pytorch构建优化器

这是莫凡python学习笔记。

1.构造数据，可以可视化看看数据样子

import torch

import torch.utils.data as Data

import torch.nn.functional as F

import matplotlib.pyplot as plt

%matplotlib inline

# torch.manual_seed(1)    # reproducible

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()

输出

2.构造数据集，及数据加载器

# 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,)

3.搭建网络，以相应优化器命名

# 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

net_SGD         = Net()

net_Momentum    = Net()

net_RMSprop     = Net()

net_Adam        = Net()

nets = [net_SGD, net_Momentum, net_RMSprop, net_Adam]

4.构造优化器，此处共构造了SGD,Momentum,RMSprop,Adam四种优化器

# 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]

5.定义损失函数，并开始迭代训练

　　 loss_func = torch.nn.MSELoss()

    losses_his = [[], [], [], []]   # record loss

    # training

    for epoch in range(EPOCH):

        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

6.画图，观察损失在不同优化器下的变化

    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()

输出

可以看到RMSprop和Adam的效果最好。