用PyTorch实现图像验证码识别

本文讲解如何使用Python和PyTorch搭建一个验证码识别系统，覆盖数据生成、模型构建、训练和测试的完整流程。

1. 安装必需的库
   先安装需要用到的Python库：
   pip install torch torchvision pillow captcha numpy2. 生成验证码图片
   使用​​captcha​​库批量生成验证码图片数据集：
   from captcha.image import ImageCaptcha
   import random
   import string
   import os
   更多内容访问ttocr.com或联系1436423940
   characters = string.digits + string.ascii_uppercase
   captcha_length = 4
   image_width = 160
   image_height = 60

def create_captcha_images(num_images=10000, output_dir="captcha_images"):
os.makedirs(output_dir, exist_ok=True)
generator = ImageCaptcha(width=image_width, height=image_height)
for idx in range(num_images):
text = ''.join(random.choices(characters, k=captcha_length))
image = generator.generate_image(text)
image.save(os.path.join(output_dir, f"{text}_{idx}.png"))

create_captcha_images()3. 定义数据集类
创建一个继承自​​Dataset​​的自定义数据集类：
from torch.utils.data import Dataset, DataLoader
from torchvision import transforms
from PIL import Image
import torch

class CaptchaDataset(Dataset):
def init(self, root_dir):
self.root_dir = root_dir
self.images = os.listdir(root_dir)
self.transform = transforms.Compose([
transforms.ToTensor(),
transforms.Normalize((0.5,), (0.5,))
])
self.char_to_idx = {char: idx for idx, char in enumerate(characters)}

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

def __getitem__(self, idx):
    img_name = self.images[idx]
    label_str = img_name.split('_')[0]
    img_path = os.path.join(self.root_dir, img_name)
    image = Image.open(img_path).convert('RGB')
    image = self.transform(image)
    label = torch.tensor([self.char_to_idx[c] for c in label_str], dtype=torch.long)
    return image, label

dataset = CaptchaDataset("captcha_images")
train_loader = DataLoader(dataset, batch_size=64, shuffle=True)4. 搭建卷积和循环神经网络
模型分为CNN特征提取和RNN序列建模两个部分：
import torch.nn as nn

class CaptchaModel(nn.Module):
def init(self):
super(CaptchaModel, self).init()
self.cnn = nn.Sequential(
nn.Conv2d(3, 32, 3, padding=1), nn.ReLU(), nn.MaxPool2d(2),
nn.Conv2d(32, 64, 3, padding=1), nn.ReLU(), nn.MaxPool2d(2),
nn.Conv2d(64, 128, 3, padding=1), nn.ReLU(),
nn.MaxPool2d((2, 1))
)
self.rnn = nn.LSTM(128 * 7, 128, bidirectional=True, num_layers=2, batch_first=True)
self.fc = nn.Linear(256, len(characters))

def forward(self, x):
    x = self.cnn(x)
    x = x.permute(0, 3, 1, 2)
    b, w, c, h = x.size()
    x = x.reshape(b, w, c * h)
    x, _ = self.rnn(x)
    x = self.fc(x)
    return x5. 训练模型

配置训练过程，定义损失函数和优化器：
device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')
model = CaptchaModel().to(device)
optimizer = torch.optim.Adam(model.parameters(), lr=0.001)
criterion = nn.CrossEntropyLoss()

for epoch in range(20):
model.train()
total_loss = 0
for images, labels in train_loader:
images, labels = images.to(device), labels.to(device)
outputs = model(images)
loss = sum(criterion(outputs[:, i, :], labels[:, i]) for i in range(captcha_length))
optimizer.zero_grad()
loss.backward()
optimizer.step()
total_loss += loss.item()
print(f"Epoch {epoch+1} Loss {total_loss:.4f}")6. 测试单张图片
写一个预测函数用于识别验证码内容：
def predict(model, image_path):
model.eval()
transform = transforms.Compose([
transforms.ToTensor(),
transforms.Normalize((0.5,), (0.5,))
])
image = Image.open(image_path).convert('RGB')
image = transform(image).unsqueeze(0).to(device)
with torch.no_grad():
output = model(image)
pred = torch.argmax(output, dim=2)
result = ''.join([characters[i] for i in pred[0]])
return result

sample_image = "captcha_images/5G7Q_0.png"
prediction = predict(model, sample_image)
print("Predicted:", prediction)