PyTorch学习笔记6——优化器对比

分别在pytorch中对比了SGD、Momentum、RMSprop和Adam四种优化器的训练效果。
结合了前面的构建网络方法、批训练方法等

import torch
import torch.utils.data as Data
import torch
from torch.autograd import Variable
import matplotlib.pyplot as plt
import torch.nn.functional as F
'''
优化器
'''

# hyper parameters
LR = 0.01
BATCH_SIZE = 32
EPOCH = 12
# data
x = torch.unsqueeze(torch.linspace(-1,1,1000),dim=1)
y = x.pow(2) + 0.1*torch.normal(torch.zeros(*x.size()))
torch_dataset = Data.TensorDataset(x,y)
loader = Data.DataLoader(dataset=torch_dataset,batch_size=BATCH_SIZE,shuffle=True)
# build net
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

# four different nets
net_SGD = Net()
net_Momentum = Net()
net_RMSprop = Net()
net_Adam = Net()
nets = [net_SGD,net_Momentum,net_RMSprop,net_Adam]
# four different optimizer
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]

# train
loss_func = torch.nn.MSELoss()
losses_his = [[],[],[],[]]

for epoch in range(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(b_x)
            loss = loss_func(output,b_y)
            opt.zero_grad()
            loss.backward()
            opt.step()
            l_his.append(loss.data)

# draw
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()