pytorch1.0进行Optimizer 优化器对比

import torch
import torch.utils.data as Data  # Torch 中提供了一种帮助整理数据结构的工具, 叫做 DataLoader, 能用它来包装自己的数据, 进行批训练.
import torch.nn.functional as F  # 包含激励函数
import matplotlib.pyplot as plt

LR = 0.01   # 学习率
BATCH_SIZE = 32
EPOCH = 12

# 伪数据
# 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()

# DataLoader 是 torch 用来包装开发者自己的数据的工具.
# 将自己的 (numpy array 或其他) 数据形式装换成 Tensor, 然后再放进这个包装器中.
# 使用 DataLoader 的好处就是他们帮你有效地迭代数据

# 先转换成 torch 能识别的 Dataset
# put dateset into torch dataset
torch_dataset = Data.TensorDataset(x, y)
# 把 dataset 放入 DataLoader
loader = Data.DataLoader(dataset=torch_dataset, batch_size=BATCH_SIZE, shuffle=True, num_workers=2,) # 随机打乱数据 (打乱比较好)

# 每个优化器优化一个神经网络

# 默认的 network 形式
# default network
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

# 创建不同的优化器, 用来训练不同的网络. 并创建一个 loss_func 用来计算误差.
if __name__ == ‘__main__‘:
    # different nets
    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 = [[], [], [], []]   # record loss

    # 训练/出图
    # training
    for epoch in range(EPOCH):
        print(‘Epoch: ‘, epoch)
        for step, (b_x, b_y) in enumerate(loader):          # for each training step
            # 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

    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()