分类网络

"""
pytorch中数据标签默认的数据格式是LongTensor,即64位的整数
"""
import torch
from torch.autograd import Variable
import torch.nn.functional as F
import matplotlib.pyplot as plt

# 制作数据
n_data = torch.ones(100, 2)
x0 = torch.normal(2*n_data, 1)      # x0的横纵坐标
y0 = torch.zeros(100)               # x0对应的标签
x1 = torch.normal(-2*n_data, 1)     # x1的横纵坐标
y1 = torch.ones(100)                # x1对应的标签
x = torch.cat((x0, x1), 0).type(torch.FloatTensor)  # shape (200, 2) FloatTensor = 32-bit floating
y = torch.cat((y0, y1), ).type(torch.LongTensor)    # shape (200,) LongTensor = 64-bit integer

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

# 以下显示出散点图
# plt.scatter(x.data.numpy()[:, 0], x.data.numpy()[:, 1], c=y.data.numpy(), s=100, lw=0, cmap='RdYlGn')
# plt.show()

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)     # 定义网络
print(net)  # 打印出网络结构

optimizer = torch.optim.SGD(net.parameters(), lr=0.02)
loss_func = torch.nn.CrossEntropyLoss()  # 用于分类问题

plt.ion()   # 设置为实时打印

for t in range(100):
    out = net(x)                 # 输入x经过网络的前向传播，得到预测值，此时还不是概率
    loss = loss_func(out, y)     # 预测值在前，真实值在后

    optimizer.zero_grad()   # 清除上一次的梯度
    loss.backward()         # 反向传播，计算梯度
    optimizer.step()        # 优化梯度

    if t % 2 == 0:
        # 打印
        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()