快速搭建神经网络

搭建网络&保存网络

以下内容是根据torch官网和莫烦python学习所得

搭建网络

• 新建网络

  class Net(torch.nn.Module):
      def __init__(self, n_feature, n_hidden, n_output):
          super(Net, self).__init__()
          self.hidden = torch.nn.Linear(n_feature, n_hidden)
          self.predict = torch.nn.Linear(n_hidden, n_output)
  
      def forward(self, x):
          x = F.relu(self.hidden(x))
          x = self.predict(x)
          return x
  
  net1 = Net(1, 10, 1)   # 这是我们用这种方式搭建的 net1
  

• 快速新建

  net2 = torch.nn.Sequential(
      torch.nn.Linear(1, 10),
      torch.nn.ReLU(),
      torch.nn.Linear(10, 1)
  )
  

• 二者对比

  print(net1)
  Net(
    (hidden): Linear(in_features=1, out_features=10, bias=True)
    (predict): Linear(in_features=10, out_features=1, bias=True)
  )
  
  #######################################################
  print(net2)
  Sequential(
    (0): Linear(in_features=1, out_features=10, bias=True)
    (1): ReLU()
    (2): Linear(in_features=10, out_features=1, bias=True)
  )
  
  

保存网络

• 新建网络

  torch.manual_seed(1)    # reproducible
  
  # 假数据
  x = torch.unsqueeze(torch.linspace(-1, 1, 100), dim=1)  # x data (tensor), shape=(100, 1)
  y = x.pow(2) + 0.2*torch.rand(x.size())  # noisy y data (tensor), shape=(100, 1)
  
  def save():
      # 建网络
      net1 = torch.nn.Sequential(
          torch.nn.Linear(1, 10),
          torch.nn.ReLU(),
          torch.nn.Linear(10, 1)
      )
      optimizer = torch.optim.SGD(net1.parameters(), lr=0.5)
      loss_func = torch.nn.MSELoss()
  
      # 训练
      for t in range(100):
          prediction = net1(x)
          loss = loss_func(prediction, y)
          optimizer.zero_grad()
          loss.backward()
          optimizer.step()
  

• 保存网络

  torch.save(net1, 'net.pkl')  # 保存整个网络
  torch.save(net1.state_dict(), 'net_params.pkl')   # 只保存网络中的参数 (速度快, 占内存少)
  

• 提取网络

  # 提取整个网络
  def restore_net():
      # restore entire net1 to net2
      net2 = torch.load('net.pkl')
      prediction = net2(x)
  

  # 只提取网络参数
  def restore_params():
      # 新建 net3
      net3 = torch.nn.Sequential(
          torch.nn.Linear(1, 10),
          torch.nn.ReLU(),
          torch.nn.Linear(10, 1)
      )
  
      # 将保存的参数复制到 net3
      net3.load_state_dict(torch.load('net_params.pkl'))
      prediction = net3(x)
  

源代码

import torch
import matplotlib.pyplot as plt

# torch.manual_seed(1)    # reproducible

# fake data
x = torch.unsqueeze(torch.linspace(-1, 1, 100), dim=1)  # x data (tensor), shape=(100, 1)
y = x.pow(2) + 0.2*torch.rand(x.size())  # noisy y data (tensor), shape=(100, 1)

# The code below is deprecated in Pytorch 0.4. Now, autograd directly supports tensors
# x, y = Variable(x, requires_grad=False), Variable(y, requires_grad=False)


def save():
    # save net1
    net1 = torch.nn.Sequential(
        torch.nn.Linear(1, 10),
        torch.nn.ReLU(),
        torch.nn.Linear(10, 1)
    )
    optimizer = torch.optim.SGD(net1.parameters(), lr=0.5)
    loss_func = torch.nn.MSELoss()

    for t in range(100):
        prediction = net1(x)
        loss = loss_func(prediction, y)
        optimizer.zero_grad()
        loss.backward()
        optimizer.step()

    # plot result
    plt.figure(1, figsize=(10, 3))
    plt.subplot(131)
    plt.title('Net1')
    plt.scatter(x.data.numpy(), y.data.numpy())
    plt.plot(x.data.numpy(), prediction.data.numpy(), 'r-', lw=5)

    # 2 ways to save the net
    torch.save(net1, 'net.pkl')  # save entire net
    torch.save(net1.state_dict(), 'net_params.pkl')   # save only the parameters


def restore_net():
    # restore entire net1 to net2
    net2 = torch.load('net.pkl')
    prediction = net2(x)

    # plot result
    plt.subplot(132)
    plt.title('Net2')
    plt.scatter(x.data.numpy(), y.data.numpy())
    plt.plot(x.data.numpy(), prediction.data.numpy(), 'r-', lw=5)


def restore_params():
    # restore only the parameters in net1 to net3
    net3 = torch.nn.Sequential(
        torch.nn.Linear(1, 10),
        torch.nn.ReLU(),
        torch.nn.Linear(10, 1)
    )

    # copy net1's parameters into net3
    net3.load_state_dict(torch.load('net_params.pkl'))
    prediction = net3(x)

    # plot result
    plt.subplot(133)
    plt.title('Net3')
    plt.scatter(x.data.numpy(), y.data.numpy())
    plt.plot(x.data.numpy(), prediction.data.numpy(), 'r-', lw=5)
    plt.show()

# save net1
save()

# restore entire net (may slow)
restore_net()

# restore only the net parameters
restore_params()