项目github : https://github.com/taisuii/ClassificationCaptchaOcr
某验验证码识别，算法部分不放了，识别的教程和代码如下
import requests
from PIL import Image, ImageFont, ImageDraw, ImageOps
from io import BytesIO
def crop_image(image_bytes, coordinates):
img = Image.open(BytesIO(image_bytes))
width, height = img.size
grid_width = width // 3
grid_height = height // 3
cropped_images = []
for coord in coordinates:
y, x = coord
left = (x - 1) * grid_width
upper = (y - 1) * grid_height
right = left + grid_width
lower = upper + grid_height
box = (left, upper, right, lower)
cropped_img = img.crop(box)
cropped_images.append(cropped_img)
return cropped_images
coordinates = [[1, 1], [1, 2], [1, 3], [2, 1], [2, 2], [2, 3], [3, 1], [3, 2], [3, 3]]
bg_img = requests.get("https://static.geetest.com/captcha_v4/policy/3d0936b11a2c4a65bbb53635e656c780/nine/110394/2024-09-06T00/ed02acd0ac294a41b880d9106240f12a.jpg").content
cropped_images = crop_image(bg_img, coordinates)
for j, img_crop in enumerate(cropped_images):
img_crop.save(f"./test_crop/bg{j}.jpg")
import requests
from PIL import Image, ImageFont, ImageDraw, ImageOps
from io import BytesIO
def crop_image(image_bytes, coordinates):
img = Image.open(BytesIO(image_bytes))
width, height = img.size
grid_width = width // 3
grid_height = height // 3
cropped_images = []
for coord in coordinates:
y, x = coord
left = (x - 1) * grid_width
upper = (y - 1) * grid_height
right = left + grid_width
lower = upper + grid_height
box = (left, upper, right, lower)
cropped_img = img.crop(box)
cropped_images.append(cropped_img)
return cropped_images
coordinates = [[1, 1], [1, 2], [1, 3], [2, 1], [2, 2], [2, 3], [3, 1], [3, 2], [3, 3]]
bg_img = requests.get("https://static.geetest.com/captcha_v4/policy/3d0936b11a2c4a65bbb53635e656c780/nine/110394/2024-09-06T00/ed02acd0ac294a41b880d9106240f12a.jpg").content
cropped_images = crop_image(bg_img, coordinates)
for j, img_crop in enumerate(cropped_images):
img_crop.save(f"./test_crop/bg{j}.jpg")
import torchvision.transforms as transforms
from torchvision.datasets import ImageFolder
from tqdm import tqdm
import torch
import torchvision
import torch.nn as nn
from torch.utils.data import DataLoader
import numpy as np
data_transform = transforms.Compose(
[
transforms.Resize((224, 224)),
transforms.ToTensor(),
transforms.Normalize(
(0.485, 0.456, 0.406), (0.229, 0.224, 0.225)
),
]
)
class CustomDataset:
def __init__(self, data_dir):
self.dataset = ImageFolder(root=data_dir, transform=data_transform)
def __len__(self):
return len(self.dataset)
def __getitem__(self, idx):
image, label = self.dataset[idx]
return image, label
class MyResNet18(torch.nn.Module):
def __init__(self, num_classes):
super(MyResNet18, self).__init__()
self.resnet = torchvision.models.resnet18(pretrained=True)
self.resnet.fc = nn.Linear(512, num_classes)
def forward(self, x):
return self.resnet(x)
def train(epoch):
device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
data_dir = "dataset"
custom_dataset = CustomDataset(data_dir)
batch_size = 64
data_loader = DataLoader(custom_dataset, batch_size=batch_size, shuffle=True)
model = MyResNet18(num_classes=91)
model.to(device)
criterion = torch.nn.CrossEntropyLoss()
optimizer = torch.optim.SGD(model.parameters(), lr=0.001, momentum=0.9)
for i in range(epoch):
losses = []
data_loader_tqdm = tqdm(data_loader)
for inputs, labels in data_loader_tqdm:
inputs, labels = inputs.to(device), labels.to(device)
optimizer.zero_grad()
outputs = model(inputs)
loss = criterion(outputs, labels)
losses.append(loss.item())
epoch_loss = np.mean(losses)
data_loader_tqdm.set_description(
f"This epoch is {i} and it's loss is {loss.item()}, average loss {epoch_loss}"
)
loss.backward()
optimizer.step()
torch.save(model.state_dict(), f'model/my_resnet18_{epoch_loss}.pth')
print(f"completed. Model saved.")
if __name__ == '__main__':
train(50)
import torchvision.transforms as transforms
from torchvision.datasets import ImageFolder
from tqdm import tqdm
import torch
import torchvision
import torch.nn as nn
from torch.utils.data import DataLoader
import numpy as np
data_transform = transforms.Compose(
[
transforms.Resize((224, 224)),
transforms.ToTensor(),
transforms.Normalize(
(0.485, 0.456, 0.406), (0.229, 0.224, 0.225)
),
]
)
class CustomDataset:
def __init__(self, data_dir):
self.dataset = ImageFolder(root=data_dir, transform=data_transform)
def __len__(self):
return len(self.dataset)
def __getitem__(self, idx):
image, label = self.dataset[idx]
return image, label
class MyResNet18(torch.nn.Module):
def __init__(self, num_classes):
super(MyResNet18, self).__init__()
self.resnet = torchvision.models.resnet18(pretrained=True)
self.resnet.fc = nn.Linear(512, num_classes)
def forward(self, x):
return self.resnet(x)
def train(epoch):
device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
data_dir = "dataset"
custom_dataset = CustomDataset(data_dir)
batch_size = 64
data_loader = DataLoader(custom_dataset, batch_size=batch_size, shuffle=True)
model = MyResNet18(num_classes=91)
model.to(device)
[培训]内核驱动高级班，冲击BAT一流互联网大厂工作，每周日13:00-18:00直播授课
