Sound Classification Bildstatistik

mySketch
xxxxxxxxxx
 
  // Global variable to store the classifier
let classifier;
​
// Label
let label = 'listening...';
let confidence;
​
let hahn = 3;
let taube = 5;
​
let img, img_hahn, img_taube;
​
// Teachable Machine model URL:
let soundModel = 'https://teachablemachine.withgoogle.com/models/uOFvz1eDY/';
​
​
function preload() {
  // Load the model
  classifier = ml5.soundClassifier(soundModel + 'model.json');
  
  img = loadImage("Vögel_Icons_V1-04.png"); // microphone
  img_hahn = loadImage("Vögel_Icons_V1-02.png"); // clap
  img_taube = loadImage("Vögel_Icons_V1-03.png"); // snap
}
​
function setup() {
  createCanvas(windowWidth, windowHeight);
  
  // Start classifying
  // The sound model will continuously listen to the microphone
  classifier.classify(gotResult);
}
​
function draw() {
  background(200);
  
  imageMode(CENTER); 
  
  let icon_size = 50;
  
  // start position
  translate(100, height/4);
  
  // left to right
  for (i=0; i<hahn; i++) {
    image(img_hahn, i*icon_size, 0, icon_size, icon_size);
  }
  
  // next row
  translate(0, icon_size*2);
  for (i=0; i<taube; i++) {
    image(img_taube, i*icon_size, 0, icon_size, icon_size);
  }
  
  
  /*
  // colums
  let colums = 5;
  
  push();
  translate(width/2 - colums*icon_size - icon_size, height/4);
  for (i=1; i<=snap; i++) {
    image(img_snap, ((i-1)%colums)*icon_size, 0, icon_size, icon_size);
    if (i%colums == 0)
      translate(0, icon_size); // next row
  }
  pop();
  
  push();
  translate(width/2 + icon_size, height/4);
  for (i=1; i<=clap; i++) {
    image(img_clap, ((i-1)%colums)*icon_size, 0, icon_size, icon_size);
    if (i%colums == 0)
      translate(0, icon_size); // next row
  }
  pop();
  */
  
  //textSize(50);
  //textAlign(CENTER, CENTER);
  
  //text("Clap: " + clap, width / 2, height / 3);
  //text("Snap: " + snap, width / 2, height / 2);
​
}
​
​
// The model recognizing a sound will trigger this event
function gotResult(error, results) {
  if (error) {
    console.error(error);
    return;
  }
  // The results are in an array ordered by confidence.
  // console.log(results[0]);
  label = results[0].label;
  confidence = nf(results[0].confidence, 0, 2);
  
  //print(label + " / " + confidence);
  
  if (label.indexOf("clap") > -1 && confidence > 0.9) {
    clap += 1;
  }
  else if (label.indexOf("snap") > -1 && confidence > 0.9) {
    snap += 1;
  }
}