Pytorch_study_Task_6:PyTorch理解更多神经网络优化方法

包含:
1.了解不同优化器
2.书写优化器代码
3.Momentum
4.二维优化，随机梯度下降法进行优化实现
5.Ada自适应梯度调节法
6.RMSProp
7.Adam
8.PyTorch优化器选择

了解不同优化器
优化器用于加速神经网络训练过程。包括以下几种：

• Stochastic Gradient Descent (SGD)
• Momentum
• AdaGrad
• RMSProp
• Adam

我觉得莫烦PTHON里的讲解特别好，虽然缺少了一点理论讲解但是非常易于理解，也很有道理。了解优化器进入该网址：https://morvanzhou.github.io/tutorials/machine-learning/torch/3-06-A-speed-up-learning/

代码实现
建立伪数据;

import torch
import torch.utils.data as Data
import torch.nn.functional as F

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()))

# 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,)

每个优化器优化一个神经网络:

# 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:

# 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

训练网络：

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

注：

• 代码参考莫烦PYTHON：
  https://morvanzhou.github.io/tutorials/machine-learning/torch/3-06-optimizer/