【从0开始的深度学习】torch解决XOR异或问题

导入库

import torch
import torch.nn.functional as F
from torch.autograd import Variable
import matplotlib.pyplot as plt

%matplotlib inline

torch.manual_seed(1)

构建数据

data = torch.tensor([[1, 0, 1], [0, 1, 1],
                 [1, 1, 0], [0, 0, 0]])
x = data[:, :2].type(torch.FloatTensor) 
y = data[:, 2].type(torch.LongTensor)
x, y = Variable(x), Variable(y)

查看构造的点

plt.scatter(x.data.numpy()[:, 0], x.data.numpy()[:, 1], c=y.data.numpy(), s=100, lw=0)
plt.show()

构建网络

class Net(torch.nn.Module):
    def __init__(self, n_feature, n_hidden, n_output):
        super(Net, self).__init__()
        self.hidden = torch.nn.Linear(n_feature, n_hidden)   
        self.out = torch.nn.Linear(n_hidden, n_output)   

    def forward(self, x):
        x = F.relu(self.hidden(x))      
        x = self.out(x)
        return x
net = Net(n_feature=2, n_hidden=10, n_output=2)
print(net)

选择优化器与损失函数

optimizer = torch.optim.Adam(net.parameters(), lr=0.01, betas=(0.9, 0.99))
loss_func = torch.nn.CrossEntropyLoss()

训练并显示训练过程

for t in range(50):
    out = net.forward(x)                 
    loss = loss_func(out, y)      
    optimizer.zero_grad()
    loss.backward()         
    optimizer.step()        
    
    if t % 10 == 0 or t in [3, 6]:
        plt.cla()
        _, prediction = torch.max(F.softmax(out), 1)
        pred_y = prediction.data.numpy().squeeze()
        target_y = y.data.numpy()
        plt.scatter(x.data.numpy()[:, 0], x.data.numpy()[:, 1], c=pred_y, s=100, lw=0)
        accuracy = sum(pred_y == target_y)/4.
        plt.text(1.5, -4, 'Accuracy=%.2f' % accuracy, fontdict={'size': 20, 'color':  'red'})
        plt.show()
        plt.pause(0.1)

plt.ioff()

效果：