目錄

前言

一、MyDataset文件

二、完整代碼：

三、結果展示：

四、添加accuracy值

---

• 🍨 本文為🔗365天深度學習訓練營?中的學習記錄博客
• 🍖 原作者：K同學啊 | 接輔導、項目定制

本周的學習內容是，使用pytorch實現車牌識別。

前言

????????之前的案例里面，我們大多是使用的是datasets.ImageFolder函數，直接導入已經分類好的數據集形成Dataset，然后使用DataLoader加載Dataset，但是如果對無法分類的數據集，我們應該如何導入呢。

????????這篇文章主要就是介紹通過自定義的一個MyDataset加載車牌數據集并完成車牌識別。

一、MyDataset文件

數據文件是這樣的，沒有進行分類的。

# 加載數據文件
class MyDataset(data.Dataset):def __init__(self, all_labels, data_paths_str, transform):self.img_labels = all_labels  # 獲取標簽信息self.img_dir = data_paths_str  # 圖像目錄路徑self.transform = transform   # 目標轉換函數def __len__(self):return len(self.img_labels)   # 返回數據集的長度，即標簽的數量def __getitem__(self, index):image = Image.open(self.img_dir[index]).convert('RGB')   # 打開指定索引的圖像文件，并將其轉換為RGB模式label = self.img_labels[index]  # 獲取圖像對應的標簽if self.transform:image = self.transform(image)   # 如果設置了轉換函數，則對圖像進行轉換（如，裁剪、縮放、歸一化等）return image, label  # 返回圖像和標簽

二、完整代碼：

import pathlibimport matplotlib.pyplot as plt
import numpy as np
import torch
from PIL import Image
from torch import nn
from torch.utils import data
from torchvision import transforms
import torch.nn.functional as F
from torch.autograd import Variable
import matplotlib as mpl
mpl.use('Agg')  # 在服務器上運行的時候，打開注釋device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')
print(device)data_dir = './data'
data_dir = pathlib.Path(data_dir)data_paths = list(data_dir.glob('*'))
classNames = [str(path).split('/')[1].split('_')[1].split('.')[0] for path in data_paths]
# print(classNames)  # '滬G1CE81', '云G86LR6', '鄂U71R9F', '津G467JR'....data_paths_str = [str(path) for path in data_paths]# 數據可視化
plt.rcParams['axes.unicode_minus'] = False
plt.figure(figsize=(14,5))
plt.suptitle('data show', fontsize=15)
for i in range(18):plt.subplot(3, 6, i+1)# 顯示圖片images = plt.imread(data_paths_str[i])plt.imshow(images)
plt.show()# 3、標簽數字化
char_enum = ["京","滬","津","渝","冀","晉","蒙","遼","吉","黑","蘇","浙","皖","閩","贛","魯","豫","鄂","湘","粵","桂","瓊","川","貴","云","藏","陜","甘","青","寧","新","軍","使"]number = [str(i) for i in range(0, 10)]  # 0-9 的數字
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(classNames[0])# 將字符串數字化
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 classNames]# 加載數據文件
class MyDataset(data.Dataset):def __init__(self, all_labels, data_paths_str, transform):self.img_labels = all_labels  # 獲取標簽信息self.img_dir = data_paths_str  # 圖像目錄路徑self.transform = transform   # 目標轉換函數def __len__(self):return len(self.img_labels)def __getitem__(self, index):image = Image.open(self.img_dir[index]).convert('RGB')label = self.img_labels[index]  # 獲取圖像對應的標簽if self.transform:image = self.transform(image)return image, label  # 返回圖像和標簽total_datadir = './data/'
train_transforms = transforms.Compose([transforms.Resize([224, 224]),transforms.ToTensor(),transforms.Normalize(mean=[0.485, 0.456, 0.406],std=[0.229, 0.224, 0.225])
])total_data = MyDataset(all_labels, data_paths_str, train_transforms)
# 劃分數據
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])
print(train_size, test_size)  # 10940 2735# 數據加載
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)for X, y in test_loader:print('Shape of X [N,C,H,W]:',X.shape)   # ([16, 3, 224, 224])print('Shape of y:', y.shape, y.dtype)    # torch.Size([16, 7, 69]) torch.float64break# 搭建網絡模型
class Network_bn(nn.Module):def __init__(self):super(Network_bn, self).__init__()"""nn.Conv2d()函數：第一個參數（in_channels）是輸入的channel數量第二個參數（out_channels）是輸出的channel數量第三個參數（kernel_size）是卷積核大小第四個參數（stride）是步長，默認為1第五個參數（padding）是填充大小，默認為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)# 最終reshapex = self.reshape(x)return xclass 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)model = Network_bn().to(device)
print(model)# 優化器與損失函數
optimizer = torch.optim.Adam(model.parameters(), lr=1e-4, weight_decay=0.0001)
loss_model = nn.CrossEntropyLoss()def 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()correct += (pred.argmax(1) == y).type(torch.float).sum().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 是標起始位置的值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))# 模型的訓練
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！！！')# 結果分析
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()
plt.savefig("/data/jupyter/deep_demo/p10_car_number/resultImg.jpg")  # 保存圖片在服務器的位置
plt.show()

三、結果展示：

總結：從剛開始損失為0.077 到，訓練30輪后，損失到了0.026。

四、添加accuracy值

需求：對在上面的代碼中，對loss進行了統計更新，請補充acc統計更新部分，即獲取每一次測試的ACC值。

添加accuracy的運行過程：

?