人工智能概论第五次作业

一、模型的保存提取

import torch

import matplotlib.pyplot as plt

import os

os.environ["KMP_DUPLICATE_LIB_OK"]="TRUE"

# 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)

# x, y = Variable(x, requires_grad=False), Variable(y, requires_grad=False)

def save():    ＃建网络

    # save net1S

    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()

    # 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') # 保存整个网络

    torch.save(net1.state_dict(), 'net_params.pkl') # 只保存网络中的参数

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()

# 保存 net1
save()

#提取整个网络
restore_net()

# 提取网络参数，复制到新网络
restore_params()

二、更改模型存放地址（到D盘）  

import torch

import matplotlib.pyplot as plt

import os

os.environ["KMP_DUPLICATE_LIB_OK"]="TRUE"

# 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)

# x, y = Variable(x, requires_grad=False), Variable(y, requires_grad=False)

def save():    ＃建网络

    # save net1S

    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()

    # 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, 'D:\\pytorch\\net.pkl') # 保存整个网络

    torch.save(net1.state_dict(), 'D:\\pytorch\\net_params.pkl') # 只保存网络中的参数

def restore_net():

    # restore entire net1 to net2

    net2 = torch.load('D:\\pytorch\\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('D:\\pytorch\\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()

# 保存 net1
save()

#提取整个网络
restore_net()

# 提取网络参数，复制到新网络
restore_params()

 

三、运行结果

 模型存放在D盘：