index.js

import { pipeline, env } from 'https://cdn.jsdelivr.net/npm/@xenova/[email protected]';

// Since we will download the model from the Hugging Face Hub, we can skip the local model check
env.allowLocalModels = false;

// Reference the elements that we will need
const status = document.getElementById('status');
const fileUpload = document.getElementById('upload');
const imageContainer = document.getElementById('container');
const example = document.getElementById('example');
const labels = document.getElementById('labels');
const form = document.getElementById('form');

let parsedLabels = ['human face', 'rocket', 'helmet', 'american flag'];
let img = 'https://huggingface.co/datasets/Xenova/transformers.js-docs/resolve/main/astronaut.png';

// Create a new object detection pipeline
status.textContent = 'Loading model...';
const detector = await pipeline('zero-shot-object-detection', 'Xenova/owlvit-base-patch32');
status.textContent = 'Ready';

example.addEventListener('click', (e) => {
    e.preventDefault();
    detect();
});

fileUpload.addEventListener('change', function (e) {
    const file = e.target.files[0];
    if (!file) {
        return;
    }

    const reader = new FileReader();

    // Set up a callback when the file is loaded
    reader.onload = (e2) => {
      img = e2.target.result;
      detect();
    }

    reader.readAsDataURL(file);
});


labels.addEventListener('blur', (e) => {
  parsedLabels = e.target.value.split(",");
  if (img) {
    status.textContent = 'Analysing...';
    detect();
  }
});

form.addEventListener('submit', (e) => {
  e.preventDefault();
  parsedLabels = labels.value.split(",");
  if (img) {
    status.textContent = 'Analysing...';
    detect();
  }
})

// Detect objects in the image
async function detect() {
    imageContainer.innerHTML = '';
    imageContainer.style.backgroundImage = `url(${img})`;

    status.textContent = 'Analysing...';
  
    const output = await detector(img, parsedLabels, { percentage: true });
    status.textContent = '';
    output.forEach(renderBox);
   
}

// Render a bounding box and label on the image
function renderBox({ box, label }) {
    const { xmax, xmin, ymax, ymin } = box;

    // Generate a random color for the box
    const color = '#' + Math.floor(Math.random() * 0xFFFFFF).toString(16).padStart(6, 0);

    // Draw the box
    const boxElement = document.createElement('div');
    boxElement.className = 'bounding-box';
    Object.assign(boxElement.style, {
        borderColor: color,
        left: 100 * xmin + '%',
        top: 100 * ymin + '%',
        width: 100 * (xmax - xmin) + '%',
        height: 100 * (ymax - ymin) + '%',
    })

    // Draw label
    const labelElement = document.createElement('span');
    labelElement.textContent = label;
    labelElement.className = 'bounding-box-label';
    labelElement.style.backgroundColor = color;

    boxElement.appendChild(labelElement);
    imageContainer.appendChild(boxElement);
}