Tensorflow.js tf.train.adam()用法及代碼示例

// A cubic function with its coeffiecient l,m,n.
const x = tf.tensor1d([0, 1, 2, 3]);
const y = tf.tensor1d([1., 2., 5., 11.]);
  
const l = tf.scalar(Math.random()).variable();
const m = tf.scalar(Math.random()).variable();
const n = tf.scalar(Math.random()).variable();
  
// y = l * x^3 - m * x + n.
const f = x => l.mul(x.pow(3)).sub(m.mul(x)).add(n);
const loss = (pred, label) => pred.sub(label).square().mean();
  
const learningRate = 0.01;
const optimizer = tf.train.adam(learningRate);
  
// Training the model and printing the coefficients.
for (let i = 0; i < 10; i++) {
   optimizer.minimize(() => loss(f(x), y));
  console.log(
     `l:${l.dataSync()}, m:${m.dataSync()}, n:${n.dataSync()}`);
}
  
// Predictions are made.
  
const preds = f(x).dataSync();
preds.forEach((pred, i) => {
   console.log(`x:${i}, pred:${pred}`);
});

// Importing the tensorflow.js library
import * as tf from "@tensorflow/tfjs"
  
// defining the model
const model = tf.sequential({
    layers:[tf.layers.dense({ units:1, inputShape:[12] })],
});
    
  
// in the compilation we use tf.train.adam optimizer 
  const optimizer = tf.train.adam(0.001);
model.compile({ optimizer:optimizer, loss:"meanSquaredError" },
              (metrics = ["accuracy"]));
    
// evaluate the model which was compiled above
const result = model.evaluate(tf.ones([10, 12]), tf.ones([10, 1]), {
    batchSize:4,
});
    
// print the result
result.print();