Pytorch学习07——优化器

一些知识

torch.manual_seed

设定生成随机数的种子，并返回一个torch._C.Generator 对象.

torch.manual_seed(seed)

torch.unsqueeze

返回一个新的张量，对输入的制定位置插入维度 1

注意： 返回张量与输入张量共享内存，所以改变其中一个的内容会改变另一个。

>>> x = torch.Tensor([1, 2, 3, 4])
>>> torch.unsqueeze(x, 0)
 1  2  3  4
[torch.FloatTensor of size 1x4]
>>> torch.unsqueeze(x, 1)
 1
 2
 3
 4
[torch.FloatTensor of size 4x1]

代码

import torch
import torch.utils.data as Data
import torch.nn.functional as F
import matplotlib.pyplot as plt
import os
os.environ['KMP_DUPLICATE_LIB_OK'] = 'True'

torch.manual_seed(1)

# 超参数
LR = 0.01   # 学习率
BATCH_SIZE = 32   # 一次批训练的数据多少
EPOCH = 12    # 迭代多少次

# 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 显示数据
plt.scatter(x.numpy(), y.numpy())
plt.show()

# 批训练 data loader
torch_dataset = Data.TensorDataset(x, y)
loader = Data.DataLoader(
    dataset=torch_dataset,
    batch_size=BATCH_SIZE,
    shuffle=True,    # 是否打乱数据
    num_workers=0,
)

# 每一个优化器优化一个NN

# 默认的 network 形式
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

# 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]

# 创建不同的优化器，训练不同的网络
# 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()   # 损失函数 计算误差
losses_his = [[], [], [], []]   # 记录 training 时不同神经网络的 loss

# 训练
for epoch in range(EPOCH):
    print('Epoch: ', epoch)
    for step, (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

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()

结果

原始伪数据

对比结果