目录
index.html
<!DOCTYPE html>
<html>
<head>
<title>TensorFlow.js Tutorial</title>
<!-- Import TensorFlow.js -->
<script src="https://cdn.jsdelivr.net/npm/@tensorflow/tfjs@2.0.0/dist/tf.min.js"></script>
<!-- Import tfjs-vis -->
<script src="https://cdn.jsdelivr.net/npm/@tensorflow/tfjs-vis@1.0.2/dist/tfjs-vis.umd.min.js"></script>
<!-- Import the main script file -->
<script src="script.js"></script>
</head>
<body>
</body>
</html>script.js
/**
* Get the car data reduced to just the variables we are interested
* and cleaned of missing data. */
// async function:https://www.runoob.com/w3cnote/es6-async.html
async function getData() {
/* const:https://www.runoob.com/js/js-let-const.html
* fetch:发起请求 */
const carsDataResponse = await fetch('https://storage.googleapis.com/tfjs-tutorials/carsData.json');
// 数据格式转换为json文本
const carsData = await carsDataResponse.json();
// map() 方法返回一个新数组
const cleaned = carsData.map(car => ({
mpg: car.Miles_per_Gallon,
horsepower: car.Horsepower,
}))
// filter() 方法创建一个新的数组，新数组中的元素是通过检查指定数组中符合条件的所有元素
.filter(car => (car.mpg != null && car.horsepower != null));
return cleaned;
}
/*------------------------------------------------------------------------------------------------------------------*/
async function run() {
// Load and plot the original input data that we are going to train on.
// 调用自己定义的getData()函数
const data = await getData();
const values = data.map(d => ({
x: d.horsepower,
y: d.mpg,
}));
// 绘制原始图像
tfvis.render.scatterplot(
{name: 'Horsepower v MPG'},
{values}, // values上面定义的x、y数据
{
xLabel: 'Horsepower',
yLabel: 'MPG',
height: 300
}
);
// Create the model
const model = createModel();
tfvis.show.modelSummary({name: 'Model Summary'}, model);
// Convert the data to a form we can use for training.
const tensorData = convertToTensor(data);
const {inputs, labels} = tensorData;
// Train the model
await trainModel(model, inputs, labels);
console.log('Done Training');
// Make some predictions using the model and compare them to the original data
testModel(model, data, tensorData);
}
document.addEventListener('DOMContentLoaded', run);
/*------------------------------------------------------------------------------------------------------------------*/
function createModel() {
// Create a sequential model
const model = tf.sequential();
// Add a single input layer
model.add(tf.layers.dense({inputShape: [1], units: 1, useBias: true}));
// Add an output layer
model.add(tf.layers.dense({units: 1, useBias: true}));
return model;
}
/*------------------------------------------------------------------------------------------------------------------*/
/**
* Convert the input data to tensors that we can use for machine
* learning. We will also do the important best practices of _shuffling_
* the data and _normalizing_ the data
* MPG on the y-axis.
*/
function convertToTensor(data) {
// Wrapping these calculations in a tidy will dispose any
// intermediate tensors.
return tf.tidy(() => {
// Step 1. 重排数据
tf.util.shuffle(data);
// Step 2. 转换为张量。张量：即有标签的数据
const inputs = data.map(d => d.horsepower)
const labels = data.map(d => d.mpg);
const inputTensor = tf.tensor2d(inputs, [inputs.length, 1]);
const labelTensor = tf.tensor2d(labels, [labels.length, 1]);
//Step 3. 对数据进行0-1归一化
const inputMax = inputTensor.max();
const inputMin = inputTensor.min();
const labelMax = labelTensor.max();
const labelMin = labelTensor.min();
const normalizedInputs = inputTensor.sub(inputMin).div(inputMax.sub(inputMin));
const normalizedLabels = labelTensor.sub(labelMin).div(labelMax.sub(labelMin));
return {
inputs: normalizedInputs,
labels: normalizedLabels,
// Return the min/max bounds so we can use them later.
inputMax,
inputMin,
labelMax,
labelMin,
}
});
}
/*------------------------------------------------------------------------------------------------------------------*/
async function trainModel(model, inputs, labels) {
// Prepare the model for training.
model.compile({
// 这是用于控制模型更新的算法，我们选择了 Adam 优化器，因为它在实际使用中非常有效，无需进行任何配置。
optimizer: tf.train.adam(),
// 这是一个函数，用于告知模型在学习所显示的各个批次（数据子集）时的表现如何。我们使用 meanSquaredError 将模型所做的预测与真实值进行比较
loss: tf.losses.meanSquaredError,
metrics: ['mse'],
});
// 是指模型在每次训练迭代时会看到的数据子集的大小。常见的批次大小通常介于 32-512 之间
const batchSize = 32;
// 表示模型查看您提供的整个数据集的次数。我们将对数据集执行 50 次迭代
const epochs = 50;
return await model.fit(inputs, labels, {
batchSize,
epochs,
shuffle: true,
callbacks: tfvis.show.fitCallbacks(
{ name: 'Training Performance' },
['loss', 'mse'],
{ height: 200, callbacks: ['onEpochEnd'] }
)
});
}
/*------------------------------------------------------------------------------------------------------------------*/
function testModel(model, inputData, normalizationData) {
const {inputMax, inputMin, labelMin, labelMax} = normalizationData;
// Generate predictions for a uniform range of numbers between 0 and 1;
// We un-normalize the data by doing the inverse of the min-max scaling
// that we did earlier.
// .tidy() 函数用于执行给定的函数
const [xs, preds] = tf.tidy(() => {
// 生成 100 个新“样本”，以提供给模型
const xs = tf.linspace(0, 1, 100);
const preds = model.predict(xs.reshape([100, 1]));
// 将数据恢复到原始范围
const unNormXs = xs
.mul(inputMax.sub(inputMin))
.add(inputMin);
const unNormPreds = preds
.mul(labelMax.sub(labelMin))
.add(labelMin);
// Un-normalize the data
return [unNormXs.dataSync(), unNormPreds.dataSync()];
});
const predictedPoints = Array.from(xs).map((val, i) => {
return {x: val, y: preds[i]}
});
const originalPoints = inputData.map(d => ({
x: d.horsepower, y: d.mpg,
}));
// 使用 tfjs-vis 来绘制 原始数据 和 模型的预测
tfvis.render.scatterplot(
{name: 'Model Predictions vs Original Data'},
{values: [originalPoints, predictedPoints], series: ['original', 'predicted']},
{
xLabel: 'Horsepower',
yLabel: 'MPG',
height: 300
}
);
}
1024
被折叠的 条评论
为什么被折叠?
到【灌水乐园】发言
