pytorch 多种optimizer优化器 的使用

"""optimizer优化器"""
import torch
import torch.utils.data as Data  #批处理模块
from torch.autograd import Variable
import torch.nn.functional as F  #激励函数模块
import matplotlib.pyplot as plt  #画图模块

#hyper parameters 超参数
LR = 0.01   #学习率
BATCH_SIZE = 32   #批处理尺寸
EPOCH = 12  #数据迭代轮数

#回归数据
x = torch.unsqueeze(torch.linspace(-1, 1, 1000),dim = 1)  #-1 到1 取1000个数 dim = 1 代表结果是列向量
# print(x)
y = x.pow(2) + 0.1*torch.normal(torch.zeros(*x.size()))
# print(y)

torch_dataset = Data.TensorDataset(x,y)
loader = Data.DataLoader(dataset=torch_dataset,batch_size=BATCH_SIZE,
                         shuffle=True,)

#建立神经网络
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):    #前向传递过程
        x = F.relu(self.hidden(x))
        x = self.predict(x)
        return x

# different nets
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=0.8)
opt_RMSprop = torch.optim.RMSprop(net_RMSprop.parameters(), 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()
losses_his = [[],[],[],[]]

for epoch in range(EPOCH):
    print(epoch)
    for step, (batch_x, batch_y) in enumerate(loader):
        # b_x = Variable(batch_x)
        # b_y = Variable(batch_y)
        for net, opt, l_his in zip(nets, optimizers,losses_his):
            output = net(x)
            loss = loss_func(output, y)

            #
            opt.zero_grad()  # 所有梯度为0
            loss.backward()  # 反向传递
            opt.step()  # 优化梯度
            print(loss.data)
            l_his.append(loss.data)

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()









转自：https://www.bilibili.com/video/av15997678/?p=17