批训练&优化器

数据先Tensor化再load

批训练.py

import torch
import torch.utils.data as Data

torch.manual_seed(1)    # reproducible

BATCH_SIZE = 5
# BATCH_SIZE = 8

x = torch.linspace(1, 10, 10)       # this is x data (torch tensor)
y = torch.linspace(10, 1, 10)       # this is y data (torch tensor)

torch_dataset = Data.TensorDataset(data_tensor=x, target_tensor=y)
loader = Data.DataLoader(
    dataset=torch_dataset,      # torch TensorDataset format
    batch_size=BATCH_SIZE,      # mini batch size
    shuffle=True,               # random shuffle for training
    num_workers=2,              # subprocesses for loading data
)
if __name__ == '__main__':
    for epoch in range(3):   # train entire dataset 3 times
        for step, (batch_x, batch_y) in enumerate(loader):  # for each training step
            # train your data...
            print('Epoch: ', epoch, '| Step: ', step, '| batch x: ',
                  batch_x.numpy(), '| batch y: ', batch_y.numpy())

优化器比较

在数据分批训练的基础上比较几种不同优化器的收敛效果

优化器.py

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

# 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()

# put dateset into torch dataset
torch_dataset = Data.TensorDataset(data_tensor=x, target_tensor=y)
loader = Data.DataLoader(dataset=torch_dataset, batch_size=BATCH_SIZE, shuffle=True, num_workers=2, )


# 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


# 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

# training
if __name__ == '__main__':
    for epoch in range(EPOCH):
        print('Epoch: ', epoch)
        for step, (batch_x, batch_y) in enumerate(loader):  # for each training step
            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[0])  # 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()