温馨提示×

温馨提示×

您好，登录后才能下订单哦！

密码登录×
登录注册×
获取短信验证码
其他方式登录
点击 登录注册 即表示同意《亿速云用户服务条款》
登 录 注册有礼
云服务器 香港服务器 高防服务器
最新更新 网站标签 地图导航
产品

在浏览器中怎么实现训练模型

发布时间：2022-07-11 10:06:55 来源：亿速云 阅读：150 作者：zzz 栏目：开发技术

这篇“在浏览器中怎么实现训练模型”文章的知识点大部分人都不太理解，所以小编给大家总结了以下内容，内容详细，步骤清晰，具有一定的借鉴价值，希望大家阅读完这篇文章能有所收获，下面我们一起来看看这篇“在浏览器中怎么实现训练模型”文章吧。

识别鸢尾花

本文将在浏览器中定义、训练和运行模型。 为了实现这一功能，我将构建一个识别鸢尾花的案例。

接下来，我们将创建一个神经网络。同时，根据开源数据集我们将鸢尾花分为三类：Setosa、Virginica 和 Versicolor。

每个机器学习项目的核心都是数据集。 我们需要采取的第一步是将这个数据集拆分为训练集和测试集。

这样做的原因是我们将使用我们的训练集来训练我们的算法和我们的测试集来检查我们的预测的准确性，以验证我们的模型是否可以使用或需要调整。

为了方便起见，我已经将训练集和测试集拆分为两个 JSON 文件:

测试集: testing.json

[{"sepal_length":6,"sepal_width":2.9,"petal_length":4.5,"petal_width":1.5,"species":"versicolor"},
{"sepal_length":5.2,"sepal_width":3.4,"petal_length":1.4,"petal_width":0.2,"species":"setosa"},
{"sepal_length":6.5,"sepal_width":3,"petal_length":5.8,"petal_width":2.2,"species":"virginica"},
{"sepal_length":5.9,"sepal_width":3.2,"petal_length":4.8,"petal_width":1.8,"species":"versicolor"},
{"sepal_length":5.1,"sepal_width":3.8,"petal_length":1.9,"petal_width":0.4,"species":"setosa"},
{"sepal_length":5.4,"sepal_width":3,"petal_length":4.5,"petal_width":1.5,"species":"versicolor"},
{"sepal_length":7,"sepal_width":3.2,"petal_length":4.7,"petal_width":1.4,"species":"versicolor"},
{"sepal_length":5.7,"sepal_width":2.8,"petal_length":4.5,"petal_width":1.3,"species":"versicolor"},
{"sepal_length":5.1,"sepal_width":2.5,"petal_length":3,"petal_width":1.1,"species":"versicolor"},
{"sepal_length":4.9,"sepal_width":2.4,"petal_length":3.3,"petal_width":1,"species":"versicolor"},
{"sepal_length":5.1,"sepal_width":3.7,"petal_length":1.5,"petal_width":0.4,"species":"setosa"},
{"sepal_length":5.7,"sepal_width":2.8,"petal_length":4.1,"petal_width":1.3,"species":"versicolor"},
{"sepal_length":5.6,"sepal_width":3,"petal_length":4.5,"petal_width":1.5,"species":"versicolor"},
{"sepal_length":6.1,"sepal_width":3,"petal_length":4.6,"petal_width":1.4,"species":"versicolor"}]

训练集: training.json

[{"sepal_length":5.1,"sepal_width":3.5,"petal_length":1.4,"petal_width":0.2,"species":"setosa"},
{"sepal_length":4.9,"sepal_width":3,"petal_length":1.4,"petal_width":0.2,"species":"setosa"},
{"sepal_length":4.7,"sepal_width":3.2,"petal_length":1.3,"petal_width":0.2,"species":"setosa"},
{"sepal_length":4.6,"sepal_width":3.1,"petal_length":1.5,"petal_width":0.2,"species":"setosa"},
{"sepal_length":5,"sepal_width":3.6,"petal_length":1.4,"petal_width":0.2,"species":"setosa"},
{"sepal_length":4.6,"sepal_width":3.4,"petal_length":1.4,"petal_width":0.3,"species":"setosa"},
{"sepal_length":5,"sepal_width":3.4,"petal_length":1.5,"petal_width":0.2,"species":"setosa"},
{"sepal_length":4.4,"sepal_width":2.9,"petal_length":1.4,"petal_width":0.2,"species":"setosa"},
{"sepal_length":4.9,"sepal_width":3.1,"petal_length":1.5,"petal_width":0.1,"species":"setosa"},
{"sepal_length":5.4,"sepal_width":3.7,"petal_length":1.5,"petal_width":0.2,"species":"setosa"},
{"sepal_length":4.8,"sepal_width":3.4,"petal_length":1.6,"petal_width":0.2,"species":"setosa"},
{"sepal_length":4.8,"sepal_width":3,"petal_length":1.4,"petal_width":0.1,"species":"setosa"},
{"sepal_length":4.3,"sepal_width":3,"petal_length":1.1,"petal_width":0.1,"species":"setosa"},
{"sepal_length":5.8,"sepal_width":4,"petal_length":1.2,"petal_width":0.2,"species":"setosa"},
{"sepal_length":5.7,"sepal_width":4.4,"petal_length":1.5,"petal_width":0.4,"species":"setosa"},
{"sepal_length":5.4,"sepal_width":3.9,"petal_length":1.3,"petal_width":0.4,"species":"setosa"},
{"sepal_length":5.1,"sepal_width":3.5,"petal_length":1.4,"petal_width":0.3,"species":"setosa"},
{"sepal_length":5.7,"sepal_width":3.8,"petal_length":1.7,"petal_width":0.3,"species":"setosa"},
{"sepal_length":5.1,"sepal_width":3.8,"petal_length":1.5,"petal_width":0.3,"species":"setosa"},
{"sepal_length":5.4,"sepal_width":3.4,"petal_length":1.7,"petal_width":0.2,"species":"setosa"},
{"sepal_length":4.6,"sepal_width":3.6,"petal_length":1,"petal_width":0.2,"species":"setosa"},
{"sepal_length":5.1,"sepal_width":3.3,"petal_length":1.7,"petal_width":0.5,"species":"setosa"},
{"sepal_length":4.8,"sepal_width":3.4,"petal_length":1.9,"petal_width":0.2,"species":"setosa"},
{"sepal_length":5,"sepal_width":3,"petal_length":1.6,"petal_width":0.2,"species":"setosa"},
{"sepal_length":5,"sepal_width":3.4,"petal_length":1.6,"petal_width":0.4,"species":"setosa"},
{"sepal_length":5.2,"sepal_width":3.5,"petal_length":1.5,"petal_width":0.2,"species":"setosa"},
{"sepal_length":4.7,"sepal_width":3.2,"petal_length":1.6,"petal_width":0.2,"species":"setosa"},
{"sepal_length":4.8,"sepal_width":3.1,"petal_length":1.6,"petal_width":0.2,"species":"setosa"},
{"sepal_length":5.4,"sepal_width":3.4,"petal_length":1.5,"petal_width":0.4,"species":"setosa"},
{"sepal_length":5.2,"sepal_width":4.1,"petal_length":1.5,"petal_width":0.1,"species":"setosa"},
{"sepal_length":5.5,"sepal_width":4.2,"petal_length":1.4,"petal_width":0.2,"species":"setosa"},
{"sepal_length":4.9,"sepal_width":3.1,"petal_length":1.5,"petal_width":0.1,"species":"setosa"},
{"sepal_length":5,"sepal_width":3.2,"petal_length":1.2,"petal_width":0.2,"species":"setosa"},
{"sepal_length":5.5,"sepal_width":3.5,"petal_length":1.3,"petal_width":0.2,"species":"setosa"},
{"sepal_length":4.9,"sepal_width":3.1,"petal_length":1.5,"petal_width":0.1,"species":"setosa"},
{"sepal_length":4.4,"sepal_width":3,"petal_length":1.3,"petal_width":0.2,"species":"setosa"},
{"sepal_length":5.1,"sepal_width":3.4,"petal_length":1.5,"petal_width":0.2,"species":"setosa"},
{"sepal_length":5,"sepal_width":3.5,"petal_length":1.3,"petal_width":0.3,"species":"setosa"},
{"sepal_length":4.5,"sepal_width":2.3,"petal_length":1.3,"petal_width":0.3,"species":"setosa"},
{"sepal_length":4.4,"sepal_width":3.2,"petal_length":1.3,"petal_width":0.2,"species":"setosa"},
{"sepal_length":5,"sepal_width":3.5,"petal_length":1.6,"petal_width":0.6,"species":"setosa"},
{"sepal_length":4.8,"sepal_width":3,"petal_length":1.4,"petal_width":0.3,"species":"setosa"},
{"sepal_length":5.1,"sepal_width":3.8,"petal_length":1.6,"petal_width":0.2,"species":"setosa"},
{"sepal_length":5.3,"sepal_width":3.7,"petal_length":1.5,"petal_width":0.2,"species":"setosa"},
{"sepal_length":5,"sepal_width":3.3,"petal_length":1.4,"petal_width":0.2,"species":"setosa"},
{"sepal_length":6.4,"sepal_width":3.2,"petal_length":4.5,"petal_width":1.5,"species":"versicolor"},
{"sepal_length":5.5,"sepal_width":2.3,"petal_length":4,"petal_width":1.3,"species":"versicolor"},
{"sepal_length":6.5,"sepal_width":2.8,"petal_length":4.6,"petal_width":1.5,"species":"versicolor"},
{"sepal_length":6.3,"sepal_width":3.3,"petal_length":4.7,"petal_width":1.6,"species":"versicolor"},
{"sepal_length":6.6,"sepal_width":2.9,"petal_length":4.6,"petal_width":1.3,"species":"versicolor"},
{"sepal_length":5.2,"sepal_width":2.7,"petal_length":3.9,"petal_width":1.4,"species":"versicolor"},
{"sepal_length":5,"sepal_width":2,"petal_length":3.5,"petal_width":1,"species":"versicolor"},
{"sepal_length":5.9,"sepal_width":3,"petal_length":4.2,"petal_width":1.5,"species":"versicolor"},
{"sepal_length":6,"sepal_width":2.2,"petal_length":4,"petal_width":1,"species":"versicolor"},
{"sepal_length":6.1,"sepal_width":2.9,"petal_length":4.7,"petal_width":1.4,"species":"versicolor"},
{"sepal_length":5.6,"sepal_width":2.9,"petal_length":3.6,"petal_width":1.3,"species":"versicolor"},
{"sepal_length":6.7,"sepal_width":3.1,"petal_length":4.4,"petal_width":1.4,"species":"versicolor"},
{"sepal_length":5.8,"sepal_width":2.7,"petal_length":4.1,"petal_width":1,"species":"versicolor"},
{"sepal_length":6.2,"sepal_width":2.2,"petal_length":4.5,"petal_width":1.5,"species":"versicolor"},
{"sepal_length":5.6,"sepal_width":2.5,"petal_length":3.9,"petal_width":1.1,"species":"versicolor"},
{"sepal_length":6.1,"sepal_width":2.8,"petal_length":4,"petal_width":1.3,"species":"versicolor"},
{"sepal_length":6.3,"sepal_width":2.5,"petal_length":4.9,"petal_width":1.5,"species":"versicolor"},
{"sepal_length":6.1,"sepal_width":2.8,"petal_length":4.7,"petal_width":1.2,"species":"versicolor"},
{"sepal_length":6.4,"sepal_width":2.9,"petal_length":4.3,"petal_width":1.3,"species":"versicolor"},
{"sepal_length":6.6,"sepal_width":3,"petal_length":4.4,"petal_width":1.4,"species":"versicolor"},
{"sepal_length":6.8,"sepal_width":2.8,"petal_length":4.8,"petal_width":1.4,"species":"versicolor"},
{"sepal_length":6.7,"sepal_width":3,"petal_length":5,"petal_width":1.7,"species":"versicolor"},
{"sepal_length":5.7,"sepal_width":2.6,"petal_length":3.5,"petal_width":1,"species":"versicolor"},
{"sepal_length":5.5,"sepal_width":2.4,"petal_length":3.8,"petal_width":1.1,"species":"versicolor"},
{"sepal_length":5.5,"sepal_width":2.4,"petal_length":3.7,"petal_width":1,"species":"versicolor"},
{"sepal_length":5.8,"sepal_width":2.7,"petal_length":3.9,"petal_width":1.2,"species":"versicolor"},
{"sepal_length":6,"sepal_width":2.7,"petal_length":5.1,"petal_width":1.6,"species":"versicolor"},
{"sepal_length":6,"sepal_width":3.4,"petal_length":4.5,"petal_width":1.6,"species":"versicolor"},
{"sepal_length":6.7,"sepal_width":3.1,"petal_length":4.7,"petal_width":1.5,"species":"versicolor"},
{"sepal_length":6.3,"sepal_width":2.3,"petal_length":4.4,"petal_width":1.3,"species":"versicolor"},
{"sepal_length":5.6,"sepal_width":3,"petal_length":4.1,"petal_width":1.3,"species":"versicolor"},
{"sepal_length":5.5,"sepal_width":2.5,"petal_length":4,"petal_width":1.3,"species":"versicolor"},
{"sepal_length":5.5,"sepal_width":2.6,"petal_length":4.4,"petal_width":1.2,"species":"versicolor"},
{"sepal_length":5.8,"sepal_width":2.6,"petal_length":4,"petal_width":1.2,"species":"versicolor"},
{"sepal_length":5,"sepal_width":2.3,"petal_length":3.3,"petal_width":1,"species":"versicolor"},
{"sepal_length":5.6,"sepal_width":2.7,"petal_length":4.2,"petal_width":1.3,"species":"versicolor"},
{"sepal_length":5.7,"sepal_width":3,"petal_length":4.2,"petal_width":1.2,"species":"versicolor"},
{"sepal_length":6.2,"sepal_width":2.9,"petal_length":4.3,"petal_width":1.3,"species":"versicolor"},
{"sepal_length":6.3,"sepal_width":3.3,"petal_length":6,"petal_width":2.5,"species":"virginica"},
{"sepal_length":5.8,"sepal_width":2.7,"petal_length":5.1,"petal_width":1.9,"species":"virginica"},
{"sepal_length":7.1,"sepal_width":3,"petal_length":5.9,"petal_width":2.1,"species":"virginica"},
{"sepal_length":6.3,"sepal_width":2.9,"petal_length":5.6,"petal_width":1.8,"species":"virginica"},
{"sepal_length":7.6,"sepal_width":3,"petal_length":6.6,"petal_width":2.1,"species":"virginica"},
{"sepal_length":4.9,"sepal_width":2.5,"petal_length":4.5,"petal_width":1.7,"species":"virginica"},
{"sepal_length":7.3,"sepal_width":2.9,"petal_length":6.3,"petal_width":1.8,"species":"virginica"},
{"sepal_length":6.7,"sepal_width":2.5,"petal_length":5.8,"petal_width":1.8,"species":"virginica"},
{"sepal_length":7.2,"sepal_width":3.6,"petal_length":6.1,"petal_width":2.5,"species":"virginica"},
{"sepal_length":6.5,"sepal_width":3.2,"petal_length":5.1,"petal_width":2,"species":"virginica"},
{"sepal_length":6.4,"sepal_width":2.7,"petal_length":5.3,"petal_width":1.9,"species":"virginica"},
{"sepal_length":6.8,"sepal_width":3,"petal_length":5.5,"petal_width":2.1,"species":"virginica"},
{"sepal_length":5.7,"sepal_width":2.5,"petal_length":5,"petal_width":2,"species":"virginica"},
{"sepal_length":5.8,"sepal_width":2.8,"petal_length":5.1,"petal_width":2.4,"species":"virginica"},
{"sepal_length":6.4,"sepal_width":3.2,"petal_length":5.3,"petal_width":2.3,"species":"virginica"},
{"sepal_length":6.5,"sepal_width":3,"petal_length":5.5,"petal_width":1.8,"species":"virginica"},
{"sepal_length":7.7,"sepal_width":3.8,"petal_length":6.7,"petal_width":2.2,"species":"virginica"},
{"sepal_length":7.7,"sepal_width":2.6,"petal_length":6.9,"petal_width":2.3,"species":"virginica"},
{"sepal_length":6,"sepal_width":2.2,"petal_length":5,"petal_width":1.5,"species":"virginica"},
{"sepal_length":6.9,"sepal_width":3.2,"petal_length":5.7,"petal_width":2.3,"species":"virginica"},
{"sepal_length":5.6,"sepal_width":2.8,"petal_length":4.9,"petal_width":2,"species":"virginica"},
{"sepal_length":7.7,"sepal_width":2.8,"petal_length":6.7,"petal_width":2,"species":"virginica"},
{"sepal_length":6.3,"sepal_width":2.7,"petal_length":4.9,"petal_width":1.8,"species":"virginica"},
{"sepal_length":6.7,"sepal_width":3.3,"petal_length":5.7,"petal_width":2.1,"species":"virginica"},
{"sepal_length":7.2,"sepal_width":3.2,"petal_length":6,"petal_width":1.8,"species":"virginica"},
{"sepal_length":6.2,"sepal_width":2.8,"petal_length":4.8,"petal_width":1.8,"species":"virginica"},
{"sepal_length":6.1,"sepal_width":3,"petal_length":4.9,"petal_width":1.8,"species":"virginica"},
{"sepal_length":6.4,"sepal_width":2.8,"petal_length":5.6,"petal_width":2.1,"species":"virginica"},
{"sepal_length":7.2,"sepal_width":3,"petal_length":5.8,"petal_width":1.6,"species":"virginica"},
{"sepal_length":7.9,"sepal_width":3.8,"petal_length":6.4,"petal_width":2,"species":"virginica"},
{"sepal_length":6.4,"sepal_width":2.8,"petal_length":5.6,"petal_width":2.2,"species":"virginica"},
{"sepal_length":6.3,"sepal_width":2.8,"petal_length":5.1,"petal_width":1.5,"species":"virginica"},
{"sepal_length":6.1,"sepal_width":2.6,"petal_length":5.6,"petal_width":1.4,"species":"virginica"},
{"sepal_length":7.7,"sepal_width":3,"petal_length":6.1,"petal_width":2.3,"species":"virginica"},
{"sepal_length":6.3,"sepal_width":3.4,"petal_length":5.6,"petal_width":2.4,"species":"virginica"},
{"sepal_length":6.4,"sepal_width":3.1,"petal_length":5.5,"petal_width":1.8,"species":"virginica"},
{"sepal_length":6,"sepal_width":3,"petal_length":4.8,"petal_width":1.8,"species":"virginica"},
{"sepal_length":6.9,"sepal_width":3.1,"petal_length":5.4,"petal_width":2.1,"species":"virginica"},
{"sepal_length":6.7,"sepal_width":3.1,"petal_length":5.6,"petal_width":2.4,"species":"virginica"},
{"sepal_length":6.9,"sepal_width":3.1,"petal_length":5.1,"petal_width":2.3,"species":"virginica"},
{"sepal_length":5.8,"sepal_width":2.7,"petal_length":5.1,"petal_width":1.9,"species":"virginica"},
{"sepal_length":6.8,"sepal_width":3.2,"petal_length":5.9,"petal_width":2.3,"species":"virginica"},
{"sepal_length":6.7,"sepal_width":3.3,"petal_length":5.7,"petal_width":2.5,"species":"virginica"},
{"sepal_length":6.7,"sepal_width":3,"petal_length":5.2,"petal_width":2.3,"species":"virginica"},
{"sepal_length":6.3,"sepal_width":2.5,"petal_length":5,"petal_width":1.9,"species":"virginica"},
{"sepal_length":6.5,"sepal_width":3,"petal_length":5.2,"petal_width":2,"species":"virginica"},
{"sepal_length":6.2,"sepal_width":3.4,"petal_length":5.4,"petal_width":2.3,"species":"virginica"}]

其中，训练集包含 130 个项目，测试集包含 14 个。如果你看看这些数据是什么样子，你会看到

如下内容：

{
  "sepal_length": 5.1,
  "sepal_width": 3.5,
  "petal_length": 1.4,
  "petal_width": 0.2,
  "species": "setosa"
}

我们可以看到萼片和花瓣的长度和宽度的四个不同特征，以及物种的标签。

为了能够将它与 Tensorflow.js 一起使用，我们需要将这些数据塑造成框架能够理解的格式，在这种情况下，对于训练数据，它将是 [130, 4] 的 130 个样本，每个样本有四个特征。

import * as trainingSet from "training.json";
import * as testSet from "testing.json";
const trainingData = tf.tensor2d(
  trainingSet.map(item => [
    item.sepal_length,
    item.sepal_width,
    item.petal_length,
    item.petal_width
  ]),
  [130, 4]
);
const testData = tf.tensor2d(
  testSet.map(item => [
    item.sepal_length,
    item.sepal_width,
    item.petal_length,
    item.petal_width
  ]),
  [14, 4]
);

接下来，我们还需要对输出数据进行整形：

const output = tf.tensor2d(trainingSet.map(item => [
    item.species === 'setosa' ? 1 : 0,
    item.species === 'virginica' ? 1 : 0,
    item.species === 'versicolor' ? 1 : 0
]), [130,3])

然后，一旦我们的数据准备就绪，我们就可以继续创建模型：

const model = tf.sequential();
model.add(tf.layers.dense(
    {
        inputShape: 4,
        activation: 'sigmoid',
        units: 10
    }
));
model.add(tf.layers.dense(
    {
        inputShape: 10,
        units: 3,
        activation: 'softmax'
    }
));

在上面的代码示例中，我们首先实例化一个顺序模型，添加一个输入和输出层。

你可以看到内部使用的参数（inputShape, activation, and units）超出了本文的范围，因为它们可能会根据你创建的模型、使用的数据类型等而有所不同。

一旦我们的模型准备就绪，我们就可以使用我们的数据对其进行训练：

async function train_data(){
    for(let i=0;i<15;i++){
      const res = await model.fit(trainingData, outputData,{epochs: 40});
    }
}
async function main() {
  await train_data();
  model.predict(testSet).print();
}

如果这运作良好，你可以开始用自定义用户输入替换测试数据。

一旦我们调用我们的 main 函数，预测的输出将看起来像以下三个选项之一：

[1,0,0] // Setosa[0,1,0] // Virginica[0,0,1] // Versicolor

预测返回一个由三个数字组成的数组，表示数据属于三个类别之一的概率。 最接近 1 的数字是最高预测值。

例如，如果分类的输出为 [0.0002, 0.9494, 0.0503]，则数组的第二个元素最高，因此模型预测新的输入很可能是 Virginica。

这就是 Tensorflow.js 中的简单神经网络！

我们只讨论了 Irises 的一个小数据集，但如果您想继续使用更大的数据集或处理图像，步骤将是相同的：

  • 收集数据；

  • 在训练集和测试集之间拆分；

  • 重新格式化数据以便 Tensorflow.js 可以理解它；

  • 选择你的算法；

  • 拟合数据；

  • 预测。

如果你想保存创建的模型以便能够在另一个应用程序中加载它并预测新数据，你可以使用以下行来执行此操作：

await model.save('file:///path/to/my-model'); // in Node.js

完整代码

index.html

<!DOCTYPE html>
<html lang="en">
<head>
	<meta charset="UTF-8">
	<meta name="viewport" content="width=device-width, initial-scale=1.0">
	<meta http-equiv="X-UA-Compatible" content="ie=edge">
	<title>Tensorflow.js</title>
	<link rel="stylesheet" href="src/styles.css" rel="external nofollow" >
</head>
<body>
	<h2>使用 Tensorflow.js 在 JavaScript 中定义、训练和运行机器学习模型</h2>
	<section class="data-inputs">
		<h4>鸢尾花分类</h4>
		<p>正在训练中...</p>
		<p class="training-steps"></p>
		<div class="input-block">
			<label for="sepal-length">Sepal lenth:</label>
			<input name="sepal-length" type="number" min="0" max="100" placeholder="1.5">
		</div>
		<div class="input-block">
			<label for="sepal-width">Sepal width:</label>
			<input name="sepal-width" type="number" min="0" max="100" placeholder="0.4">
		</div>
		<div class="input-block">
			<label for="petal-length">Petal length:</label>
			<input name="petal-length" type="number" min="0" max="100" placeholder="1.0">
		</div>
		<div class="input-block">
			<label for="petal-width">Petal width:</label>
			<input name="petal-width" type="number" min="0" max="100" placeholder="0.7">
		</div>
		<button class="predict" disabled>预测</button>
	</section>
	<section class="prediction-block">
		<p>鸢尾花 预测:</p>
		<p class="prediction"></p>
	</section>
	<script src="src/index.js"></script>
</body>
</html>

index.js

import * as tf from "@tensorflow/tfjs";
import trainingSet from "./training.json";
import testSet from "./testing.json";
let trainingData, testingData, outputData, model;
let training = true;
let predictButton = document.getElementsByClassName("predict")[0];
const init = async () => {
  splitData();
  createModel();
  await trainData();
  if (!training) {
    predictButton.disabled = false;
    predictButton.onclick = () => {
      const inputData = getInputData();
      predict(inputData);
    };
  }
};
const splitData = () => {
  trainingData = tf.tensor2d(
    trainingSet.map(item => [
      item.sepal_length,
      item.sepal_width,
      item.petal_length,
      item.petal_width
    ]),
    [130, 4]
  );
  testingData = tf.tensor2d(
    testSet.map(item => [
      item.sepal_length,
      item.sepal_width,
      item.petal_length,
      item.petal_width
    ]),
    [14, 4]
  );
  outputData = tf.tensor2d(
    trainingSet.map(item => [
      item.species === "setosa" ? 1 : 0,
      item.species === "virginica" ? 1 : 0,
      item.species === "versicolor" ? 1 : 0
    ]),
    [130, 3]
  );
};
const createModel = () => {
  model = tf.sequential();
  model.add(
    tf.layers.dense({ inputShape: 4, activation: "sigmoid", units: 10 })
  );
  model.add(
    tf.layers.dense({
      inputShape: 10,
      units: 3,
      activation: "softmax"
    })
  );
  model.compile({
    loss: "categoricalCrossentropy",
    optimizer: tf.train.adam()
  });
};
const trainData = async () => {
  let numSteps = 15;
  let trainingStepsDiv = document.getElementsByClassName("training-steps")[0];
  for (let i = 0; i < numSteps; i++) {
    let res = await model.fit(trainingData, outputData, { epochs: 40 });
    trainingStepsDiv.innerHTML = `Training step: ${i}/${numSteps - 1}, loss: ${
      res.history.loss[0]
    }`;
    if (i === numSteps - 1) {
      training = false;
    }
  }
};
const predict = async inputData => {
  for (let [key, value] of Object.entries(inputData)) {
    inputData[key] = parseFloat(value);
  }
  inputData = [inputData];
  let newDataTensor = tf.tensor2d(
    inputData.map(item => [
      item.sepal_length,
      item.sepal_width,
      item.petal_length,
      item.petal_width
    ]),
    [1, 4]
  );
  let prediction = model.predict(newDataTensor);
  displayPrediction(prediction);
};
const getInputData = () => {
  let sepalLength = document.getElementsByName("sepal-length")[0].value;
  let sepalWidth = document.getElementsByName("sepal-width")[0].value;
  let petalLength = document.getElementsByName("petal-length")[0].value;
  let petalWidth = document.getElementsByName("petal-width")[0].value;
  return {
    sepal_length: sepalLength,
    sepal_width: sepalWidth,
    petal_length: petalLength,
    petal_width: petalWidth
  };
};
const displayPrediction = prediction => {
  let predictionDiv = document.getElementsByClassName("prediction")[0];
  let predictionSection = document.getElementsByClassName(
    "prediction-block"
  )[0];
  let maxProbability = Math.max(...prediction.dataSync());
  let predictionIndex = prediction.dataSync().indexOf(maxProbability);
  let irisPrediction;
  switch (predictionIndex) {
    case 0:
      irisPrediction = "Setosa";
      break;
    case 1:
      irisPrediction = "Virginica";
      break;
    case 2:
      irisPrediction = "Versicolor";
      break;
    default:
      irisPrediction = "";
      break;
  }
  predictionDiv.innerHTML = irisPrediction;
  predictionSection.style.display = "block";
};
init();

styles.css

body {
  font-family: "Avenir";
}
h2 {
  text-align: center;
  width: 80%;
  margin: 0 auto;
}
.data-inputs {
  display: block;
  width: 80%;
  margin: 0 auto;
}
.input-block {
  display: inline-block;
  width: fit-content;
  margin: 1em 0.5em 2em 0.5em;
}
.input-block:first-of-type {
  margin-left: 0;
}
.input-block input {
  width: 7em;
  height: 2em;
}
.input-block input::placeholder {
  color: rgba(0, 0, 0, 0.3);
}
button {
  display: block;
  padding: 0.5em 1em;
  border-radius: 5px;
  font-size: 14px;
}
.prediction-block {
  display: none;
  width: 80%;
  margin: 0 auto;
}

package.json

{
  "name": "Irises Classficaton",
  "version": "1.0.0",
  "description": "",
  "main": "index.html",
  "scripts": {
    "start": "parcel index.html --open",
    "build": "parcel build index.html"
  },
  "dependencies": {
    "@tensorflow/tfjs": "1.1.2"
  },
  "devDependencies": {
    "@babel/core": "7.2.0",
    "parcel-bundler": "^1.6.1"
  },
  "keywords": []
}

效果如下：

在浏览器中怎么实现训练模型

以上就是关于“在浏览器中怎么实现训练模型”这篇文章的内容，相信大家都有了一定的了解，希望小编分享的内容对大家有帮助，若想了解更多相关的知识内容，请关注亿速云行业资讯频道。

向AI问一下细节
推荐阅读：
  1. keras如何实现调用训练模型和去掉全连接层
  2. keras中深度模型训练的示例分析

免责声明：本站发布的内容（图片、视频和文字）以原创、转载和分享为主，文章观点不代表本网站立场，如果涉及侵权请联系站长邮箱：is@yisu.com进行举报，并提供相关证据，一经查实，将立刻删除涉嫌侵权内容。

浏览器

猜你喜欢

最新资讯
相关推荐

相关标签

safari浏览器 uc浏览器 微信跳转外部浏览器 微信跳转浏览器 默认浏览器 手机浏览器 浏览器兼容 火狐浏览器 浏览器支持 浏览器证书 php浏览器 无头浏览器 360浏览器 文件浏览器 浏览器缓存 图片浏览器 谷歌浏览器 ie6浏览器 浏览器渲染 浏览器内核
AI
助
手
产品服务
地区划分
专题活动
帮助支持
关于我们
售后咨询
7*24小时在线电话：400-100-2938
7*24小时在线 QQ：800811969
关注亿速云

亿速云公众号

手机网站二维码

Copyright © Yisu Cloud Ltd. All Rights Reserved. 2018 版权所有

广州亿速云计算有限公司粤ICP备17096448号-1 粤公网安备 44010402001142号增值电信业务经营许可证编号：B1-20181529