output label and confidence

nodejs/onnxruntime.js

@@ -5,15 +5,13 @@ const ort = require('onnxruntime-node');
 (async () => {
   try {
     // Step 1: Load and preprocess the image
-    const imageBuffer = await sharp('./training_images/shirt/00e745c9-97d9-429d-8c3f-d3db7a2d2991.jpg')
+    const imageBuffer = await sharp('./training_images/hat.jpg')
       .resize(128, 128) // Resize to 128x128
       .raw() // Get raw pixel data
       .toBuffer();
 
-    // Convert to Float32 and normalize pixel values to [0, 1]
+    // Normalize to [0, 1] and create input tensor
     const imgArray = Float32Array.from(imageBuffer).map(value => value / 255.0);
-
-    // Add batch dimension [1, 128, 128, 3]
     const inputTensor = new ort.Tensor('float32', imgArray, [1, 128, 128, 3]);
 
     // Step 2: Load ONNX model
@@ -22,7 +20,16 @@ const ort = require('onnxruntime-node');
     // Step 3: Run inference
     const results = await session.run({ [session.inputNames[0]]: inputTensor });
 
-    console.log('Inference outputs:', results[session.outputNames[0]]);
+    // Step 4: Get output probabilities
+    const probabilities = results[session.outputNames[0]].data; // Float32Array
+    const labelIndex = probabilities.indexOf(Math.max(...probabilities)); // Find the index of the max probability
+
+    // Step 5: Load the label map
+    const labelMap = JSON.parse(fs.readFileSync('./labelMap.json', 'utf8')); // Assuming you saved the label map
+    const label = Object.keys(labelMap).find(key => labelMap[key] === labelIndex);
+
+    console.log(`Predicted label: ${label}`);
+    console.log(`Confidencex: ${(probabilities[labelIndex] * 100).toFixed(2)}%`);
   } catch (err) {
     console.error('Error:', err);
   }