代码以及详细注释：

import torch
import torch.utils.data as Data
import torch.nn.functional as F
import matplotlib.pyplot as plt

# torch.manual_seed(1)    # reproducible
"""
    超参数
"""
# 学习率
LR = 0.01
# 批大小
BATCH_SIZE = 32
# 轮次
EPOCH = 12

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

# # plot dataset
# plt.scatter(x.numpy(), y.numpy())
# plt.show()


# put dateset into torch dataset
torch_dataset = Data.TensorDataset(x, y)
# 数据加载器
loader = Data.DataLoader(dataset=torch_dataset, batch_size=BATCH_SIZE, shuffle=True, num_workers=2,)


# default network
class Net(torch.nn.Module):
    def __init__(self):
        super(Net, self).__init__()
        self.hidden = torch.nn.Linear(1, 20)   # hidden layer
        self.predict = torch.nn.Linear(20, 1)   # output layer

    def forward(self, x):
        x = F.relu(self.hidden(x))      # activation function for hidden layer
        x = self.predict(x)             # linear output
        return x

if __name__ == '__main__':
    # 相同的网络结构
    net_SGD         = Net()
    net_Momentum    = Net()
    net_RMSprop     = Net()
    net_Adam        = Net()
    # 将上面的网络集成到这里
    nets = [net_SGD, net_Momentum, net_RMSprop, net_Adam]

    # 不同的优化器
    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))
    # 将上面的优化器集成到这里
    optimizers = [opt_SGD, opt_Momentum, opt_RMSprop, opt_Adam]

    # 损失函数
    loss_func = torch.nn.MSELoss()
    losses_his = [[], [], [], []]   # record loss

    # 训练轮次
    for epoch in range(EPOCH):
        print('Epoch: ', epoch)
        # 分批训练
        for step, (b_x, b_y) in enumerate(loader):          # for each training step
            for net, opt, l_his in zip(nets, optimizers, losses_his):
                output = net(b_x)              # get output for every net
                loss = loss_func(output, b_y)  # compute loss for every net
                opt.zero_grad()                # clear gradients for next train
                loss.backward()                # backpropagation, compute gradients
                opt.step()                     # apply gradients
                l_his.append(loss.data)        # loss recoder

    # 绘图
    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()

运行结果：