Java实现深度神经网络：ReLU层

使用Java实现

/**
 * ReLU层
 * 
 * @author xiaocheng
 *
 */
public class ReLU {
	public ReLU() {

	}

	public double[] out(double[] x) {
		double[] out = new double[x.length];
		for (int i = 0; i < x.length; i++) {
			out[i] = ReLUF(x[i]);
		}
		return out;
	}

	private double ReLUF(double x) {
		if (x < 0)
			return 0;
		return x;
	}
}

测试

public class Welcome {
	public static void main(String[] args) {
		double[] x = { -10, 7, 3 };
		ReLU relu= new ReLU();
		double[] out1 = relu.out(x);
		System.out.println(out1[0] + "  " + out1[1] + "  " + out1[2]);
	}
}

运行结果

0.0  7.0  3.0

使用Pytorch实现

import torch as t
input=t.tensor([-10,7,3],dtype=t.float32)
relu=t.nn.ReLU()
print(relu(input))

运行结果

H:\ProgramData\Anaconda3\python.exe D:/PycharmProjects/untitled3/test.py
tensor([0., 7., 3.])

Process finished with exit code 0

结果相同，达到目标