基于pytorch的人脸识别脚本（python示例）

Statement

本代码未经系统测试及专业测评

示例1

import torch
import torch.nn as nn
import torch.optim as optim
import torchvision.transforms as transforms
import torchvision.datasets as datasets

# 定义数据转换
transform = transforms.Compose([
    transforms.Resize((224, 224)),
    transforms.ToTensor(),
    transforms.Normalize(mean=[.485, .456, .406], std=[.229, .224, .225])
])

# 加载数据集
train_dataset = datasets.ImageFolder('path/to/train/dataset', transform=transform)
test_dataset = datasets.ImageFolder('path/to/test/dataset', transform=transform)

# 定义模型
model = nn.Sequential(
    nn.Conv2d(3, 64, kernel_size=3, stride=1, padding=1),
    nn.ReLU(),
    nn.MaxPool2d(kernel_size=2, stride=2),
    nn.Conv2d(64, 128, kernel_size=3, stride=1, padding=1),
    nn.ReLU(),
    nn.MaxPool2d(kernel_size=2, stride=2),
    nn.Conv2d(128, 256, kernel_size=3, stride=1, padding=1),
    nn.ReLU(),
    nn.MaxPool2d(kernel_size=2, stride=2),
    nn.Flatten(),
    nn.Linear(256 * 28 * 28, 1024),
    nn.ReLU(),
    nn.Linear(1024, 512),
    nn.ReLU(),
    nn.Linear(512, 2)
)

# 定义损失函数和优化器
criterion = nn.CrossEntropyLoss()
optimizer = optim.Adam(model.parameters(), lr=.001)

# 训练模型
for epoch in range(10):
    running_loss = .
    for i, data in enumerate(train_dataset, ):
        inputs, labels = data
        optimizer.zero_grad()
        outputs = model(inputs)
        loss = criterion(outputs, labels)
        loss.backward()
        optimizer.step()
        running_loss += loss.item()
        if i % 100 == 99:
            print('[%d, %5d] loss: %.3f' % (epoch + 1, i + 1, running_loss / 100))
            running_loss = .

# 测试模型
correct = 
total = 
with torch.no_grad():
    for data in test_dataset:
        images, labels = data
        outputs = model(images)
        _, predicted = torch.max(outputs.data, 1)
        total += labels.size()
        correct += (predicted == labels).sum().item()

print('Accuracy of the network on the test images: %d %%' % (100 * correct / total))

示例2

import torch
import torch.nn as nn
import torch.optim as optim
import torchvision
import torchvision.transforms as transforms
from torch.utils.data import DataLoader
from torch.utils.data import Dataset
from PIL import Image

# 定义数据集类
class FaceDataset(Dataset):
    def __init__(self, data_list, transform=None):
        self.data_list = data_list
        self.transform = transform

    def __len__(self):
        return len(self.data_list)

    def __getitem__(self, index):
        img_path, label = self.data_list[index]
        img = Image.open(img_path).convert('RGB')
        if self.transform is not None:
            img = self.transform(img)
        return img, label

# 定义卷积神经网络模型
class Net(nn.Module):
    def __init__(self):
        super(Net, self).__init__()
        self.conv1 = nn.Conv2d(3, 6, 5)
        self.pool = nn.MaxPool2d(2, 2)
        self.conv2 = nn.Conv2d(6, 16, 5)
        self.fc1 = nn.Linear(16 * 5 * 5, 120)
        self.fc2 = nn.Linear(120, 84)
        self.fc3 = nn.Linear(84, 2)

    def forward(self, x):
        x = self.pool(torch.relu(self.conv1(x)))
        x = self.pool(torch.relu(self.conv2(x)))
        x = x.view(-1, 16 * 5 * 5)
        x = torch.relu(self.fc1(x))
        x = torch.relu(self.fc2(x))
        x = self.fc3(x)
        return x

# 定义训练函数
def train(model, train_loader, criterion, optimizer):
    model.train()
    running_loss = 0.0
    for i, (inputs, labels) in enumerate(train_loader, 0):
        optimizer.zero_grad()
        outputs = model(inputs)
        loss = criterion(outputs, labels)
        loss.backward()
        optimizer.step()
        running_loss += loss.item()
    return running_loss / len(train_loader)

# 定义测试函数
def test(model, test_loader, criterion):
    model.eval()
    correct = 0
    total = 0
    running_loss = 0.0
    with torch.no_grad():
        for i, (inputs, labels) in enumerate(test_loader, 0):
            outputs = model(inputs)
            _, predicted = torch.max(outputs.data, 1)
            total += labels.size(0)
            correct += (predicted == labels).sum().item()
            loss = criterion(outputs, labels)
            running_loss += loss.item()
    return running_loss / len(test_loader), correct / total

# 定义主函数
def main():
    # 定义数据预处理
    transform = transforms.Compose([transforms.Resize((32, 32)),
                                    transforms.ToTensor(),
                                    transforms.Normalize((0.5, 0.5, 0.5), (0.5, 0.5, 0.5))])

    # 定义数据集
    train_list = [('path/to/face1.jpg', 0), ('path/to/face2.jpg', 1), ...]
    test_list = [('path/to/face3.jpg', 0), ('path/to/face4.jpg', 1), ...]
    train_dataset = FaceDataset(train_list, transform=transform)
    test_dataset = FaceDataset(test_list, transform=transform)

    # 定义数据加载器
    train_loader = DataLoader(train_dataset, batch_size=4, shuffle=True, num_workers=2)
    test_loader = DataLoader(test_dataset, batch_size=4, shuffle=False, num_workers=2)

    # 定义模型、损失函数、优化器
    net = Net()
    criterion = nn.CrossEntropyLoss()
    optimizer = optim.SGD(net.parameters(), lr=0.001, momentum=0.9)

    # 训练模型
    for epoch in range(10):
        train_loss = train(net, train_loader, criterion, optimizer)
        test_loss, test_acc = test(net, test_loader, criterion)
        print('Epoch %d, Train Loss: %.3f, Test Loss: %.3f, Test Acc: %.3f' % (epoch+1, train_loss, test_loss, test_acc))

    # 保存模型
    torch.save(net.state_dict(), 'path/to/model.pt')

if __name__ == '__main__':
    main()

这个示例代码中，我们首先定义了一个数据集类 FaceDataset，它继承自 torch.utils.data.Dataset，并重写了__len__ 和 __ getitem__ 方法，用于获取数据集中的样本。然后我们定义了一个卷积神经网络模型 Net，它继承自 nn.Module，并实现了 forward 方法，用于前向计算。接着我们定义了训练函数 train 和测试函数 test，它们分别用于模型的训练和测试。最后我们定义了一个主函数 main，它首先定义了数据预处理和数据加载器，然后定义了模型、损失函数和优化器，接着训练模型并保存。在训练过程中，我们使用了交叉熵损失函数和随机梯度下降优化器，每个 epoch 训练和测试一次，并输出训练和测试的损失和准确率。

示例3

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

# 定义数据预处理
transform = transforms.Compose([
                transforms.Resize((224, 224)),
                transforms.ToTensor(),
                transforms.Normalize(mean=[0.485, 0.456, 0.406],
                                     std=[0.229, 0.224, 0.225])
                ])

# 加载训练集和测试集
train_dataset = datasets.ImageFolder('./train', transform=transform)
test_dataset = datasets.ImageFolder('./test', transform=transform)

# 定义批量大小
batch_size = 8

# 创建数据加载器
train_loader = DataLoader(train_dataset, batch_size=batch_size, shuffle=True)
test_loader = DataLoader(test_dataset, batch_size=batch_size, shuffle=False)

# 定义模型
class Net(nn.Module):
    def __init__(self):
        super(Net, self).__init__()
        self.conv1 = nn.Conv2d(3, 32, 5, padding=2)
        self.pool = nn.MaxPool2d(2, 2)
        self.conv2 = nn.Conv2d(32, 64, 5, padding=2)
        self.fc1 = nn.Linear(64 * 56 * 56, 1024)
        self.fc2 = nn.Linear(1024, 2)

    def forward(self, x):
        x = self.pool(torch.relu(self.conv1(x)))
        x = self.pool(torch.relu(self.conv2(x)))
        x = x.view(-1, 64 * 56 * 56)
        x = torch.relu(self.fc1(x))
        x = self.fc2(x)
        return x

# 实例化模型并定义损失函数和优化器
net = Net()
criterion = nn.CrossEntropyLoss()
optimizer = optim.SGD(net.parameters(), lr=0.001, momentum=0.9)

# 训练网络
for epoch in range(10):

    running_loss = 0.0
    for i, data in enumerate(train_loader, 0):

        inputs, labels = data
        optimizer.zero_grad()

        outputs = net(inputs)
        loss = criterion(outputs, labels)
        loss.backward()
        optimizer.step()

        running_loss += loss.item()
        if i % 100 == 99:
            print('[%d, %5d] loss: %.3f' % (epoch + 1, i + 1, running_loss / 100))
            running_loss = 0.0

print('Finished Training')

# 测试网络
correct = 0
total = 0
with torch.no_grad():
    for data in test_loader:
        images, labels = data
        outputs = net(images)
        _, predicted = torch.max(outputs.data, 1)
        total += labels.size(0)
        correct += (predicted == labels).sum().item()

print('Accuracy of the network on the test images: %d %%' % (100 * correct / total))