第11讲 卷积神经网络(高级篇) GPU版本源代码
原理是基于B站 刘二大人 ：传送门PyTorch深度学习实践——卷积神经网络(高级篇)
这篇基于博主错错莫：传送门 深度学习实践 第11讲博文
仅在他的基础上加入了GPU模块，详细原理解释请看他的博文
1、Inception Moudel
import torch import torch.nn as nn from torchvision import transforms from torchvision import datasets from torch.utils.data import DataLoader import torch.nn.functional as F import torch.optim as optim # prepare dataset batch_size = 64 transform = transforms.Compose([transforms.ToTensor(), transforms.Normalize((0.1307,), (0.3081,))]) # 归一化,均值和方差 train_dataset = datasets.MNIST(root='../dataset/mnist/', train=True, download=True, transform=transform) train_loader = DataLoader(train_dataset, shuffle=True, batch_size=batch_size) test_dataset = datasets.MNIST(root='../dataset/mnist/', train=False, download=True, transform=transform) test_loader = DataLoader(test_dataset, shuffle=False, batch_size=batch_size) # design model using class class InceptionA(nn.Module): def __init__(self, in_channels): super(InceptionA, self).__init__() self.branch1x1 = nn.Conv2d(in_channels, 16, kernel_size=1) self.branch5x5_1 = nn.Conv2d(in_channels, 16, kernel_size=1) self.branch5x5_2 = nn.Conv2d(16, 24, kernel_size=5, padding=2) self.branch3x3_1 = nn.Conv2d(in_channels, 16, kernel_size=1) self.branch3x3_2 = nn.Conv2d(16, 24, kernel_size=3, padding=1) self.branch3x3_3 = nn.Conv2d(24, 24, kernel_size=3, padding=1) self.branch_pool = nn.Conv2d(in_channels, 24, kernel_size=1) def forward(self, x): branch1x1 = self.branch1x1(x) branch5x5 = self.branch5x5_1(x) branch5x5 = self.branch5x5_2(branch5x5) branch3x3 = self.branch3x3_1(x) branch3x3 = self.branch3x3_2(branch3x3) branch3x3 = self.branch3x3_3(branch3x3) branch_pool = F.avg_pool2d(x, kernel_size=3, stride=1, padding=1) branch_pool = self.branch_pool(branch_pool) outputs = [branch1x1, branch5x5, branch3x3, branch_pool] return torch.cat(outputs, dim=1) # b,c,w,h c对应的是dim=1 class Net(nn.Module): def __init__(self): super(Net, self).__init__() self.conv1 = nn.Conv2d(1, 10, kernel_size=5) self.conv2 = nn.Conv2d(88, 20, kernel_size=5) # 88 = 24x3 + 16 self.incep1 = InceptionA(in_channels=10) # 与conv1 中的10对应 self.incep2 = InceptionA(in_channels=20) # 与conv2 中的20对应 self.mp = nn.MaxPool2d(2) self.fc = nn.Linear(1408, 10) def forward(self, x): in_size = x.size(0) x = F.relu(self.mp(self.conv1(x))) # 卷积和池化的先后关系不影响 x = self.incep1(x) x = F.relu(self.mp(self.conv2(x))) x = self.incep2(x) x = x.view(in_size, -1) x = self.fc(x) return x model = Net() device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu") model.to(device) # construct loss and optimizer criterion = torch.nn.CrossEntropyLoss() optimizer = optim.SGD(model.parameters(), lr=0.01, momentum=0.5) # training cycle forward, backward, update def train(epoch): running_loss = 0.0 for batch_idx, data in enumerate(train_loader, 0): inputs, target = data inputs, target = inputs.to(device), target.to(device) optimizer.zero_grad() outputs = model(inputs) loss = criterion(outputs, target) loss.backward() optimizer.step() running_loss += loss.item() if batch_idx % 300 == 299: print('[%d, %5d] loss: %.3f' % (epoch + 1, batch_idx + 1, running_loss / 300)) running_loss = 0.0 def test(): correct = 0 total = 0 with torch.no_grad(): for data in test_loader: images, labels = data labels, images = labels.to(device), images.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(10): train(epoch) test()
2、ResidualBlock
import torch import torch.nn as nn from torchvision import transforms from torchvision import datasets from torch.utils.data import DataLoader import torch.nn.functional as F import torch.optim as optim # prepare dataset batch_size = 64 transform = transforms.Compose([transforms.ToTensor(), transforms.Normalize((0.1307,), (0.3081,))]) # 归一化,均值和方差 train_dataset = datasets.MNIST(root='../dataset/mnist/', train=True, download=True, transform=transform) train_loader = DataLoader(train_dataset, shuffle=True, batch_size=batch_size) test_dataset = datasets.MNIST(root='../dataset/mnist/', train=False, download=True, transform=transform) test_loader = DataLoader(test_dataset, shuffle=False, batch_size=batch_size) # design model using class class ResidualBlock(nn.Module): def __init__(self, channels): super(ResidualBlock, self).__init__() self.channels = channels self.conv1 = nn.Conv2d(channels, channels, kernel_size=3, padding=1) self.conv2 = nn.Conv2d(channels, channels, kernel_size=3, padding=1) def forward(self, x): y = F.relu(self.conv1(x)) y = self.conv2(y) return F.relu(x + y) # 先做y+x再做relu class Net(nn.Module): def __init__(self): super(Net, self).__init__() self.conv1 = nn.Conv2d(1, 16, kernel_size=5) self.conv2 = nn.Conv2d(16, 32, kernel_size=5) self.rblock1 = ResidualBlock(16) self.rblock2 = ResidualBlock(32) self.mp = nn.MaxPool2d(2) self.fc = nn.Linear(512, 10) def forward(self, x): in_size = x.size(0) x = self.mp(F.relu(self.conv1(x))) x = self.rblock1(x) x = self.mp(F.relu(self.conv2(x))) x = self.rblock2(x) x = x.view(in_size, -1) x = self.fc(x) return x model = Net() device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu") model.to(device) # construct loss and optimizer criterion = torch.nn.CrossEntropyLoss() optimizer = optim.SGD(model.parameters(), lr=0.01, momentum=0.5) # training cycle forward, backward, update def train(epoch): running_loss = 0.0 for batch_idx, data in enumerate(train_loader, 0): inputs, target = data inputs, target = inputs.to(device), target.to(device) optimizer.zero_grad() outputs = model(inputs) loss = criterion(outputs, target) loss.backward() optimizer.step() running_loss += loss.item() if batch_idx % 300 == 299: print('[%d, %5d] loss: %.3f' % (epoch + 1, batch_idx + 1, running_loss / 300)) running_loss = 0.0 def test(): correct = 0 total = 0 with torch.no_grad(): for data in test_loader: images, labels = data images, labels = images.to(device), 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(10): train(epoch) test()
再次感谢b站up刘二大人，和博主错错莫
