微调现有的模型
import torch
import torch.nn as nn
import torch.optim as optim
import torchvision
import torchvision.transforms as transforms
from torchvision import models
def main():
# 数据预处理
transform = transforms.Compose([
transforms.Resize(224), # ResNet expects input size of 224x224
transforms.ToTensor(),
transforms.Normalize((0.5, 0.5, 0.5), (0.5, 0.5, 0.5))
])
# 加载训练和测试数据集
trainset = torchvision.datasets.CIFAR10(root='./data', train=True, download=True, transform=transform)
trainloader = torch.utils.data.DataLoader(trainset, batch_size=100, shuffle=True, num_workers=2)
testset = torchvision.datasets.CIFAR10(root='./data', train=False, download=True, transform=transform)
testloader = torch.utils.data.DataLoader(testset, batch_size=100, shuffle=False, num_workers=2)
# 检查是否有可用的GPU
device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")
print(f'Using device: {device}')
# 加载预训练的 ResNet-18 模型
net = models.resnet18(pretrained=True)
num_ftrs = net.fc.in_features
net.fc = nn.Linear(num_ftrs, 10) # CIFAR-10 有 10 个类别
net = net.to(device)
#微调模型结构
# 定义损失函数和优化器
criterion = nn.CrossEntropyLoss()
optimizer = optim.SGD(net.parameters(), lr=0.001, momentum=0.9)
# 训练网络
for epoch in range(10): # 训练10个epoch
running_loss = 0.0
for i, data in enumerate(trainloader, 0):
inputs, labels = data
inputs, labels = inputs.to(device), labels.to(device)
optimizer.zero_grad()
outputs = net(inputs)
loss = criterion(outputs, labels)
loss.backward()
optimizer.step()
running_loss += loss.item()
if i % 100 == 99: # 每100个小批量打印一次
print(f'[Epoch {epoch + 1}, Batch {i + 1}] loss: {running_loss / 100:.3f}')
running_loss = 0.0
print('Finished Training')
# 在测试数据集上测试网络
correct = 0
total = 0
with torch.no_grad():
for data in testloader:
images, labels = data
images, labels = images.to(device), labels.to(device)
outputs = net(images)
_, predicted = torch.max(outputs.data, 1)
total += labels.size(0)
correct += (predicted == labels).sum().item()
print(f'Accuracy of the network on the 10000 test images: {100 * correct / total:.2f}%')
if __name__ == '__main__':
main()
从0开始实现
import torch
import torch.nn as nn
import torch.optim as optim
import torchvision
import torchvision.transforms as transforms
import torch.nn.functional as F
# 定义一个残差块
class BasicBlock(nn.Module):
def __init__(self, in_channels, out_channels, stride=1):
super(BasicBlock, self).__init__()
self.conv1 = nn.Conv2d(in_channels, out_channels, kernel_size=3, stride=stride, padding=1, bias=False)
self.bn1 = nn.BatchNorm2d(out_channels)
self.relu = nn.ReLU(inplace=True)
self.conv2 = nn.Conv2d(out_channels, out_channels, kernel_size=3, stride=1, padding=1, bias=False)
self.bn2 = nn.BatchNorm2d(out_channels)
self.shortcut = nn.Sequential()
if stride != 1 or in_channels != out_channels:
self.shortcut = nn.Sequential(
nn.Conv2d(in_channels, out_channels, kernel_size=1, stride=stride, bias=False),
nn.BatchNorm2d(out_channels)
)
def forward(self, x):
out = self.relu(self.bn1(self.conv1(x)))
out = self.bn2(self.conv2(out))
out += self.shortcut(x)
out = self.relu(out)
return out
# 定义 ResNet 模型
class ResNet(nn.Module):
def __init__(self, block, num_blocks, num_classes=10):
super(ResNet, self).__init__()
self.in_channels = 64
self.conv1 = nn.Conv2d(3, 64, kernel_size=3, stride=1, padding=1, bias=False)
self.bn1 = nn.BatchNorm2d(64)
self.relu = nn.ReLU(inplace=True)
self.layer1 = self._make_layer(block, 64, num_blocks[0], stride=1)
self.layer2 = self._make_layer(block, 128, num_blocks[1], stride=2)
self.layer3 = self._make_layer(block, 256, num_blocks[2], stride=2)
self.layer4 = self._make_layer(block, 512, num_blocks[3], stride=2)
self.avg_pool = nn.AdaptiveAvgPool2d((1, 1))
self.fc = nn.Linear(512, num_classes)
def _make_layer(self, block, out_channels, num_blocks, stride):
strides = [stride] + [1] * (num_blocks - 1)
layers = []
for stride in strides:
layers.append(block(self.in_channels, out_channels, stride))
self.in_channels = out_channels
return nn.Sequential(*layers)
def forward(self, x):
out = self.relu(self.bn1(self.conv1(x)))
out = self.layer1(out)
out = self.layer2(out)
out = self.layer3(out)
out = self.layer4(out)
out = self.avg_pool(out)
out = out.view(out.size(0), -1)
out = self.fc(out)
return out
def ResNet18():
return ResNet(BasicBlock, [2, 2, 2, 2])
def main():
# 数据预处理
transform = transforms.Compose([
transforms.Resize(32),
transforms.ToTensor(),
transforms.Normalize((0.5, 0.5, 0.5), (0.5, 0.5, 0.5))
])
# 加载训练和测试数据集
trainset = torchvision.datasets.CIFAR10(root='./data', train=True, download=True, transform=transform)
trainloader = torch.utils.data.DataLoader(trainset, batch_size=100, shuffle=True, num_workers=2)
testset = torchvision.datasets.CIFAR10(root='./data', train=False, download=True, transform=transform)
testloader = torch.utils.data.DataLoader(testset, batch_size=100, shuffle=False, num_workers=2)
# 检查是否有可用的GPU
device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")
print(f'Using device: {device}')
# 定义网络、损失函数和优化器
net = ResNet18().to(device)
criterion = nn.CrossEntropyLoss()
optimizer = optim.SGD(net.parameters(), lr=0.001, momentum=0.9)
# 训练网络
for epoch in range(10): # 训练10个epoch
running_loss = 0.0
for i, data in enumerate(trainloader, 0):
inputs, labels = data
inputs, labels = inputs.to(device), labels.to(device)
optimizer.zero_grad()
outputs = net(inputs)
loss = criterion(outputs, labels)
loss.backward()
optimizer.step()
running_loss += loss.item()
if i % 100 == 99: # 每100个小批量打印一次
print(f'[Epoch {epoch + 1}, Batch {i + 1}] loss: {running_loss / 100:.3f}')
running_loss = 0.0
print('Finished Training')
# 在测试数据集上测试网络
correct = 0
total = 0
with torch.no_grad():
for data in testloader:
images, labels = data
images, labels = images.to(device), labels.to(device)
outputs = net(images)
_, predicted = torch.max(outputs.data, 1)
total += labels.size(0)
correct += (predicted == labels).sum().item()
print(f'Accuracy of the network on the 10000 test images: {100 * correct / total:.2f}%')
if __name__ == '__main__':
main()