_with_zeros;i++){
// for (var y = left_cols_with_zeros;j<right_cols_with_zeros;i++){
// matrix[i][j] = oned_array[index];
// index = index + 1;
// }
// }
// return matrix;
}
//Karl Murphy code
function find_top_rows_to_delete(the_array){
rows_to_delete = 0
for(var i = 0; i < the_array.length; i++)
{
var row = the_array[i];
for(var j = 0; j < row.length; j++)
{
if (row[j] !== 0){
return rows_to_delete;
}
}
rows_to_delete = i + 1;
}
}
//Karl Murphy code
function find_bottom_rows_to_delete(the_array){
rows_to_delete = 27
for(var i = the_array.length -1; i > 0; i--) {
var row = the_array[i];
for(var j = 0; j < row.length; j++)
{
if (row[j] !== 0){
return rows_to_delete;
}
}
rows_to_delete = i - 1;
}
}
//Karl Murphy code
function find_left_columns_to_delete(the_array){
left_colums_to_delete = 0
for(var i = 0; i < 28; i++)
{
for(var j = 0; j < 28; j++)
{
if (the_array[j][i] !== 0){
return left_colums_to_delete;
}
}
left_colums_to_delete = i + 1;
}
}
//Karl Murphy code
function find_right_columns_to_delete(the_array){
right_colums_to_delete = 27
for(var i = 27; i > 0 ; i--)
{
for(var j = 0; j < 28; j++)
{
if (the_array[j][i] !== 0){
return right_colums_to_delete;
}
}
right_colums_to_delete = i - 1;
}
}
//Karl Murphy code
function find_blank_rows_and_columns(matrix){
start_row_point = find_top_rows_to_delete(matrix);
//console.log("top_rows_to_delete " + start_row_point);
end_row_point = find_bottom_rows_to_delete(matrix);
//console.log("bottom_rows_to_delete " + end_row_point);
start_column_point = find_left_columns_to_delete(matrix);
//console.log("left_columns_to_delete " + start_column_point);
end_column_point = find_right_columns_to_delete(matrix);
//console.log("right_columns_to_delete " + end_column_point);
//New matrix dimensions
matrix_rows = (end_row_point - start_row_point) + 1
matrix_columns = (end_column_point - start_column_point) + 1
return {"rows" : matrix_rows,
"columns": matrix_columns,
"start_row_point": start_row_point,
"end_row_point": end_row_point,
"start_column_point": start_column_point,
"end_column_point": end_column_point
}
}
//Karl Murphy code
function create_2d_array(rows) {
var arr = [];
for (var i=0;i<rows;i++) {
arr[i] = [];
}
return arr;
}
//Karl Murphy code
function resize_array(mat_dims){
if (mat_dims.rows > mat_dims.columns){
factor = 20.0/mat_dims.rows
//console.log("in if ..factor == " + factor);
rows = 20
cols = Math.ceil(mat_dims.columns*factor)
}
else{
factor = 20.0/mat_dims.columns
cols = 20
//console.log("in else ...factor == " + factor);
rows = Math.ceil(mat_dims.rows*factor)
}
return {"rows": rows, "cols": cols};
}
//Karl Murphy code
function copy_non_zero_rows_to_new_matrix(old_matrix, new_matrix, mat_dims ){
for(var i = mat_dims.start_row_point, x = 0; i <= mat_dims.end_row_point; x++, i++)
{
var row = old_matrix[i];
for(var j = mat_dims.start_column_point, y=0; j <= mat_dims.end_column_point; y++, j++)
{
new_matrix[x][y] = row[j];
}
}
return new_matrix;
}
//Karl Murphy code
function get_padding_amounts(factors){
top_rows = Math.floor((28 - factors.rows) / 2);
bottom_rows = Math.ceil((28 - factors.rows) / 2);
left_cols_padding = Math.floor((28 - factors.cols) / 2);
right_cols_padding = Math.ceil((28 - factors.cols) / 2);
return {"top_rows": top_rows,
"bottom_rows": bottom_rows,
"left_cols_padding": left_cols_padding,
"right_cols_padding": right_cols_padding}
}
//Karl Murphy code
function convert_mat_image_to_2d_array(mat_image, matrix){
for(let i = 0; i < mat_image.rows; i++){
for(let j = 0; j < mat_image.cols; j++){
matrix[i][j] = mat_image.data[i*j*4];
}
}
return matrix;
}
//Karl Murphy code
function strip_out_zeros(mat_dims, matrix){
let arr = [];
for (let i = mat_dims.start_row_point; i <= mat_dims.end_row_point ; i++){
for (let j = mat_dims.start_column_point; j<= mat_dims.end_column_point ; j++){
arr.push(matrix[i][j]);
}
}
return arr;
}
/*
Karl Murphy code
Replicate steps found here - https://medium.com/@o.kroeger/tensorflow-mnist-and-your-own-handwritten-digits-4d1cd32bbab4
*/
function guessDoodle()
{
// doodle is createGraphics not createImage
// let img = doodle.get();
// img.resize ( PIXELS, PIXELS );
// img.loadPixels();
//STEP 1 - read image in grayscale mode
let gray_scaled_image= cv.imread("doodle_canvas", cv.CV_LOAD_IMAGE_GRAYSCALE);
//STEP 2
//Rescale the image to 28*28px
let image_28_px = new cv.Mat();
let dsize = new cv.Size(28, 28);
cv.resize(gray_scaled_image, image_28_px, dsize, 0, 0, cv.INTER_AREA);
gray_scaled_image.delete();
//console.log(rescaled_28_px);
//let ret2;
//let dst = new cv.Mat();
//ret2,grey = cv.threshold(rescaled_28_px, dst, 127, 255, cv.THRESH_BINARY);
//ret2,grey = cv.threshold(grey,0,255,cv.THRESH_BINARY | cv.THRESH_OTSU)
//Convert MAT IMAGE to 2d array
let matrix_28_px = create_2d_array(28);
matrix_28_px = convert_mat_image_to_2d_array(image_28_px, matrix_28_px);
console.log("matrix_28_px");
console.log(matrix_28_px);
//STEP 3a- Attempt to remove zeros (black) around image and resize the image to 20 * 20px
matrix_dimensions = find_blank_rows_and_columns(matrix_28_px);
console.log("matrix_dimensions");
console.log(matrix_dimensions);
//new_matrix = create_2d_array(matrix_dimensions.rows);
// new_array_without_zeros = strip_out_zeros(matrix_dimensions, matrix_28_px)
// console.log("new_array_without_zeros");
// console.log(new_array_without_zeros);
// let mat_XXX = cv.matFromArray(matrix_dimensions.rows, matrix_dimensions.columns, cv.CV_8U, new_array_without_zeros)
// console.log("mat_XXX");
// console.log(mat_XXX);
factors = resize_array(matrix_dimensions);
console.log("factors");
console.log(factors);
let image_20_px = new cv.Mat();
dsize = new cv.Size(factors.cols, factors.rows);
cv.resize(image_28_px, image_20_px, dsize, 0, 0, cv.INTER_AREA);
console.log("image_20_px");
console.log(image_20_px);
//Convert MAT IMAGE to 2d array
// let xxx = create_2d_array(20);
// matrix_28_px = convert_mat_image_to_2d_array(rescaled_20_px, xxx);
// console.log(xxx);
// A = new cv.Mat(20, 20, cv.CV_8U, xxx ); //for 2D array
// console.log("A");
// console.log(A);
//STEP 3b - Insert inner 20*20px box in to a outer 28*28px box and pad around the inner box with zeros
let padded_image_28_px = new cv.Mat();
let s = new cv.Scalar(0, 0, 0, 255);
p = get_padding_amounts(factors)
console.log("padding amounts");
console.log(p);
console.log(padded_image_28_px);
cv.copyMakeBorder(image_20_px, padded_image_28_px, p.top_rows, p.bottom_rows, p.left_cols_padding, p.right_cols_padding, cv.BORDER_CONSTANT, s);
//Convert MAT IMAGE to 2d array
let ppp = create_2d_array(28);
ppp_x = convert_mat_image_to_2d_array(padded_image_28_px, ppp);
console.log("ppp_x");
console.log(ppp_x);
//console.log(padded_28_px);
// set up inputs
// let inputs = [];
// for (let i = 0; i < PIXELSSQUARED ; i++)
// {
// inputs[i] = rescaled_28_px.data[i * 4];
// }
//console.log(rescaled_28_px);
//old_matrix_28_px = oned_to_2d_array(inputs, 28);
//console.log(old_matrix_28_px);
//console.log(old_matrix[12][2]);
//console.log("new_rescaled_20_px");
//console.log(new_rescaled_20_px);
let inputs = [];
for (let i = 0; i < PIXELSSQUARED ; i++)
{
inputs[i] = padded_image_28_px.data[i * 4]/255;
}
// new_2d_array = create_2d_array(28)
// nmm = oned_to_2d_array_with_padding(k_inputs, 28, factors, new_2d_array);
// console.log(nnm);
//console.log(k_inputs);
// cv.resize(rescaled_28_px, rescaled_20_px, fx=factors.rows, fy=factors.cols, cv.INTER_AREA);
// console.log(rescaled_20_px);
// img.resize(factors.rows, factors.cols);
// console.log(img);
//cloned_array = copy_non_zero_rows_to_new_matrix(old_matrix, new_matrix, matrix_dimensions );
//console.log("CLONED ARRAY" + cloned_array);
// centre_of_mass = centerOfMass (inputs);
// console.log(centre_of_mass);
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
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 ( 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);
}