09-pytorch(优化器)

优化器

Momentum 从平地到了下坡的地方，加速了他的行走
AdaGrad 让每一个参数都有学习率，相当给人穿了一双鞋子
RMSProp 是两者的结合

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

### 定义神经网络
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))
        x = self.predict(x)
        return x

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

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()

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

比较四个优化器

# 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(),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]

# 记录误差
loss_func = torch.nn.MSELoss()
losses_his = [[], [], [], []]   # record loss

    # training
    plt.figure(figsize=(10,10))
    for epoch in range(EPOCH):
        print('Epoch: ', epoch)
        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.numpy())     # loss recoder

    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()

Epoch:  0
Epoch:  1
Epoch:  2
Epoch:  3
Epoch:  4
Epoch:  5
Epoch:  6
Epoch:  7
Epoch:  8
Epoch:  9
Epoch:  10
Epoch:  11