Teachable Machine - Images

// First train image model:

// https://teachablemachine.withgoogle.com/train/image

​

​

// Classifier Variable

let classifier;

// Your Model URL from Teachable Machine

let imageModelURL = 'https://teachablemachine.withgoogle.com/models/eAh32u4g1/';

​

// Video

let video;

// To store the classification

let label = "";

let confidence;

​

// Load the model first

function preload() {

  classifier = ml5.imageClassifier(imageModelURL + 'model.json');

}

​

function setup() {

  createCanvas(720, 480);

  // Create the video

  video = createCapture(VIDEO);

  video.size(720, 480);

  video.hide();

  // Set Google Font

  textFont("Roboto Mono");

​

  // Start classifying

  classifyVideo();

}

​

function draw() {

  background(0);

  // Draw the video

  image(video, 0, 0);

  //tint(255, 0, 100);

  //image(video, 0, 0);

  //noTint();

​

  textSize(100);

  textAlign(CENTER);

  if (label == "Cat" && confidence >= 0.99)

  {

    textFont("Roboto Mono");

    text("Cat!", width/2, height/2);

  }

  else if (label == "Synthie" && confidence >= 0.99)

  {

    textFont("Roboto Sans");

    text("Synthie!", width/2, height/2);

  }

  // Draw the debug label

  fill(255);

  textSize(16);

  textAlign(CENTER);

  text(label + "\n" + confidence, width / 2, height - 20);

}

​

// Get a prediction for the current video frame

function classifyVideo() {

  let flippedVideo = ml5.flipImage(video)

  classifier.classify(flippedVideo, gotResult);

  flippedVideo.remove();

}

​

// When we get a result

function gotResult(error, results) {

  // If there is an error

  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);

  // Classifiy again!

  classifyVideo();

}