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

lr = 0.01
batchsize = 32
epoch = 12
x = torch.unsqueeze(torch.linspace(-1,1,1000),dim=1)
# unsqueeze 把一维变二维
y = x.pow(2) + 0.1 * torch.normal(torch.zeros(*x.size()))
# 0.1 * torch.normal(torch.zeros(*x.size())) 增加噪点
torch_dataset = Data.TensorDataset(x,y)
loader = Data.DataLoader(dataset=torch_dataset,batch_size=batchsize,shuffle=True)
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
net_SGD = Net()
net_Momentum = Net()
net_RMSProp = Net()
net_Adam = Net()
nets = [net_SGD,net_Momentum,net_RMSProp,net_Adam]
opt_SGD = torch.optim.SGD(net_SGD.parameters(),lr=lr)
opt_Momentum = torch.optim.SGD(net_Momentum.parameters(),lr=lr,momentum=0.9)
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]
loss_func = torch.nn.MSELoss()
loss_his = [[],[],[],[]]             # 记录损失
for epoch in range(12):
    for step,(batch_x,batch_y) in enumerate(loader):
        for net,opt,l_his in zip(nets,optimizers,loss_his):
            output = net(batch_x)
            loss = loss_func(output,batch_y)
            opt.zero_grad()
            loss.backward()
            opt.step()
            l_his.append(loss.data.numpy())
labels = ['SGD','Momentum','RMSProp','Adam']
for i ,l_his in enumerate(loss_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()