第P10周：Pytorch实现车牌识别

---

FROM

• 🍨 本文为🔗365天深度学习训练营 中的学习记录博客
• 🍖 原作者：K同学啊

---

我的环境

• 语言环境：Python 3.11.9
• 开发工具：Jupyter Lab
• 深度学习环境：
  • torch==2.3.1+cu121
  • torchvision==0.18.1+cu121

---

一、导入数据

from torchvision.transforms import transforms
from torch.utils.data       import DataLoader
from torchvision            import datasets
import torchvision.models   as models
import torch.nn.functional  as F
import torch.nn             as nn
import torch,torchvision

device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
device

输出：

1. 获取类别名

import os,PIL,random,pathlib
import matplotlib.pyplot as plt
# 支持中文
plt.rcParams['font.sans-serif'] = ['SimHei']  # 用来正常显示中文标签
plt.rcParams['axes.unicode_minus'] = False  # 用来正常显示负号

data_dir = './015_licence_plate/'
data_dir = pathlib.Path(data_dir)

data_paths  = list(data_dir.glob('*'))
classeNames = [str(path).split("/")[1].split("_")[1].split(".")[0] for path in data_paths]
print(classeNames)

输出：

data_paths     = list(data_dir.glob('*'))
data_paths_str = [str(path) for path in data_paths]
data_paths_str

输出：

2.数据可视化

plt.figure(figsize=(14,5))
plt.suptitle("数据示例（K同学啊）",fontsize=15)

for i in range(18):
    plt.subplot(3,6,i+1)
    # plt.xticks([])
    # plt.yticks([])
    # plt.grid(False)
    
    # 显示图片
    images = plt.imread(data_paths_str[i])
    plt.imshow(images)

plt.show()

输出：

3. 标签数字化

import numpy as np

char_enum = ["京","沪","津","渝","冀","晋","蒙","辽","吉","黑","苏","浙","皖","闽","赣","鲁",\
              "豫","鄂","湘","粤","桂","琼","川","贵","云","藏","陕","甘","青","宁","新","军","使"]

number   = [str(i) for i in range(0, 10)]    # 0 到 9 的数字
alphabet = [chr(i) for i in range(65, 91)]   # A 到 Z 的字母

char_set       = char_enum + number + alphabet
char_set_len   = len(char_set)
label_name_len = len(classeNames[0])

# 将字符串数字化
def text2vec(text):
    vector = np.zeros([label_name_len, char_set_len])
    for i, c in enumerate(text):
        idx = char_set.index(c)
        vector[i][idx] = 1.0
    return vector

all_labels = [text2vec(i) for i in classeNames]

4. 加载数据文件

import os
import pandas as pd
from torchvision.io import read_image
from torch.utils.data import Dataset
import torch.utils.data as data
from PIL import Image

class MyDataset(data.Dataset):
    def __init__(self, all_labels, data_paths_str, transform):
        self.img_labels = all_labels      # 获取标签信息
        self.img_dir    = data_paths_str  # 图像目录路径
        self.transform  = transform       # 目标转换函数

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

    def __getitem__(self, index):
        image    = Image.open(self.img_dir[index]).convert('RGB')#plt.imread(self.img_dir[index])  # 使用 torchvision.io.read_image 读取图像
        label    = self.img_labels[index]  # 获取图像对应的标签
        
        if self.transform:
            image = self.transform(image)
            
        return image, label  # 返回图像和标签
       
 total_datadir = './03_traffic_sign/'

# 关于transforms.Compose的更多介绍可以参考：https://blog.youkuaiyun.com/qq_38251616/article/details/124878863
train_transforms = transforms.Compose([
    transforms.Resize([224, 224]),  # 将输入图片resize成统一尺寸
    transforms.ToTensor(),          # 将PIL Image或numpy.ndarray转换为tensor，并归一化到[0,1]之间
    transforms.Normalize(           # 标准化处理-->转换为标准正太分布（高斯分布），使模型更容易收敛
        mean=[0.485, 0.456, 0.406], 
        std =[0.229, 0.224, 0.225])  # 其中 mean=[0.485,0.456,0.406]与std=[0.229,0.224,0.225] 从数据集中随机抽样计算得到的。
])

total_data = MyDataset(all_labels, data_paths_str, train_transforms)
total_data

5.划分数据

train_size = int(0.8 * len(total_data))
test_size  = len(total_data) - train_size
train_dataset, test_dataset = torch.utils.data.random_split(total_data, [train_size, test_size])
train_size,test_size

输出：

train_loader = torch.utils.data.DataLoader(train_dataset,
                                           batch_size=16,
                                           shuffle=True)
test_loader = torch.utils.data.DataLoader(test_dataset,
                                          batch_size=16,
                                          shuffle=True)

print("The number of images in a training set is: ", len(train_loader)*16)
print("The number of images in a test set is: ", len(test_loader)*16)
print("The number of batches per epoch is: ", len(train_loader))

输出：