// Cloned by Abdelshafa Abdala on 15 Nov 2021 from World "Character recognition neural network Practical 2" by Pratiksha Biradar
// Please leave this clone trail here.
const PIXELS=28,
PIXELSSQUARED=PIXELS*PIXELS,
NOTRAIN=6e4,
NOTEST=1e4,
noinput=PIXELSSQUARED,
nohidden=64,
nooutput=10,
learningrate=.1;
let do_training=!0;
const TRAINPERSTEP=50,
TESTPERSTEP=5,
ZOOMFACTOR=5,
ZOOMPIXELS=5*PIXELS,
canvaswidth=PIXELS+ZOOMPIXELS+50,
canvasheight=3*ZOOMPIXELS+100,
DOODLE_THICK=14,
DOODLE_BLUR=2;
let mnist,nn,
doodle,demo,
nnType=1,
trainrun=1,
train_index=0,
testrun=1,
test_index=0,
total_tests=0,
total_correct=0,
doodle_exists=!1,
demo_exists=!1,
mousedrag=!1;
var train_inputs,test_inputs,demo_inputs,doodle_inputs,thehtml;
function randomWeight()
{
return AB.randomFloatAtoB(-.5,.5)}$("#runheaderbox").css({"max-height":"95vh"}),
thehtml=" <button id='save' onclick='saveData();' class='normbutton mybutton' >Save work</button> ",
AB.msg(thehtml,1),
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,2),
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,4),
thehtml="<h3> Hidden tests </h3> ",
AB.msg(thehtml,6),
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,8);
const greenspan="<span style='font-weight:bold; font-size:x-large; color:darkgreen'> ";
function setup()
{
createCanvas(canvaswidth,canvasheight),
(
doodle=createGraphics(ZOOMPIXELS,ZOOMPIXELS)).
pixelDensity(1),
AB.loadingScreen(),
$.getScript("/uploads/codingtrain/matrix.js",function()
{
$.getScript("/uploads/biradap2/nn.js",function()
{
$.getScript("/uploads/codingtrain/mnist.js",function()
{
$.getJSON("/uploads/biradap2/_data.0646079000.json",function(t)
{
console.log("All JS loaded"),
1===nnType?(nn=NeuralNetwork.deserialize(t),
console.log("Activation function used here is: "+nn.getActivationFunction()),
console.log("Sigmoid function with loaded json")):2===nnType?(nn=new NeuralNetwork(noinput,nohidden,nooutput,learningrate,tanh),
console.log("Tanh function is used without loaded json")):
3===nnType?
(
nn=new NeuralNetwork(noinput,nohidden,nooutput,learningrate,sigmoid),
console.log("Activation function used here is: "+nn.getActivationFunction()),
console.log("Loading Default Neural Network")):
4===nnType?(nn=new NeuralNetwork(noinput,nohidden,nooutput,learningrate,relu),
console.log("Relu function is used without loaded json")):
console.log("No neural network has been specified"),loadData()})})})})}
function saveData()
{
AB.saveData(nn)
}
function restoreData()
{
AB.restoreData
(
function(t)
{
nn=NeuralNetwork.deserialize(t),loadData(),
console.log
(
"AB.restoredata"+NeuralNetwork.deserialize(t).serialize())})}
function loadData()
{
loadMNIST
(
function(t)
{
mnist=t,
console.log("All data loaded into mnist object:"),
console.log(mnist),
AB.removeLoading()})}
function getImage(t)
{
let e=createImage(PIXELS,PIXELS);e.loadPixels();
for
(
let n=0;
n<PIXELSSQUARED;n++
)
{
let o=t[n]
i=4*n;
e.pixels[i+0]=o,
e.pixels[i+1]=o,
e.pixels[i+2]=o,
e.pixels[i+3]=255
}
return
e.updatePixels(),
e
}
function getInputs(t)
{let e=[];
for
(
let n=0;
n<PIXELSSQUARED;n++
)
{
let o=t[n];
e[n]=o/255
}
return
e
}
function trainit(t)
{
let e=mnist.train_images[train_index],
n=mnist.train_labels[train_index];
if(t)
{
var
o=getImage(e);
image(o,0,ZOOMPIXELS+50,ZOOMPIXELS,ZOOMPIXELS),
image(o,ZOOMPIXELS+50,ZOOMPIXELS+50,PIXELS,PIXELS)}
let i=getInputs(e),
s=[0,0,0,0,0,0,0,0,0,0];
s[n]=1,
train_inputs=i,
nn.train(i,s),
thehtml=" trainrun: "+trainrun+"<br> no: "+train_index,
AB.msg(thehtml,5),
++train_index==NOTRAIN&&(train_index=0,
console.log("finished trainrun: "+trainrun),trainrun++)
}
function testit()
{
let t=mnist.test_images[test_index],
e=mnist.test_labels[test_index],
n=getInputs(t);
test_inputs=n;
let o=findMax(nn.predict(n));
total_tests++,
o==e&&total_correct++;
let
i=total_correct/total_tests*100;
thehtml=" testrun: "+testrun+"<br> no: "+total_tests+" <br> correct: "+total_correct+"<br> score: "+greenspan+i.toFixed(2)+"</span>",AB.msg(thehtml,7),++test_index==NOTEST&&
(
console.log
(
"finished testrun: "+testrun+" score: "+i.toFixed(2)),
testrun++,test_index=0,
total_tests=0,
total_correct=0
)
}
function find12(t)
{
let
e=0,
n=0,
o=0,
i=0;
let s = 0;
s<t.length;
s++)t[s]>o?(e=s,o=t[s]);
t[s]>i&&(n=s,i=t[s]);
return[e,n];
}
function findMax(t)
{
let e=0,
n=0;
for
(
let
o=0;
o<t.length;o++)t[o]>n&&(e=o,n=t[o]);
return
e
}
function draw()
{
if
(
void 0!==mnist
)
{
if(
background("yellow"),
do_training)
{
for
(
let
t=0;
t<TRAINPERSTEP;
t++)trainit(0==t);
for
(
let
t=0;
t<TESTPERSTEP;
t++)testit()}
if
(
demo_exists&&(drawDemo(),
guessDemo()),
doodle_exists&&(drawDoodle(),
guessDoodle()),
mouseIsPressed)
{
var
t=ZOOMPIXELS+20;
mouseX<t&&mouseY<t&&
pmouseX<t&&pmouseY<t&&(
mousedrag=!0,
doodle_exists=!0,
doodle.stroke("white"),
doodle.smooth(),
doodle.strokeWeight
(DOODLE_THICK),
doodle.line
(
mouseX,mouseY,pmouseX,pmouseY))
}
else mousedrag&&(mousedrag=!1,doodle.filter(BLUR,DOODLE_BLUR))}}
function makeDemo()
{
demo_exists=!0;
var
t=AB.randomIntAtoB(0,NOTEST-1);
demo=mnist.test_images[t];
var e=mnist.test_labels[t];
thehtml="Test image no: "+t+"<br>Classification: "+e+"<br>",
AB.msg(thehtml,9)}
function drawDemo()
{
var
t=getImage(demo);
image(t,0,canvasheight-ZOOMPIXELS,ZOOMPIXELS,ZOOMPIXELS),
image(t,ZOOMPIXELS+50,canvasheight-ZOOMPIXELS,PIXELS,PIXELS)}
function
guessDemo()
{
let t=getInputs(demo);demo_inputs=t;
let e=findMax(nn.predict(t));thehtml=" We classify it as: "+greenspan+e+"</span>",AB.msg(thehtml,10)}
function drawDoodle()
{
let t=doodle.get();
image(t,0,0,ZOOMPIXELS,ZOOMPIXELS),
image(t,ZOOMPIXELS+50,0,PIXELS,PIXELS)}
function guessDoodle()
{
let t=doodle.get();t.resize(PIXELS,PIXELS),t.loadPixels();
let e=[];
for
let n = 0;
n<PIXELSSQUARED;
n++)e[n]=t.pixels[4*n]/255;
doodle_inputs=e;
let n=find12(nn.predict(e));
thehtml=" We classify it as: "+greenspan+n[0]+"</span> <br> No.2 guess is: "+greenspan+n[1]+"</span>",
AB.msg(thehtml,3)}
function wipeDoodle(){doodle_exists=!1,doodle.background("black")}
function showInputs(t){
var e="";
for
(
let n=0;n<t.length;n++){n%PIXELS==0&&(e+="\n"),e=e+" "+t[n].toFixed(2)}
console.log(e)}