基于pytorch的车牌识别

🍨 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

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

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 = 'F:/host/Data/车牌识别数据/'
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]
classeNames = []
for path in data_paths:parts = str(path).split(os.sep)if len(parts) > 1:filename = parts[-1]if "_" in filename:name_part = filename.split("_")[1]if "." in name_part:classeNames.append(name_part.split(".")[0])print(classeNames)

输出：
在这里插入图片描述

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

输出：
在这里插入图片描述

2. 数据可视化

plt.figure(figsize=(14,5))
plt.suptitle("数据示例",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()

在这里插入图片描述

3. 标签数字化

import numpy as npchar_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] = 1.0return vectorall_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 Imageclass 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 = 'F:/host/Data/车牌识别数据/'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

在这里插入图片描述

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

在这里插入图片描述

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))

在这里插入图片描述

for X, y in test_loader:print("Shape of X [N, C, H, W]: ", X.shape)print("Shape of y: ", y.shape, y.dtype)break

在这里插入图片描述

二、自建模型

class Network_bn(nn.Module):def __init__(self):super(Network_bn, self).__init__()"""nn.Conv2d()函数：第一个参数（in_channels）是输入的channel数量第二个参数（out_channels）是输出的channel数量第三个参数（kernel_size）是卷积核大小第四个参数（stride）是步长，默认为1第五个参数（padding）是填充大小，默认为0"""self.conv1 = nn.Conv2d(in_channels=3, out_channels=12, kernel_size=5, stride=1, padding=0)self.bn1 = nn.BatchNorm2d(12)self.conv2 = nn.Conv2d(in_channels=12, out_channels=12, kernel_size=5, stride=1, padding=0)self.bn2 = nn.BatchNorm2d(12)self.pool = nn.MaxPool2d(2,2)self.conv4 = nn.Conv2d(in_channels=12, out_channels=24, kernel_size=5, stride=1, padding=0)self.bn4 = nn.BatchNorm2d(24)self.conv5 = nn.Conv2d(in_channels=24, out_channels=24, kernel_size=5, stride=1, padding=0)self.bn5 = nn.BatchNorm2d(24)self.fc1 = nn.Linear(24*50*50, label_name_len*char_set_len)self.reshape = Reshape([label_name_len,char_set_len])def forward(self, x):x = F.relu(self.bn1(self.conv1(x)))      x = F.relu(self.bn2(self.conv2(x)))     x = self.pool(x)                        x = F.relu(self.bn4(self.conv4(x)))     x = F.relu(self.bn5(self.conv5(x)))  x = self.pool(x)                        x = x.view(-1, 24*50*50)x = self.fc1(x)# 最终reshapex = self.reshape(x)return x# 定义Reshape层
class Reshape(nn.Module):def __init__(self, shape):super(Reshape, self).__init__()self.shape = shapedef forward(self, x):return x.view(x.size(0), *self.shape)device = "cuda" if torch.cuda.is_available() else "cpu"
print("Using {} device".format(device))model = Network_bn().to(device)
model

在这里插入图片描述

import torchsummary''' 显示网络结构 '''
torchsummary.summary(model, (3, 224, 224))

在这里插入图片描述

三、模型训练

1. 优化器与损失函数

optimizer  = torch.optim.Adam(model.parameters(), lr=1e-4, weight_decay=0.0001)loss_model = nn.CrossEntropyLoss()

from torch.autograd import Variabledef test(model, test_loader, loss_model):size = len(test_loader.dataset)num_batches = len(test_loader)model.eval()test_loss, correct = 0, 0with torch.no_grad():for X, y in test_loader:X, y = X.to(device), y.to(device)pred = model(X)test_loss += loss_model(pred, y).item()test_loss /= num_batchesprint(f"Avg loss: {test_loss:>8f} \n")return correct,test_lossdef train(model,train_loader,loss_model,optimizer):model=model.to(device)model.train()for i, (images, labels) in enumerate(train_loader, 0): #0是标起始位置的值。images = Variable(images.to(device))labels = Variable(labels.to(device))optimizer.zero_grad()outputs = model(images)loss = loss_model(outputs, labels)loss.backward()optimizer.step()if i % 1000 == 0:    print('[%5d] loss: %.3f' % (i, loss))

2. 模型的训练

test_acc_list  = []
test_loss_list = []
epochs = 30for t in range(epochs):print(f"Epoch {t+1}\n-------------------------------")train(model,train_loader,loss_model,optimizer)test_acc,test_loss = test(model, test_loader, loss_model)test_acc_list.append(test_acc)test_loss_list.append(test_loss)
print("Done!")

在这里插入图片描述

四、结果分析

import numpy as np
import matplotlib.pyplot as pltx = [i for i in range(1,31)]plt.plot(x, test_loss_list, label="Loss", alpha=0.8)plt.xlabel("Epoch")
plt.ylabel("Loss")plt.legend()
plt.show()

在这里插入图片描述

五、个人小结

在本项目中，我构建了一个基于深度学习的车牌识别系统。通过导入必要的库、获取类别名、数据可视化、标签数字化、加载数据文件、划分数据集、创建自定义数据集类、定义网络结构、设置优化器与损失函数、进行模型训练和测试，以及绘制训练过程中的损失曲线，我们对整个流程进行了详细的实践和分析。模型训练结果显示，随着训练的进行，损失逐渐减小，表明模型正在学习并逐渐优化。

本文来自互联网用户投稿，该文观点仅代表作者本人，不代表本站立场。本站仅提供信息存储空间服务，不拥有所有权，不承担相关法律责任。如若转载，请注明出处：http://www.rhkb.cn/news/342926.html

如若内容造成侵权/违法违规/事实不符，请联系长河编程网进行投诉反馈email:809451989@qq.com，一经查实，立即删除！