网络优化

"""
常用的网络优化器有四种：SGD, Momentum, RMSprop, Adam
通过网络的运行结果可以知道SGD的收敛效果最差
"""
import torch
import torch.utils.data as Data
import torch.nn.functional as F
from torch.autograd import Variable
import matplotlib.pyplot as plt

# 超参数
LR = 0.01
BATCH_SIZE = 32
EPOCH = 12

# 数据
x = torch.unsqueeze(torch.linspace(-1, 1, 1000), dim=1)
y = x.pow(2) + 0.1*torch.normal(torch.zeros(*x.size()))

# 画出散点图
plt.scatter(x.numpy(), y.numpy())
plt.show()

# 将数据放入torch数据库
torch_dataset = Data.TensorDataset(data_tensor=x, target_tensor=y)
loader = Data.DataLoader(dataset=torch_dataset, batch_size=BATCH_SIZE, shuffle=True, num_workers=2,)

# 搭建网络
class Net(torch.nn.Module):
    def __init__(self):
        super(Net, self).__init__()
        self.hidden = torch.nn.Linear(1, 20)
        self.predict = torch.nn.Linear(20, 1)

    def forward(self, x):
        x = F.relu(self.hidden(x))
        x = self.predict(x)
        return x

# 定义四个网络放入一个列表中
net_SGD         = Net()
net_Momentum    = Net()
net_RMSprop     = Net()
net_Adam        = Net()
nets = [net_SGD, net_Momentum, net_RMSprop, net_Adam]

# 经过不同的优化函数优化并放入列表
opt_SGD         = torch.optim.SGD(net_SGD.parameters(), lr=LR)
opt_Momentum    = torch.optim.SGD(net_Momentum.parameters(), lr=LR, momentum=0.8)
opt_RMSprop     = torch.optim.RMSprop(net_RMSprop.parameters(), lr=LR, alpha=0.9)
opt_Adam        = torch.optim.Adam(net_Adam.parameters(), lr=LR, betas=(0.9, 0.99))
optimizers = [opt_SGD, opt_Momentum, opt_RMSprop, opt_Adam]

# 计算损失值
loss_func = torch.nn.MSELoss()

# 用于记录四个网络各自的损失值
losses_his = [[], [], [], []]

# 训练
for epoch in range(EPOCH):
    print('Epoch: ', epoch)
    for step, (batch_x, batch_y) in enumerate(loader):
        # 之前的数据格式为tensor格式，不能用于训练网络，必须转换为variable
        b_x = Variable(batch_x)
        b_y = Variable(batch_y)

        for net, opt, l_his in zip(nets, optimizers, losses_his):
            output = net(b_x)              # b_x经过各自的网络获得预测值
            loss = loss_func(output, b_y)  # 计算各自的损失值
            opt.zero_grad()                # 清除上一步的梯度值
            loss.backward()                # 反向传播，计算梯度值
            opt.step()                     # 优化各个节点的参数值
            l_his.append(loss.data[0])     # 记录损失值

labels = ['SGD', 'Momentum', 'RMSprop', 'Adam']
for i, l_his in enumerate(losses_his):
    plt.plot(l_his, label=labels[i])
plt.legend(loc='best')
plt.xlabel('Steps')
plt.ylabel('Loss')
plt.ylim((0, 0.2))
plt.show()