Java深度学习发行版

1.4.6

2025-02-06 23:39

## **Multi-layer Perception NeuralNetwork**
# 多层感知器神经网络
使用Java类构建 Multi-layer Perception NeuralNetwork

```java
public static void main(String[] args) {
//        X = MnistRead.getImagesMatrix(MnistRead.TRAIN_IMAGES_FILE);

X = MnistRead.getImagesBinarization(MnistRead.TRAIN_IMAGES_FILE);
        XT = MnistRead.getImagesBinarization(MnistRead.TEST_IMAGES_FILE);

Y = MnistRead.getLabels(MnistRead.TRAIN_LABELS_FILE);
        YT = MnistRead.getLabels(MnistRead.TEST_LABELS_FILE);

MultilayeredPerceptronNeuralNetworks multilayeredPerceptronNeuralNetworks = new MultilayeredPerceptronNeuralNetworks();
        multilayeredPerceptronNeuralNetworks.run();

//下面是CNN训练
        ConvolutionLayer cl1 = new ConvolutionLayer();
        cl1.setConvolutionNeuralNumber(6);
        cl1.setConvolutionLayerParameter(5, 1, 6, ActivationType.RELU);
        cl1.setPoolingLayerParameter(2, 2, 0, PoolingType.MaxPooling);
        ConvolutionLayer cl2 = new ConvolutionLayer();
        cl2.setConvolutionNeuralNumber(16);
        cl2.setConvolutionLayerParameter(5, 1, 2, ActivationType.RELU);
        cl2.setPoolingLayerParameter(2, 2, 0, PoolingType.MaxPooling);
        ConvolutionLayer cl3 = new ConvolutionLayer();
        cl3.setConvolutionNeuralNumber(18);
        cl3.setConvolutionLayerParameter(3, 1, 1, ActivationType.RELU);
        cl3.setPoolingLayerParameter(2, 2, 0, PoolingType.MaxPooling);

Layer layer1 = new Layer(120, ActivationType.Sigmoid);
        Layer layer2 = new Layer(84, ActivationType.Sigmoid);
        Layer layer3 = new Layer(10, ActivationType.Sigmoid);

ConvolutionLayerConfiguration clc = new ConvolutionLayerConfiguration(X, Y);
        clc.convolutionLayerConfiguration(cl1);
        clc.convolutionLayerConfiguration(cl2);
        clc.convolutionLayerConfiguration(cl3);
        clc.fullyConnectedLayerConfiguration(layer1);
        clc.fullyConnectedLayerConfiguration(layer2);
//        clc.fullyConnectedLayerConfiguration(layer3);
        clc.learningRateConfiguration(0.05);
        clc.lossConfiguration(LossType.MeanSquareErrorLossFunction);
        clc.saveParameter("src/main/resources/DataSet/CNN.mode");
        clc.train();

//        下面是CNN模型读取运行 （可以学到90%）
        ConvolutionLayerConfiguration clc1 = new ConvolutionLayerConfiguration(XT, YT);
        clc1.readParameter("src/main/resources/DataSet/CNN.mode");
        clc1.run();
        
        }
```

### 个人网站

[墨染随想](https://morn.ink) https://morn.ink

创建感知器网络层和感知器网络， 设置数据集和学习率以及误差函数， train就开始训练了。

激活函数有:

Sigmoid
    RELU
    Softmax
    Tanh

损失函数有:

MeanSquareErrorLossFunction
    L2LossFunction
    L1LossFunction
    SmoothL1LossFunction
    HuBerLossFunction  未实现
    KullbackLeiblerDivergenceFunction
    CrossEntropyLossFunction
    SoftmaxLossFunction
    FocalLossFunction  未实现

训练准确率为84.3% ^_^  
CNN 卷积神经网络准确率提升90%;

项目地址：https://gitee.com/Mint-Space/DeepLearning

[多层感知器神经网络](https://gitee.com/Mint-Space/DeepLearning)

![人工智能](https://pic1.zhimg.com/v2-f672a345fd1382a1c2954741ccd5a75d_r.jpg)

喜欢这个项目可以支持一下
![微信](https://gitee.com/Mint-Space/DeepLearning/raw/master/src/main/resources/DataSet/inkdyes.jpg)
![支付宝](https://gitee.com/Mint-Space/DeepLearning/raw/master/src/main/resources/DataSet/zhifu.jpg)
模型正在优化中。。。。

最后提交信息为：优化打包程序大小

2024-05-07 11:15

最后提交信息为：优化入口函数

2024-05-06 19:44

最后提交信息为：优化入口函数

2024-05-06 13:14

最后提交信息为：优化入口函数

2024-05-05 21:04

最后提交信息为：添加 README 文档

2024-05-05 08:36

public static void main(String[] args) {
    //        X = MnistRead.getImagesMatrix(MnistRead.TRAIN_IMAGES_FILE);

X = MnistRead.getImagesBinarization(MnistRead.TRAIN_IMAGES_FILE);
        XT = MnistRead.getImagesBinarization(MnistRead.TEST_IMAGES_FILE);

Y = MnistRead.getLabels(MnistRead.TRAIN_LABELS_FILE);
        YT = MnistRead.getLabels(MnistRead.TEST_LABELS_FILE);

MultiLayerConfiguration multiLayerConfiguration = new MultiLayerConfiguration(X, Y);
        multiLayerConfiguration
                .layerConfiguration(new Layer(784, ActivationType.Sigmoid))
                .layerConfiguration(new Layer(50, ActivationType.Sigmoid))
                .layerConfiguration(new Layer(10, ActivationType.Sigmoid))
                .learningRateConfiguration(0.02)
                .lossConfiguration(LossType.MeanSquareErrorLossFunction)
                .train();

MultiLayerConfiguration mlcRUN = new MultiLayerConfiguration(XT, YT);
        mlcRUN.readParameter().run();
    }

最后提交信息为：添加 README 文档

北极熊/Java深度学习 .gitee-modal { width: 500px !important; }

搜索帮助

北极熊/Java深度学习