比较神经网络的优化器

创建数据集并进行小批量分组

import torch
import torch.utils.data as Data
import matplotlib.pyplot as plt

torch.manual_seed(1)    # reproducible #设置Cpu

BATCH_SIZE = 32 #批量大小

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

# plot dataset 画图
plt.scatter(x.numpy(), y.numpy())
plt.show()

# 使用上节内容提到的 data loader 开始小批量 shuffle 打乱
torch_dataset = Data.TensorDataset(x, y) 
loader = Data.DataLoader(dataset=torch_dataset, batch_size=BATCH_SIZE, shuffle=True, )

创建神经网络

import torch
import torch.nn.functional as F #激励函数
#学习率
LR = 0.01
# 默认的 network 形式  定义一种nn
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))      # activation function for hidden layer
        x = self.predict(x)             # linear output
        return x

#以上神经网络已经结束 为了对比以下优化器 因此创建如下
# 为每个优化器创建一个 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 = [[], [], [], []]   # 记录 training 时不同神经网络的 loss

训练

from 数据集 import loader
from 神经网络 import nets,optimizers,losses_his,loss_func
import matplotlib.pyplot as plt
#外循环测试
EPOCH = 12
for epoch in range(EPOCH):
    print('Epoch: ', epoch)
    for _, (b_x, b_y) in enumerate(loader):

        # 对每个优化器, 优化属于他的神经网络
        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 存储的是损失的差值 因为比较的是哪个优化器更优秀

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()

作者声明

如有问题，欢迎指正！