利用深度学习实现验证码识别-3-ResNet18

在当今数字化时代，验证码作为一种重要的安全验证手段，广泛应用于各种网络场景。然而，传统的验证码识别方法往往效率低下，准确率不高。今天，我们将介绍一种基于 ResNet18 的验证码识别方法，它能够高效、准确地识别验证码，为网络安全提供有力保障。
在这里插入图片描述

一、技术背景

深度学习技术在图像识别领域取得了巨大的成功，ResNet18 作为一种经典的深度神经网络架构，具有强大的特征提取能力和良好的泛化性能。我们利用 ResNet18 的这些优势，将其应用于验证码识别任务中，通过迁移学习的方法，快速训练出一个高效的验证码识别模型。

以下是实现 ResNet18 验证码识别的代码：

import torch.nn as nn
import torch.optim as optim
from torch.utils.data import DataLoader, Dataset, random_split
from torchvision import transforms, models
import random
import string
from PIL import Image, ImageDraw, ImageFont
import os
import matplotlib.pyplot as plt# 检查 CUDA 是否可用
device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
print(f'Using device: {device}')# 数据生成器，支持自定义字符集和验证码长度
class CaptchaDataset(Dataset):def __init__(self, length=1000, charset=None, captcha_length=5, transform=None):self.length = lengthself.transform = transformself.charset = charset if charset is not None else string.ascii_letters + string.digitsself.captcha_length = captcha_lengthself.num_classes = len(self.charset)self.font = ImageFont.truetype("arial.ttf", 40)self.image_size = (100, 40)def __len__(self):return self.lengthdef __getitem__(self, idx):text = ''.join(random.choices(self.charset, k=self.captcha_length))image = Image.new('L', self.image_size, color=255)draw = ImageDraw.Draw(image)draw.text((10, 5), text, font=self.font, fill=0)if self.transform:image = self.transform(image)label = [self.charset.index(c) for c in text]return image, torch.tensor(label, dtype=torch.long)# 数据增强和预处理
transform = transforms.Compose([transforms.Resize((40, 100)),transforms.RandomRotation(10),transforms.ColorJitter(brightness=0.5, contrast=0.5),transforms.ToTensor(),transforms.Normalize((0.5,), (0.5,))
])# 设置字符集和验证码长度
charset = string.digits  # 仅支持数字
captcha_length = 4  # 验证码长度设置为 6 位
dataset = CaptchaDataset(length=2000, charset=charset, captcha_length=captcha_length, transform=transform)
train_size = int(0.8 * len(dataset))
val_size = len(dataset) - train_size
train_dataset, val_dataset = random_split(dataset, [train_size, val_size])train_loader = DataLoader(train_dataset, batch_size=64, shuffle=True)
val_loader = DataLoader(val_dataset, batch_size=64, shuffle=False)# 使用预训练 ResNet 模型，迁移学习
class CaptchaModel(nn.Module):def __init__(self, num_classes, captcha_length):super(CaptchaModel, self).__init__()self.captcha_length = captcha_lengthself.resnet = models.resnet18(weights=models.ResNet18_Weights.DEFAULT)self.resnet.conv1 = nn.Conv2d(1, 64, kernel_size=7, stride=2, padding=3, bias=False)num_ftrs = self.resnet.fc.in_featuresself.resnet.fc = nn.Linear(num_ftrs, num_classes * self.captcha_length)  # 动态调整输出层大小def forward(self, x):x = self.resnet(x)return x.view(-1, self.captcha_length, num_classes)# 初始化模型，损失函数和优化器
num_classes = len(charset)
model = CaptchaModel(num_classes=num_classes, captcha_length=captcha_length).to(device)
criterion = nn.CrossEntropyLoss()
optimizer = optim.Adam(model.parameters(), lr=0.001)# 加载或保存训练检查点
def save_checkpoint(state, filename="captcha_model_checkpoint.pth.tar"):print("=> Saving checkpoint")torch.save(state, filename)def load_checkpoint(filename="captcha_model_checkpoint.pth.tar"):print("=> Loading checkpoint")return torch.load(filename)# 支持多次训练，从检查点恢复训练
def train_model(epochs, resume=False):start_epoch = 0if resume and os.path.isfile("captcha_model_checkpoint.pth.tar"):checkpoint = load_checkpoint()model.load_state_dict(checkpoint['state_dict'])optimizer.load_state_dict(checkpoint['optimizer'])start_epoch = checkpoint['epoch']scaler = torch.cuda.amp.GradScaler()for epoch in range(start_epoch, epochs):model.train()running_loss = 0.0for images, labels in train_loader:images, labels = images.to(device), labels.to(device)optimizer.zero_grad()with torch.cuda.amp.autocast():outputs = model(images)loss = sum(criterion(outputs[:, i, :], labels[:, i]) for i in range(captcha_length))scaler.scale(loss).backward()scaler.step(optimizer)scaler.update()running_loss += loss.item()# 计算验证集准确率val_accuracy = evaluate_accuracy(val_loader)print(f'Epoch [{epoch+1}/{epochs}], Loss: {running_loss/len(train_loader):.4f}, Val Accuracy: {val_accuracy:.4f}')# 保存检查点save_checkpoint({'epoch': epoch + 1,'state_dict': model.state_dict(),'optimizer': optimizer.state_dict(),})# 计算准确率
def evaluate_accuracy(data_loader):model.eval()correct = 0total = 0with torch.no_grad():for images, labels in data_loader:images, labels = images.to(device), labels.to(device)outputs = model(images)predicted = torch.argmax(outputs, dim=2)total += labels.size(0) * captcha_lengthcorrect += (predicted == labels).sum().item()return correct / total# 可视化模型预测结果
def visualize_predictions(num_samples=16):model.eval()samples, labels = next(iter(DataLoader(val_dataset, batch_size=num_samples, shuffle=True)))samples, labels = samples.to(device), labels.to(device)with torch.no_grad():outputs = model(samples)predicted = torch.argmax(outputs, dim=2)samples = samples.cpu()predicted = predicted.cpu()labels = labels.cpu()fig, axes = plt.subplots(4, 4, figsize=(10, 10))for i in range(16):ax = axes[i // 4, i % 4]ax.imshow(samples[i].squeeze(), cmap='gray')true_text = ''.join([dataset.charset[l] for l in labels[i]])pred_text = ''.join([dataset.charset[p] for p in predicted[i]])ax.set_title(f'True: {true_text}\nPred: {pred_text}')ax.axis('off')plt.show()# 训练模型
train_model(epochs=20, resume=False)# 可视化模型预测结果
visualize_predictions()

在这里插入图片描述

四、模型评估与可视化

准确率计算：我们使用准确率作为模型的评估指标，计算方法是将模型预测正确的验证码数量除以总验证码数量。在验证集上的准确率可以反映模型的泛化能力。
可视化预测结果：为了更好地理解模型的预测结果，我们使用可视化方法展示了模型在验证集上的预测结果。具体来说，我们随机选择了一些验证码图像，并将其输入到模型中进行预测。然后，我们将模型的预测结果与真实结果进行比较，并以图像的形式展示出来。