pytorch（十八）：激活函数与GPU加速

一、激活函数

 

 二、实例

 

 

 

 三、具体代码

import  torch
import  torch.nn as nn
import  torch.nn.functional as F
import  torch.optim as optim
from torchvision import datasets, transforms
import torchvision

batch_size = 64
learning_rate = 1e-3
epochs = 10


train_loader = torch.utils.data.DataLoader(torchvision.datasets.MNIST('datasets/mnist_data',
                train=True,
                download=True,
                transform=torchvision.transforms.Compose([
                torchvision.transforms.ToTensor(),                       # 数据类型转化
                torchvision.transforms.Normalize((0.1307, ), (0.3081, )) # 数据归一化处理
    ])), batch_size=batch_size,shuffle=True)

test_loader = torch.utils.data.DataLoader(torchvision.datasets.MNIST('datasets/mnist_data/',
                train=False,
                download=True,
                transform=torchvision.transforms.Compose([
                torchvision.transforms.ToTensor(),
                torchvision.transforms.Normalize((0.1307, ), (0.3081, ))
    ])),batch_size=batch_size,shuffle=False)


class MLP(nn.Module):

    def __init__(self):
        super(MLP, self).__init__()

        self.model = nn.Sequential(
            nn.Linear(784, 200),
            nn.LeakyReLU(inplace=True),
            nn.Linear(200, 200),
            nn.LeakyReLU(inplace=True),
            nn.Linear(200, 10),
            nn.LeakyReLU(inplace=True),
        )

    def forward(self, x):
        x = self.model(x)

        return x


device = torch.device('cuda:0')
net = MLP().to(device)
optimizer = optim.SGD(net.parameters(), lr=learning_rate)
criteon = nn.CrossEntropyLoss().to(device)

for epoch in range(epochs):

    for batch_idx, (data, target) in enumerate(train_loader):
        data = data.view(-1, 28*28)
        data, target = data.to(device), target.cuda()

        logits = net(data)
        loss = criteon(logits, target)

        optimizer.zero_grad()
        loss.backward()
        # print(w1.grad.norm(), w2.grad.norm())
        optimizer.step()

        if batch_idx % 100 == 0:
            print('Train Epoch: {} [{}/{} ({:.0f}%)]\tLoss: {:.6f}'.format(
                epoch, batch_idx * len(data), len(train_loader.dataset),
                       100. * batch_idx / len(train_loader), loss.item()))


    test_loss = 0
    correct = 0
    for data, target in test_loader:
        data = data.view(-1, 28 * 28)
        data, target = data.to(device), target.cuda()
        logits = net(data)
        test_loss += criteon(logits, target).item()

        pred = logits.data.max(1)[1]
        correct += pred.eq(target.data).sum()

    test_loss /= len(test_loader.dataset)
    print('\nTest set: Average loss: {:.4f}, Accuracy: {}/{} ({:.0f}%)\n'.format(
        test_loss, correct, len(test_loader.dataset),
        100. * correct / len(test_loader.dataset)))