- JavaScript 实现神经网络应用教程

class ColorAccessibilityModel {
inputTensor;
targetTensor;
setupSession(trainingSet) {
const graph = new Graph();
this.inputTensor = graph.placeholder('input RGB value', [3]);
this.targetTensor = graph.placeholder('output classifier', [2]);
let connectedLayer = this.createConnectedLayer(graph, this.inputTensor, 0, 64);
connectedLayer = this.createConnectedLayer(graph, connectedLayer, 1, 32);
connectedLayer = this.createConnectedLayer(graph, connectedLayer, 2, 16);
}
createConnectedLayer(
graph,
inputLayer,
layerIndex,
units,
activationFunction
) {
return graph.layers.dense(
`fully_connected_${layerIndex}`,
inputLayer,
units,
activationFunction ? activationFunction : (x) => graph.relu(x)
);
}
...
}
export default ColorAccessibilityModel;

第六步，创建输出二分类的层。它有两个输出单元，每一个表示一个离散的值（黑色、白色）。

class ColorAccessibilityModel {
inputTensor;
targetTensor;
predictionTensor;
setupSession(trainingSet) {
const graph = new Graph();
this.inputTensor = graph.placeholder('input RGB value', [3]);
this.targetTensor = graph.placeholder('output classifier', [2]);
let connectedLayer = this.createConnectedLayer(graph, this.inputTensor, 0, 64);
connectedLayer = this.createConnectedLayer(graph, connectedLayer, 1, 32);
connectedLayer = this.createConnectedLayer(graph, connectedLayer, 2, 16);
this.predictionTensor = this.createConnectedLayer(graph, connectedLayer, 3, 2);
}
...
}
export default ColorAccessibilityModel;

第七步，声明一个代价张量（cost tensor），以定义损失函数。在这个案例中，代价张量是均方误差。它使用训练集的目标张量（标签）和训练算法得到的预测张量来计算代价。

class ColorAccessibilityModel {
inputTensor;
targetTensor;
predictionTensor;
costTensor;
setupSession(trainingSet) {
const graph = new Graph();
this.inputTensor = graph.placeholder('input RGB value', [3]);
this.targetTensor = graph.placeholder('output classifier', [2]);
let connectedLayer = this.createConnectedLayer(graph, this.inputTensor, 0, 64);
connectedLayer = this.createConnectedLayer(graph, connectedLayer, 1, 32);
connectedLayer = this.createConnectedLayer(graph, connectedLayer, 2, 16);
this.predictionTensor = this.createConnectedLayer(graph, connectedLayer, 3, 2);
this.costTensor = graph.meanSquaredCost(this.targetTensor, this.predictionTensor);
}
...
}
export default ColorAccessibilityModel;

最后但并非不重要的一步，设置架构图的相关会话。之后，你就可以开始准备为训练阶段导入训练集了。

import {
Graph,
Session,
NDArrayMathGPU,
} from 'deeplearn';
class ColorAccessibilityModel {
session;
inputTensor;
targetTensor;
predictionTensor;
costTensor;
setupSession(trainingSet) {
const graph = new Graph();
this.inputTensor = graph.placeholder('input RGB value', [3]);
this.targetTensor = graph.placeholder('output classifier', [2]);
let connectedLayer = this.createConnectedLayer(graph, this.inputTensor, 0, 64);
connectedLayer = this.createConnectedLayer(graph, connectedLayer, 1, 32);
connectedLayer = this.createConnectedLayer(graph, connectedLayer, 2, 16);
this.predictionTensor = this.createConnectedLayer(graph, connectedLayer, 3, 2);
this.costTensor = graph.meanSquaredCost(this.targetTensor, this.predictionTensor);
this.session = new Session(graph, math);
this.prepareTrainingSet(trainingSet);
}
prepareTrainingSet(trainingSet) {
...
}
...
}
export default ColorAccessibilityModel;

不过目前在准备神经网络的训练集之前，设置还没完成。

首先，你可以在 GPU 数学计算环境中使用回调函数（callback function）来支持计算，但这并不是强制性的，可自主选择。

import {
Graph,
Session,
NDArrayMathGPU,
} from 'deeplearn';
const math = new NDArrayMathGPU();
class ColorAccessibilityModel {
session;
inputTensor;
targetTensor;
predictionTensor;
costTensor;
...
prepareTrainingSet(trainingSet) {
math.scope(() => {
...
});
}
...
}
export default ColorAccessibilityModel;