优化器的性能比较

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

torch.manual_seed(1)    # reproducible
#hyper param
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()))

# plot dataset
# plt.scatter(x.numpy(), y.numpy())
# plt.show()
# 使用上节内容提到的 data loader
torch_dataset = Data.TensorDataset(x, y)
loader = Data.DataLoader(dataset=torch_dataset, batch_size=BATCH_SIZE, shuffle=True, num_workers=2,)
#神经网络
class Net(torch.nn.Module):     # 继承 torch 的 Module
    def __init__(self, n_feature, n_hidden, n_output):
        super(Net, self).__init__()     # 继承 __init__ 功能
        self.hidden = torch.nn.Linear(n_feature, n_hidden)   # 隐藏层线性输出
        self.out = torch.nn.Linear(n_hidden, n_output)       # 输出层线性输出

    def forward(self, x):
        # 正向传播输入值, 神经网络分析出输出值
        x = F.relu(self.hidden(x))      # 激励函数(隐藏层的线性值)
        x = self.out(x)                 # 输出值, 但是这个不是预测值, 预测值还需要再另外计算
        return x
# 为每个优化器创建一个 net
net_SGD= Net(1,10,1)
net_Momentum= Net(1,10,1)
net_RMSprop= Net(1,10,1)
net_Adam= Net(1,10,1)
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

if __name__ == '__main__':
    for epoch in range(EPOCH):
        print('Epoch: ', epoch)
        for step, (batch_x, batch_y) in enumerate(loader):
            # 对每个优化器, 优化属于他的神经网络
            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)              # 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','Momentun','RMSprop','Adam']
    for i in range(len(losses_his)):
        plt.plot(np.arange(len(losses_his[i])), losses_his[i], label=labels[i])
    plt.legend(loc='best')
    plt.xlabel('Steps')
    plt.ylabel('Loss')
    plt.show()