Update README.md

README.md

@@ -38,43 +38,19 @@ Below is the code implementation for training the XOR neural network using Tenso
 
 ```javascript
 // Import TensorFlow.js library
-import * as tf from '@tensorflow/tfjs';
-
-// XOR dataset
-const xorData = {
-  inputs: tf.tensor2d([[0, 0], [0, 1], [1, 0], [1, 1]]),
-  labels: tf.tensor2d([[0], [1], [1], [0]]),
-};
-
-// Define the neural network architecture
-const model = tf.sequential();
-model.add(tf.layers.dense({ units: 2, inputShape: [2], activation: 'relu' }));
-model.add(tf.layers.dense({ units: 1, activation: 'sigmoid' }));
-
-// Compile the model
-model.compile({ loss: 'meanSquaredError', optimizer: tf.train.sgd(0.1) });
-
-// Train the model
-async function trainModel() {
-  const history = await model.fit(xorData.inputs, xorData.labels, {
-    epochs: 10000,
-    verbose: 0,
-  });
-
-  // Print the final loss after training
-  const finalLoss = history.history.loss[history.history.loss.length - 1];
-  console.log(`Final Loss: ${finalLoss}`);
-
-  // Make predictions
-  const testData = tf.tensor2d([[0, 0], [0, 1], [1, 0], [1, 1]]);
-  const predictions = model.predict(testData);
-
-  // Display the resulting predictions
-  predictions.print();
-}
-
-// Execute the training
-trainModel();
+import * as tf from '@tensorflow/tfjs-node-gpu';
+
+this.model = await tf.loadLayersModel(`file://${this.model_path}/model.json`);
+this.model.compile({
+    optimizer: tf.train.sgd(0.1),
+    loss: 'binaryCrossentropy', // Binary classification loss
+    metrics: ['accuracy'],
+});
+
+this.model.summary();
+
+const x = tf.tensor2d([[1,1]]);
+const prediction = this.model.predict(x) as tf.Tensor;
 ```
 
 ## Resulting Prediction