常见优化器的PyTorch实现

机器学习炼丹术

发布于 2020-07-14 11:04:58

1.3K00

代码可运行

文章被收录于专栏：机器学习炼丹术机器学习炼丹术

运行总次数：0

代码可运行

这里主要讲不同常见优化器代码的实现，以及在一个小数据集上做一个简单的比较。

其中，SGD和SGDM，还有Adam是pytorch自带的优化器，而RAdam是最近提出的一个说是Adam更强的优化器，但是一般情况下真正的大佬还在用SGDM来做优化器。

导入必要库：

import torch
import torch.nn as nn
import torch.nn.functional as F
import torch.optim as optim
import matplotlib.pyplot as plt
import torch.utils.data as Data
from torch.optim.optimizer import Optimizer
import math

主程序部分：

LR = 0.01
BATCH_SIZE = 32
EPOCH = 12

# fake dataset
x = torch.unsqueeze(torch.linspace(-1, 1, 300), 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,
    num_workers=2
)


class Net(nn.Module):
    def __init__(self):
        super(Net, self).__init__()
        self.hidden = nn.Linear(1, 20)
        self.prediction = nn.Linear(20, 1)

    def forward(self, x):
        x = F.relu(self.hidden(x))
        x = self.prediction(x)
        return x


def main():
    net_SGD = Net()
    net_Momentum = Net()
    net_Adam = Net()
    net_RAdam = Net()
    nets = [net_SGD, net_Momentum, net_Adam, net_RAdam]
    opt_SGD = optim.SGD(net_SGD.parameters(), lr=LR)
    opt_Momentum = optim.SGD(net_Momentum.parameters(), lr=LR, momentum=0.9)
    opt_Adam = optim.Adam(net_Adam.parameters(), lr=LR, betas=(0.9, 0.99))
    opt_RAdam = RAdam(net_RAdam.parameters(),lr=LR,weight_decay=0)
    optimizers = [opt_SGD, opt_Momentum, opt_Adam, opt_RAdam]
    loss_func = nn.MSELoss()
    losses_his = [[], [], [], []]
    # training
    for epoch in range(EPOCH):
        print('EPOCH:', epoch)
        for step, (batch_x, batch_y) in enumerate(loader):
            b_x = batch_x
            b_y = batch_y
            for net, opt, l_his in zip(nets, optimizers, losses_his):
                out = net(b_x)
                loss = loss_func(out, b_y)
                opt.zero_grad()
                loss.backward()
                opt.step()
                l_his.append(loss.item())
    labels = ['SGD', 'Momentum', 'Adam','RAdam']
    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()


if __name__ == '__main__':
    main()

下图是优化器的对比：