pytorch實現分類

完整代碼

#實現分類
import torch
import torch.nn.functional as F
from torch.autograd import Variable
import matplotlib.pyplot as plt
import torch.optim as optim

#生成數據
n_data = torch.ones(100, 2)
x0 = torch.normal(2*n_data, 1)
y0 = torch.zeros(100)
x1 = torch.normal(-2*n_data,1)
y1 = torch.ones(100)
#x當做數據，y當做標簽
x = torch.cat((x0,x1), 0).type(torch.FloatTensor)
y = torch.cat((y0,y1), ).type(torch.LongTensor)

x,y = Variable(x),Variable(y)

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


#定義網絡
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.predict = torch.nn.Linear(n_hidden,n_output)

    def forward(self, x):
        x = F.relu(self.hidden(x))
        x = self.predict(x)
        return x
#輸入是兩個特征，x對應的特征和y對應的特征，輸出是2個類，0和1
net = Net(2, 10, 2)
#print(net)  
#輸出為[0,1]說明圖片為class1，若是[1,0],說明輸出為class0。這是二分類
#輸出為[0,1,0]說明圖片為class1，若是[1,0,0],說明輸出為class0,若是[0,0,1],說明輸出為class2。這是三分類


#優化
optimizer = optim.SGD(net.parameters(), lr=0.02)
loss_func = torch.nn.CrossEntropyLoss() 
#輸出是概率

#可視化
plt.ion()
#plt.show()

for t in range(100):
    out = net(x)
    loss = loss_func(out, y) #預測值和真實值

    optimizer.zero_grad()
    loss.backward()
    optimizer.step()
    #可視化
    if t % 2 == 0:
        plt.cla()
        prediction = torch.max(F.softmax(out), 1)[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, cmap='RdYlGn')
        accuracy = sum(pred_y == target_y)/200
        plt.text(1.5, -4, 'Accuracy=%.2f' % accuracy, fontdict={'size': 20, 'color':  'red'})
        plt.pause(0.1)

plt.ioff()
plt.show()