Image Classification Development Tutorials, Guides & Insights

import React, { useState, useEffect } from 'react';
import * as tf from '@tensorflow/tfjs';
import '@tensorflow/tfjs-backend-cpu';
import '@tensorflow/tfjs-backend-webgl';

function ImageClassifier() {
  const [image, setImage] = useState(null);
  const [model, setModel] = useState(null);
  const [predictions, setPredictions] = useState(null);

  useEffect(() => {
    const loadModel = async () => {
      const loadedModel = await tf.loadGraphModel('https://path-to-model/model.json');
      setModel(loadedModel);
    };

    loadModel();
  }, []);

  const handleImageUpload = (event) => {
    const file = event.target.files[0];
    const reader = new FileReader();

    reader.onload = async () => {
      const img = new Image();
      img.src = reader.result;
      img.onload = async () => {
        const tensor = tf.browser.fromPixels(img)
          .resizeNearestNeighbor([224, 224])
          .toFloat()
          .expandDims();

        const predictions = await model.predict(tensor).data();
        setPredictions(predictions);
      };
    };

    if (file) {
      reader.readAsDataURL(file);
    }
  };

  return (
    <div>
      <input type="file" accept="image/*" onChange={handleImageUpload} />
      {image && <img src={image} alt="Uploaded" />}
      {predictions && (
        <ul>
          {predictions.map((pred, index) => (
            <li key={index}>{pred}</li>
          ))}
        </ul>
      )}
    </div>
  );
}

export default ImageClassifier;

You can enhance the user experience by displaying the predictions in a user-friendly format, such as showing the top 3 predictions with confidence scores.