中文字体识别—书和行楷,pytorch实践，代码

下面是一个简单的中文字体识别-隶书和行楷的PyTorch实现代码，供参考：

import torch
import torch.nn as nn
import torch.optim as optim
from torch.utils.data import DataLoader, Dataset
import torchvision.transforms as transforms
from PIL import Image
import os
import numpy as np

# 定义超参数
batch_size = 32
learning_rate = 0.001
num_epochs = 10
num_classes = 2
device = torch.device("cuda" if torch.cuda.is_available() else "cpu")

# 定义数据集类
class FontDataset(Dataset):
    def __init__(self, root, transform=None):
        self.root = root
        self.transform = transform
        self.imgs = list(sorted(os.listdir(root)))

    def __getitem__(self, index):
        img_path = os.path.join(self.root, self.imgs[index])
        img = Image.open(img_path).convert("L")
        label = 0 if img_path.split("/")[-1].split("_")[0] == "lishu" else 1
        if self.transform is not None:
            img = self.transform(img)
        return img, label

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

# 定义数据预处理
transform = transforms.Compose([
    transforms.Resize((64, 64)),
    transforms.ToTensor(),
    transforms.Normalize((0.5,), (0.5,))
])

# 加载数据集
train_dataset = FontDataset(root="./font/train", transform=transform)
test_dataset = FontDataset(root="./font/test", transform=transform)
train_loader = DataLoader(dataset=train_dataset, batch_size=batch_size, shuffle=True)
test_loader = DataLoader(dataset=test_dataset, batch_size=batch_size, shuffle=False)

# 定义卷积神经网络模型
class ConvNet(nn.Module):
    def __init__(self, num_classes):
        super(ConvNet, self).__init__()
        self.layer1 = nn.Sequential(
            nn.Conv2d(1, 16, kernel_size=5, stride=1, padding=2),
            nn.BatchNorm2d(16),
            nn.ReLU(),
            nn.MaxPool2d(kernel_size=2, stride=2))
        self.layer2 = nn.Sequential(
            nn.Conv2d(16, 32, kernel_size=5, stride=1, padding=2),
            nn.BatchNorm2d(32),
            nn.ReLU(),
            nn.MaxPool2d(kernel_size=2, stride=2))
        self.fc = nn.Linear(32*16*16, num_classes)

    def forward(self, x):
        out = self.layer1(x)
        out = self.layer2(out)
        out = out.reshape(out.size(0), -1)
        out = self.fc(out)
        return out

# 定义模型、损失函数和优化器
model = ConvNet(num_classes).to(device)
criterion = nn.CrossEntropyLoss()
optimizer = optim.Adam(model.parameters(), lr=learning_rate)

# 训练模型
total_step = len(train_loader)
for epoch in range(num_epochs):
    for i, (images, labels) in enumerate(train_loader):
        images = images.to(device)
        labels = labels.to(device)

        # 前向传播和计算损失
        outputs = model(images)
        loss = criterion(outputs, labels)

        # 反向传播和优化
        optimizer.zero_grad()
        loss.backward()
        optimizer.step()

        # 打印日志
        if (i + 1) % 100 == 0:
            print('Epoch [{}/{}], Step [{}/{}], Loss: {:.4f}'
                  .format(epoch + 1, num_epochs, i + 1, total_step, loss.item()))

# 测试模型
model.eval()
with torch.no_grad():
    correct = 0
    total = 0
    for images, labels in test_loader:
        images = images.to(device)
        labels = labels.to(device)
        outputs = model(images)
        _, predicted = torch.max(outputs.data, 1)
        total += labels.size(0)
        correct += (predicted == labels).sum().item()

    print('Accuracy of the model on the test images: {} %'.format(100 * correct / total))

# 保存模型参数
torch.save(model.state_dict(), 'font.ckpt')

可以根据自己的数据集和具体需求进行修改和优化。