神经网络训练中经常会有中断/重复训练/重现的需求，所以本文记录关于神经网络保存和提取的代码

1. 准备数据

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)

2.保存神经网络模型

构建函数直接保存整个网络模型

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

注：

1. torch.save(net, 'net.pkl')：通过 torch 自带的 save() 函数将整个网络保存为 pkl 文件
2. torch.save(net.state_dict(), 'net_params.pkl') ：通过 torch 自带的 save() 函数，以 net.state_dict() 方式仅保存网络的参数和结构于 pkl 文件中

3. 提取神经网络模型

3.1 从 pkl 文件提取整个网络

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)

注：使用 torch.load() 函数从pkl 文件中直接提取整个网络

3.2 从pkl文件中提取神经网络参数

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)

注：在 pkl 中仅提取参数需要使用 torch.load_state_dict() 函数

4. 画图部分

    # 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()

5. 保存和提取神经网络

# save net1
save()

# restore entire net (may slow)
restore_net()

# restore only the net parameters
restore_params()