JavaScript之机器学习6:Tensorflow.js 欠拟合与过拟合

①欠拟合： 模型太简单，
②好的拟合： 模型刚刚好
③过拟合： 模型太复杂

操作步骤：

• 加载带有噪音的二分类数据集（训练集和验证集）
• 使用不同神经网络演示欠拟合和过拟合
• 过拟合应对法：早停法，权重衰减，丢弃法

// index.js
import * as tf from '@tensorflow/tfjs';
import * as tfvis from '@tensorflow/tfjs-vis';
import { getData } from './data';

window.onload = async () => {
    const data = getData(200, 2);

    tfvis.render.scatterplot(
        { name: '训练数据' },
        {
            values: [
                data.filter(p => p.label === 1),
                data.filter(p => p.label === 0),
            ]
        }
    );

    const model = tf.sequential();
    model.add(tf.layers.dense({
        units: 10,
        inputShape: [2],
        activation: "tanh",
        // kernelRegularizer: tf.regularizers.l2({ l2: 1 })  // 权重衰减
    }));
    model.add(tf.layers.dropout({ rate: 0.9 }));  // 丢弃法
    model.add(tf.layers.dense({
        units: 1,
        activation: 'sigmoid'
    }));
    model.compile({
        loss: tf.losses.logLoss,
        optimizer: tf.train.adam(0.1)
    });

    const inputs = tf.tensor(data.map(p => [p.x, p.y]));
    const labels = tf.tensor(data.map(p => p.label));

    await model.fit(inputs, labels, {
        validationSplit: 0.2,
        epochs: 200,
        callbacks: tfvis.show.fitCallbacks(
            { name: '训练效果' },
            ['loss', 'val_loss'],
            { callbacks: ['onEpochEnd'] }
        )
    });
};

// data.js
// variance:值越大，噪音越大
export function getData(numSamples, variance) {
    let points = [];
  
    function genGauss(cx, cy, label) {
      for (let i = 0; i < numSamples / 2; i++) {
        let x = normalRandom(cx, variance);
        let y = normalRandom(cy, variance);
        points.push({ x, y, label });
      }
    }
  
    genGauss(2, 2, 1);
    genGauss(-2, -2, 0);
    return points;
  }
  
  /**
   * Samples from a normal distribution. Uses the seedrandom library as the
   * random generator.
   *
   * @param mean The mean. Default is 0.
   * @param variance The variance. Default is 1.
   */
  function normalRandom(mean = 0, variance = 1) {
    let v1, v2, s;
    do {
      v1 = 2 * Math.random() - 1;
      v2 = 2 * Math.random() - 1;
      s = v1 * v1 + v2 * v2;
    } while (s > 1);
  
    let result = Math.sqrt(-2 * Math.log(s) / s) * v1;
    return mean + Math.sqrt(variance) * result;
  }