Code viewer for World: Character recognition neur...

// Cloned by Akash Gupta on 2 Dec 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 ---------------------------------------

// Intgerated Web cnn from https://github.com/DenseInL2/webcnn/
// All the required functions is commented out starting with "Web cnn"

const PIXELS        = 28;                       // images in data set are tiny 
const PIXELSSQUARED = PIXELS * PIXELS;

var requiredPixels = 24; // Added this to make the images compatible with the web cnn model

// 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 = 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 = 18;    // thickness of doodle lines 
const DOODLE_BLUR = 0;      // 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
}    

// 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: ---------------------------------------------------------

// Web cnn : Position the image drawn to the center
function imageToCenter(inputs, size) {
    var matrix = oneDimensionTo2D(inputs,size);
    // Get the indexes of the four corners
    var cornerPositions = getIndexOfCorners(matrix, Number.MAX_VALUE, Number.MAX_VALUE, -1, -1);
    var Y = Math.floor((size - cornerPositions[3] - cornerPositions[2]) / 2);
    var X = Math.floor((size - cornerPositions[1] - cornerPositions[0]) / 2);

    //Create the new array
    var matrix2 = [];
    for(var i=0;i<size;i++){
        matrix2[i] = [];
        for (var j = 0; j < size; j++) {
            matrix2[i][j] = 0;
        }
    } 
        
    for (i = cornerPositions[2]; i <= cornerPositions[3]; i++) {
        for (j = cornerPositions[0]; j <= cornerPositions[1]; j++) {
            matrix2[i + Y][j + X] = matrix[i][j];
        }
    }
  
    result = twoDto1D(matrix2, size);
    return result;
}

// Web cnn: two dimension to 1 dimension
function twoDto1D (arr, size){
    var result = [];
    for (var i = 0; i < size; i++) {
        for (var j = 0; j < size; j++) {
            result[i * size + j] = arr[i][j];
        }
    }
    return result;
}

// Web cnn: Find the corners of the image
function getIndexOfCorners (matrix, top, left, bottom, right){
    for (var i = 0; i < matrix.length; i++) {
        var l = matrix[i].indexOf(255);
        var r = matrix[i].lastIndexOf(255);
        if (l >= 0 && l < left){
            left = l;
        }
        if (r >= 0 && r > right){
            right = r;
        }
        if (l >= 0 && i < top) {
            top = i;
        }
        if (l >= 0 && i > bottom) {
            bottom = i;
        }
    }
    return [left, right, top, bottom];
}

// Web cnn: Converts one dimension array into 2D
function oneDimensionTo2D(arr, size){
    var matrix = [];
    for (var i = 0; i < size; i++) {
        matrix[i] = [];
        for (var j = 0; j < size; j++) {
            matrix[i][j] = arr[(i * size + j) * 4];
        }
    }
    return matrix;
}

// Web cnn: New function to guess the doodle which uses web cnn
function guessTheDigit()
{
    var 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;
    }
    
    doodle_inputs = inputs;     // can inspect in console 
    var centeredImage = imageToCenter(img.pixels, PIXELS); // To center the doodle image
    var format = updateImageFormat(centeredImage, 24);  // update the format with 24 X 24
    var result = cnn.classifyImages([format]); 
    var b = find12(result[0].values);       // 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);
}

// Web cnn: Init code for WebCNN got it from the repository https://github.com/DenseInL2/webcnn/blob/master/digitdemo.js
function loadNetworkFromJSON(networkJSON)
{
    cnn = new WebCNN();

	if (networkJSON.momentum != undefined) cnn.setMomentum( networkJSON.momentum );
	if (networkJSON.lambda != undefined) cnn.setLambda( networkJSON.lambda );
	if (networkJSON.learningRate != undefined) cnn.setLearningRate( networkJSON.learningRate );

	for ( var layerIndex = 0; layerIndex < networkJSON.layers.length; ++layerIndex )
	{
		let layerDesc = networkJSON.layers[ layerIndex ];
		//console.log( layerDesc );
		cnn.newLayer( layerDesc );
	}

	for ( var layerIndex = 0; layerIndex < networkJSON.layers.length; ++layerIndex )
	{
		let layerDesc = networkJSON.layers[ layerIndex ];

		switch ( networkJSON.layers[ layerIndex ].type )
		{
			case LAYER_TYPE_CONV:
			case LAYER_TYPE_FULLY_CONNECTED:
			{
				if (layerDesc.weights != undefined && layerDesc.biases != undefined )
				{
					cnn.layers[ layerIndex ].setWeightsAndBiases( layerDesc.weights, layerDesc.biases );
				}
				break;
			}
		}
	}

	cnn.initialize();
	return cnn;
}

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()
            {
                $.getScript ( "/uploads/akash037/mathutils.js", function()
                {
                    $.getScript ( "/uploads/akash037/webcnn.js", function()
                    {
                        $.getJSON("/uploads/akash037/cnn_mnist_10_20_98accuracy.json", function(res, err)
                        {
                            console.log ("All JS loaded");
                            cnn = loadNetworkFromJSON( res );
                            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 
  });
}

// web cnn: Requried Image Data Format for web cnn
function updateImageFormat(img) {
    var imageData = {
        "width": 24,
        "height": 24,
        "data": getRequiredImage(reduceImageSize(img)).pixels
    }
    return imageData;
}

// web cnn: Reduce the size of the image from 28 * 28 into 24 * 24
function reduceImageSize(img) {
    var startIndex = PIXELS - 24;
    var X = Math.floor(Math.random() * startIndex);
    var Y = Math.floor(Math.random() * startIndex);
    var newPixelCount = 24;
    var xEnd = X + newPixelCount;
    var yEnd = Y + newPixelCount;
    var inputs = [];
    for (var i = X; i < xEnd; i++) {
        for (let j = Y; j < yEnd; j++) {
            inputs.push(img[i * PIXELS + j])
        }
    }
    return inputs;
}

// web cnn: Creates a p5 image object of size 24 * 24
function getRequiredImage (img)      // make a P5 image object from a raw data array   
{
    let theimage  = createImage (24, 24);    // make blank image, then populate it 
    theimage.loadPixels();        
    for (let i = 0; i < 24 * 24 ; 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
  }

  // 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++;
  }
}

// web cnn: This function does testing on the test set from the precalculated weights from web cnn models
function testItWithCNN(){
    var img = mnist.test_images[test_index];
    var label = mnist.test_labels[test_index];

    var format = updateImageFormat(img, 24);
    var result = cnn.classifyImages([format]); 
    var b = find12(result[0].values);
    total_tests++;
    if (b[0] == label)  total_correct++;
    
    var 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;
    }
}

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)   // 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();
        testItWithCNN();
    }
      
}

  // 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();
    guessTheDigit();
    //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);
  
  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);
}