Pytorch 搭建分類迴歸神經網絡並用GPU進行加速

分類網絡

import torch
import torch.nn.functional as F
from torch.autograd import Variable
import matplotlib.pyplot as plt

# 構造數據
n_data = torch.ones(100, 2)
x0 = torch.normal(3*n_data, 1)
x1 = torch.normal(-3*n_data, 1)
# 標記爲y0=0，y1=1兩類標籤
y0 = torch.zeros(100)
y1 = torch.ones(100)

# 通過.cat連接數據
x = torch.cat((x0, x1), 0).type(torch.FloatTensor)
y = torch.cat((y0, y1), 0).type(torch.LongTensor)

# .cuda()會將Variable數據遷入GPU中
x, y = Variable(x).cuda(), Variable(y).cuda()

# plt.scatter(x.data.cpu().numpy()[:, 0], x.data.cpu().numpy()[:, 1], c=y.data.cpu().numpy(), s=100, lw=0, cmap='RdYlBu')
# plt.show()

# 網絡構造方法一
class Net(torch.nn.Module):
    def __init__(self, n_feature, n_hidden, n_output):
        super(Net, self).__init__()
        # 隱藏層的輸入和輸出
        self.hidden1 = torch.nn.Linear(n_feature, n_hidden)
        self.hidden2 = torch.nn.Linear(n_hidden, n_hidden)
        # 輸出層的輸入和輸出
        self.out = torch.nn.Linear(n_hidden, n_output)

    def forward(self, x):
        x = F.relu(self.hidden2(self.hidden1(x)))
        x = self.out(x)
        return x

# 初始化一個網絡，1個輸入層，10個隱藏層，1個輸出層
net = Net(2, 10, 2)

# 網絡構造方法二
'''
net = torch.nn.Sequential(
    torch.nn.Linear(2, 10),
    torch.nn.Linear(10, 10),
    torch.nn.ReLU(),
    torch.nn.Linear(10, 2),
)
'''
# .cuda()將網絡遷入GPU中
net.cuda()
# 配置網絡優化器
optimizer = torch.optim.SGD(net.parameters(), lr=0.2)
# SGD: torch.optim.SGD(net.parameters(), lr=0.01)
# Momentum: torch.optim.SGD(net.parameters(), lr=0.01, momentum=0.8)
# RMSprop: torch.optim.RMSprop(net.parameters(), lr=0.01, alpha=0.9)
# Adam: torch.optim.Adam(net.parameters(), lr=0.01, betas=(0.9, 0.99))

loss_func = torch.nn.CrossEntropyLoss()

# 動態可視化
plt.ion()
plt.show()

for t in range(300):
    print(t)
    out = net(x)
    loss = loss_func(out, y)
    optimizer.zero_grad()
    loss.backward()
    optimizer.step()
    if t % 5 == 0:
        plt.cla()
        prediction = torch.max(F.softmax(out, dim=0), 1)[1].cuda()
        # GPU中的數據無法被matplotlib利用，需要用.cpu()將數據從GPU中遷出到CPU中
        pred_y = prediction.data.cpu().numpy().squeeze()
        target_y = y.data.cpu().numpy()
        plt.scatter(x.data.cpu().numpy()[:, 0], x.data.cpu().numpy()[:, 1], c=pred_y, s=100, lw=0, cmap='RdYlBu')
        accuracy = sum(pred_y == target_y) / 200
        plt.text(1.5, -4, 'accuracy=%.2f' % accuracy, fontdict={'size':20, 'color':'red'})
        plt.pause(0.1)

plt.ioff()
plt.show()

迴歸網絡

import torch
import torch.nn.functional as F
from torch.autograd import Variable
import matplotlib.pyplot as plt

# 構造數據
x = torch.unsqueeze(torch.linspace(-1,1,100), dim=1)
y = x.pow(2) + 0.2*torch.rand(x.size())

# .cuda()會將Variable數據遷入GPU中
x, y = Variable(x).cuda(), Variable(y).cuda()

# plt.scatter(x.data.numpy(), y.data.numpy())
# plt.show()

# 網絡構造方法一
class Net(torch.nn.Module):
    def __init__(self, n_feature, n_hidden, n_output):
        super(Net, self).__init__()
        # 隱藏層的輸入和輸出
        self.hidden = torch.nn.Linear(n_feature, n_hidden)
        # 輸出層的輸入和輸出
        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
        
# 初始化一個網絡，1個輸入層，10個隱藏層，1個輸出層
net = Net(1, 10, 1)

# 網絡構造方法二
'''
net = torch.nn.Sequential(
    torch.nn.Linear(1, 10),
    torch.nn.ReLU(),
    torch.nn.Linear(10, 1),
)
'''

# .cuda()將網絡遷入GPU中
net.cuda()
# 配置網絡優化器
optimizer = torch.optim.SGD(net.parameters(), lr=0.5)
# SGD: torch.optim.SGD(net.parameters(), lr=0.01)
# Momentum: torch.optim.SGD(net.parameters(), lr=0.01, momentum=0.8)
# RMSprop: torch.optim.RMSprop(net.parameters(), lr=0.01, alpha=0.9)
# Adam: torch.optim.Adam(net.parameters(), lr=0.01, betas=(0.9, 0.99))

loss_func = torch.nn.MSELoss()

# 動態可視化
plt.ion()
plt.show()

for t in range(300):
    prediction = net(x)
    loss = loss_func(prediction, y)
    optimizer.zero_grad()
    loss.backward()
    optimizer.step()
    if t % 5 == 0 :
        plt.cla()
        # GPU中的數據無法被matplotlib利用，需要用.cpu()將數據從GPU中遷出到CPU中
        plt.scatter(x.data.cpu().numpy(), y.data.cpu().numpy())
        plt.plot(x.data.cpu().numpy(), prediction.data.cpu().numpy(), 'r-', lw=5)
        plt.text(0.5, 0, 'Loss=%.4f' % loss.item(), fontdict={'size':20, 'color':'red'})
        plt.pause(0.1)

plt.ioff()
plt.show()