莫煩Python_優化器

  為了對比各種優化器的效果，需要模拟一些資料：

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

LR = 0.01
BATCH_SIZE = 32
EPOCH = 12

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

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

為了對比每一種優化器，我們給它們各自建立一個神經網絡，但這個神經網絡都來自同一個

Net

形式：

class Net(torch.nn.Module):  # default network
    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__':
    # 為每個優化器建立一個net
    net_SGD = Net()
    net_Momentum = Net()
    net_RMSprop = Net()
    net_Adam = Net()
    nets = [net_SGD, net_Momentum, net_RMSprop, net_Adam]

    # different optimizers
    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]

    loss_func = torch.nn.MSELoss()
    losses_his = [[], [], [], []]  # 記錄training時不同神經網絡的loss

    for epoch in range(EPOCH):  # training
        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()
           

SGD

是最普通的優化器，也可以說沒有加速效果；而

Momentum

是

SGD

的改良版，它加入了動量原則；後面的

RMSprop

又是

Momentum

的更新版；而

Adam

又是

RMSprop

的更新版。