[TensorFlowJS只如初见]实战二·使用TensorFlowJS拟合直线

问题描述
拟合直线 y =（2x -1） + 0.1(-1到1的随机值)
给定x范围（0，3）
可以使用学习框架
建议使用
y = w * x + b 网络模型
代码
1、通过操作（ops）来直接完成模型

<html>

<head>
  <script src="https://cdn.jsdelivr.net/npm/@tensorflow/tfjs">
  </script>

</head>

<body>
  <button class="btn btn-primary" onclick="fnRun0();">开始0</button>
  <div id="p0Id">out0</div>
  <button class="btn btn-primary" onclick="fnRun1();">开始1</button>
  <div id="p1Id">out1</div>
  <button class="btn btn-primary" onclick="fnRun2();">开始2</button>
  <div id="p2Id">out2</div>
</body>

<script>
  //train(xst, yst, numIterations);
  function get_ys(xs) {
    var ys = new Array();
    for (var i = 0; i < xs.length; i++) {
      ys[i] = 2 * xs[i] - 1 + (0.1 * (2 * Math.random() - 1));
    }
    return (ys);
  }
  var xs = new Array();
  for (var i = 0; i < 200; i++) {
    xs[i] = 0.01 * i;
  }
  var ys = get_ys(xs);
  const xst = tf.tensor(xs, [xs.length, 1]);
  const yst = tf.tensor(ys, [ys.length, 1]);
  const w1 = tf.variable(tf.scalar(Math.random()));
  const b1 = tf.variable(tf.scalar(Math.random()));
  const f = x => w1.mul(x).add(b1);
  const numIterations = 200;
  const learningRate = 1;
  const optimizer = tf.train.adam(learningRate);
  const loss = (pred, label) => pred.sub(label).square().mean();
  for (let iter = 0; iter < numIterations; iter++) {
    optimizer.minimize(() => {
      const loss_var = loss(f(xst), yst);
      loss_var.print();
      return loss_var;
    })
  }

</script>

</html>

2、通过高级API tf.model

<html>

<head>
  <script src="https://cdn.jsdelivr.net/npm/@tensorflow/tfjs">
  </script>

</head>

<body>
  <button class="btn btn-primary" onclick="fnRun0();">开始0</button>
  <div id="p0Id">out0</div>
  <button class="btn btn-primary" onclick="fnRun1();">开始1</button>
  <div id="p1Id">out1</div>
  <button class="btn btn-primary" onclick="fnRun2();">开始2</button>
  <div id="p2Id">out2</div>
</body>

<script>

  function get_ys(xs) {
    var ys = new Array();
    for (var i = 0; i < xs.length; i++) {
      ys[i] = 2 * xs[i] - 1 + (0.1 * (2 * Math.random() - 1));
    }
    return (ys);
  }
  
  async function learnLinear() {
    var xs = new Array();
    for (var i = 0; i < 100; i++) {
      xs[i] = 0.02 * i;
    }
    var ys = get_ys(xs);
    const xst = tf.tensor(xs, [xs.length, 1]);
    const yst = tf.tensor(ys, [ys.length, 1]);
    
    const model = tf.sequential();
    model.add(tf.layers.dense({
      units: 1,
      inputShape: [1]
    }));
    model.compile({
      loss: 'meanSquaredError',
      optimizer: 'sgd'
    });
    
    await model.fit(xst, yst, {
      epochs: 100
    });
    model.predict(tf.tensor2d([1.1,1.2,1.3,1.4,1.5], [5, 1])).print();
  }
  
  learnLinear();
  
</script>

</html>

结果
当输入x为：[1.1,1.2,1.3,1.4,1.5]，输出为
[[1.2097658],
[1.3917543],
[1.5737425],
[1.755731 ],
[1.9377195]]
可见系统较好的拟合了直线 y =（2x -1）

"Tensor
    [[1.2097658],
     [1.3917543],
     [1.5737425],
     [1.755731 ],
     [1.9377195]]"

[TensorFlowJS只如初见]实战二·使用TensorFlowJS拟合直线

[TensorFlowJS只如初见]实战二·使用TensorFlowJS拟合直线

猜你喜欢