PyTorch 深度学习实践 第10讲 卷积神经网络（基础篇）

CPU

import torch
from torchvision import transforms
from torchvision import datasets
from torch.utils.data import DataLoader
import torch.nn.functional as F

batch_size = 64
transform = transforms.Compose([transforms.ToTensor(), transforms.Normalize((0.1307,), (0.3081,))])

train_dataset = datasets.MNIST(root = '../tmp/', train = True, download = True, transform = transform)
train_loader = DataLoader(dataset = train_dataset,
                    batch_size =batch_size,
                    shuffle = True,
                    num_workers = 2)
test_dataset = datasets.MNIST(root = '../tmp/', train = False, download = True, transform = transform)
test_loader = DataLoader(dataset = test_dataset,
                         batch_size = 1,
                         shuffle = False)
class Model(torch.nn.Module):
  def __init__(self):
    super(Model, self).__init__()
    self.conv1 = torch.nn.Conv2d(1, 10, kernel_size = 5)
    self.conv2 = torch.nn.Conv2d(10, 20, kernel_size = 5)
    self.pooling = torch.nn.MaxPool2d(2)
    self.fc = torch.nn.Linear(320, 10)


  def forward(self, x):
    batch_size = x.size(0)
    x = F.relu(self.pooling(self.conv1(x)))
    x = F.relu(self.pooling(self.conv2(x)))
    x = x.view(batch_size, -1)
    return self.fc(x)


model = Model()

criterion = torch.nn.CrossEntropyLoss()
optimizer = torch.optim.SGD(model.parameters(), lr = 0.01, momentum = 0.5)

def train(epoch):
  running_loss = 0.0
  for i, data in enumerate(train_loader, 0):
    inputs, target = data
    optimizer.zero_grad()
    y_pred = model(inputs)
    loss = criterion(y_pred, target)
    loss.backward()
    optimizer.step()

    running_loss += loss

    if i % 300 == 299:
      print('[%d, %5d] loss: %.3f' % (epoch + 1, i + 1, running_loss / 300) )
      running_loss = 0.0

def test():
    correct = 0
    total = 0
    with torch.no_grad():
        for i, data in enumerate(test_loader):
            images, labels = data
            outputs = model(images)
            _, predicted = torch.max(outputs.data, dim=1)
            total += labels.size(0)
            correct += (predicted == labels).sum().item()
    print('Accuracy on test set: %d %%' % (100 * correct / total))


if __name__ == '__main__':
  for epoch in range(100):
    train(epoch)
    test()

GPU

import torch
from torchvision import transforms
from torchvision import datasets
from torch.utils.data import DataLoader
import torch.nn.functional as F

batch_size = 64
transform = transforms.Compose([transforms.ToTensor(), transforms.Normalize((0.1307,), (0.3081,))])

train_dataset = datasets.MNIST(root = '../tmp/', train = True, download = True, transform = transform)
train_loader = DataLoader(dataset = train_dataset,
                    batch_size =batch_size,
                    shuffle = True,
                    num_workers = 2)
test_dataset = datasets.MNIST(root = '../tmp/', train = False, download = True, transform = transform)
test_loader = DataLoader(dataset = test_dataset,
                         batch_size = 1,
                         shuffle = False)
class Model(torch.nn.Module):
  def __init__(self):
    super(Model, self).__init__()
    self.conv1 = torch.nn.Conv2d(1, 10, kernel_size = 5)
    self.conv2 = torch.nn.Conv2d(10, 20, kernel_size = 5)
    self.pooling = torch.nn.MaxPool2d(2)
    self.fc = torch.nn.Linear(320, 10)


  def forward(self, x):
    batch_size = x.size(0)
    x = F.relu(self.pooling(self.conv1(x)))
    x = F.relu(self.pooling(self.conv2(x)))
    x = x.view(batch_size, -1)
    return self.fc(x)


model = Model()
device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")
model.to(device)

criterion = torch.nn.CrossEntropyLoss()
optimizer = torch.optim.SGD(model.parameters(), lr = 0.01, momentum = 0.5)

def train(epoch):
  running_loss = 0.0
  for i, data in enumerate(train_loader, 0):
    inputs, target = data
    inputs = inputs.to(device)
    target = target.to(device)
    optimizer.zero_grad()
    y_pred = model(inputs)
    loss = criterion(y_pred, target)
    loss.backward()
    optimizer.step()

    running_loss += loss

    if i % 300 == 299:
      print('[%d, %5d] loss: %.3f' % (epoch + 1, i + 1, running_loss / 300) )
      running_loss = 0.0

def test():
    correct = 0
    total = 0
    with torch.no_grad():
        for i, data in enumerate(test_loader):
            images, labels = data
            images = images.to(device)
            labels = labels.to(device)
            outputs = model(images)
            _, predicted = torch.max(outputs.data, dim=1)
            total += labels.size(0)
            correct += (predicted == labels).sum().item()
    print('Accuracy on test set: %d %%' % (100 * correct / total))


if __name__ == '__main__':
  for epoch in range(100):
    train(epoch)
    test()