|
|
| <html> |
| <head> |
| <script src="https://cdn.jsdelivr.net/npm/@tensorflow/tfjs"></script> |
| </head> |
| <body> |
|
|
| Make sure to run this via a server |
|
|
| <br> |
| <input accept="image/*" type='file' id="input_button" /> |
|
|
| <br> |
| <img id="img1" src="./image.jpg" style="width: 300px " /> |
| <br> <br> |
| <button onclick="predict()">predict</button> |
| <br> |
| <p id="result"> </p> |
|
|
| <script> |
| |
| let image = document.getElementById('img1'); |
| let input_button = document.getElementById('input_button'); |
| |
| input_button.onchange = evt => { |
| const [file] = input_button.files |
| if (file) { |
| image.src = URL.createObjectURL(file) |
| } |
| } |
| |
| async function predict() { |
| var model = await tf.loadGraphModel('./model.json'); |
| |
| let example = tf.browser.fromPixels(document.getElementById("img1") , 3 ).cast('float32'); |
| console.log( example.shape ) |
| example = example.reshape([1,example.shape[0], example.shape[1] ,example.shape[2]]); |
| |
| let prediction = await model.predict(example); |
| let class_scores = await prediction.data(); |
| let max_score_id = class_scores.indexOf(Math.max(...class_scores)); |
| let classes = [ "amina mostafa2024020001" , "misaa babnjki2024020002" , ] ; |
| |
| console.log(class_scores); |
| document.getElementById("result").innerHTML = classes[max_score_id].toString(); |
| } |
| </script> |
| </body> |
| </html> |
