在之前的案例中,我们多是使用`datasets.ImageFolder`函数直接导入已经分类好的数据集形成`Dataset`,然后使用`DataLoader`加载`Dataset`,但是如果对无法分类的数据集,我们如何导入,并进行识别呢?

本周我将自定义一个`MyDataset`加载车牌数据集并完成车牌识别

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

👉代码输出:

device = 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 = './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)

👉代码输出

['川W9BR26', '藏WP66B0', '沪E264UD', '津D8Z15T'...]
data_paths     = list(data_dir.glob('*'))
data_paths_str = [str(path) for path in data_paths]
data_paths_str

👉代码输出

['015_licence_plate\\000000000_川W9BR26.jpg',
 '015_licence_plate\\000000000_藏WP66B0.jpg',
 '015_licence_plate\\000000001_沪E264UD.jpg',
 
 ......
 
 '015_licence_plate\\000000003_甘G24298.jpg',
 '015_licence_plate\\000000003_青SN18Q3.jpg',
 '015_licence_plate\\000000004_云HZR899.jpg',
 ...]

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()

Pytorch入门实战:10-Pytorch实现车牌识别-LMLPHP

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

👉代码输出

total_datadir = './03_traffic_sign/'

# 关于transforms.Compose的更多介绍可以参考:https://blog.csdn.net/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

👉 代码输出

(10940, 2735)
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))

👉 代码输出

The number of images in a training set is:  10944
The number of images in a test set is:  2736
The number of batches per epoch is:  684
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

👉 代码输出

Shape of X [N, C, H, W]:  torch.Size([16, 3, 224, 224])
Shape of y:  torch.Size([16, 7, 69]) torch.float64

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reshape
        x = self.reshape(x)

        return x
    
# 定义Reshape层
class Reshape(nn.Module):
    def __init__(self, shape):
        super(Reshape, self).__init__()
        self.shape = shape

    def 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

👉 代码输出

Using cuda device

Network_bn(
  (conv1): Conv2d(3, 12, kernel_size=(5, 5), stride=(1, 1))
  (bn1): BatchNorm2d(12, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
  (conv2): Conv2d(12, 12, kernel_size=(5, 5), stride=(1, 1))
  (bn2): BatchNorm2d(12, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
  (pool): MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False)
  (conv4): Conv2d(12, 24, kernel_size=(5, 5), stride=(1, 1))
  (bn4): BatchNorm2d(24, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
  (conv5): Conv2d(24, 24, kernel_size=(5, 5), stride=(1, 1))
  (bn5): BatchNorm2d(24, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
  (fc1): Linear(in_features=60000, out_features=483, bias=True)
  (reshape): Reshape()
)
import torchsummary

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

👉 代码输出

----------------------------------------------------------------
        Layer (type)               Output Shape         Param #
================================================================
            Conv2d-1         [-1, 12, 220, 220]             912
       BatchNorm2d-2         [-1, 12, 220, 220]              24
            Conv2d-3         [-1, 12, 216, 216]           3,612
       BatchNorm2d-4         [-1, 12, 216, 216]              24
         MaxPool2d-5         [-1, 12, 108, 108]               0
            Conv2d-6         [-1, 24, 104, 104]           7,224
       BatchNorm2d-7         [-1, 24, 104, 104]              48
            Conv2d-8         [-1, 24, 100, 100]          14,424
       BatchNorm2d-9         [-1, 24, 100, 100]              48
        MaxPool2d-10           [-1, 24, 50, 50]               0
           Linear-11                  [-1, 483]      28,980,483
          Reshape-12                [-1, 7, 69]               0
================================================================
Total params: 29,006,799
Trainable params: 29,006,799
Non-trainable params: 0
----------------------------------------------------------------
Input size (MB): 0.57
Forward/backward pass size (MB): 26.56
Params size (MB): 110.65
Estimated Total Size (MB): 137.79
----------------------------------------------------------------

注意对比观察模型的输出[-1, 7, 69],我们之前的网络结构输出都是[-1, 7][-1, 2][-1, 4]这样的二维数据,如果要求模型输出结果是多维数据,那么本案例将是很好的示例。

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 Variable
def test(model, test_loader, loss_model):
    size = len(test_loader.dataset) 
    num_batches = len(test_loader)
   
    model.eval()
    test_loss, correct = 0, 0
    with 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()
                  
            pred = pred.argmax(2)
            _, predicted = torch.max(y, 2)
            correct += (pred == predicted).type(torch.float).sum().item()/(y.size(0)*y.size(1))
 
    test_loss /= num_batches
    correct /= num_batches
 
    print(f'Avg loss: {test_loss:>8f}, accuracy:{correct:>8f}\n')
    return correct, test_loss
 
 
def train(model,train_loader, loss_model, optimizer):
    size = len(train_loader.dataset)
    num_batches = len(train_loader)
    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 % 100 == 0:
            print('[%5d] loss: %.3f' % (i, loss))

2. 模型的训练

test_acc_list  = []
test_loss_list = []
epochs = 30

for 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!")
Epoch 1
-------------------------------
[    0] loss: 0.211
[  100] loss: 0.163
[  200] loss: 0.141
[  300] loss: 0.125
[  400] loss: 0.090
[  500] loss: 0.090
[  600] loss: 0.097
Avg loss: 0.072495, accuracy:0.312023
 
...............
 
Epoch 30
-------------------------------
[    0] loss: 0.016
[  100] loss: 0.008
[  200] loss: 0.017
[  300] loss: 0.006
[  400] loss: 0.016
[  500] loss: 0.011
[  600] loss: 0.017
Avg loss: 0.027576, accuracy:0.623085
 
Done!

四、结果分析

import numpy as np
import matplotlib.pyplot as plt

x = [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()

Pytorch入门实战:10-Pytorch实现车牌识别-LMLPHP

五、个人总结

本周学习了如何使用Pytorch识别车牌

05-24 20:29