街景字符識別編碼- 字符識別模型

CNN模型

pytorch代碼構建CNN模型

CNN即卷積神經網絡，是一種層次模型，輸入的是原始的像素數據，CNN通過卷積、池化、非線性激活函數和全連接層構成。

層級結構主要是數據輸入層/ Input layer，卷積計算層/ CONV layer，ReLU激勵層 / ReLU layer，池化層 / Pooling layer，全，連接層 / FC layer；
CNN作爲一種端到端的結構。在CNN訓練的過程中是直接從圖像像素到最終的輸出，並不涉及到具體的特徵提取和構建模型的過程；在Pytorch中構建CNN模型只需要定義好模型的參數和正向傳播即可，Pytorch會根據正向傳播自動計算反向傳播。

下面會構建一個非常簡單的CNN，然後進行訓練。這個CNN模型包括兩個卷積層，最後並聯6個全連接層進行分類。

pytorch代碼構建CNN模型

#導入模塊
import os, sys, glob, shutil, json
os.environ["CUDA_VISIBLE_DEVICES"] = '0'
import cv2

from PIL import Image
import numpy as np

from tqdm import tqdm, tqdm_notebook

%pylab inline

import torch
torch.manual_seed(0)
torch.backends.cudnn.deterministic = False
torch.backends.cudnn.benchmark = True

import torchvision.models as models
import torchvision.transforms as transforms
import torchvision.datasets as datasets
import torch.nn as nn
import torch.nn.functional as F
import torch.optim as optim
from torch.autograd import Variable
from torch.utils.data.dataset import Dataset

class SVHNDataset(Dataset):
    def __init__(self, img_path, img_label, transform=None):
        self.img_path = img_path
        self.img_label = img_label 
        if transform is not None:
            self.transform = transform
        else:
            self.transform = None

    def __getitem__(self, index):
        img = Image.open(self.img_path[index]).convert('RGB')#因爲opencv打開的是BGR格式，所以我們需要轉換成RGB

        if self.transform is not None:
            img = self.transform(img)
        
        lbl = np.array(self.img_label[index], dtype=np.int)
        lbl = list(lbl)  + (5 - len(lbl)) * [10]
        return img, torch.from_numpy(np.array(lbl[:5]))

    def __len__(self):
        return len(self.img_path)
        
 train_path = glob.glob('/mchar_train/*.png')
train_path.sort()
train_json = json.load(open('/mchar_train.json'))
train_label = [train_json[x]['label'] for x in train_json]
print(len(train_path), len(train_label))

train_loader = torch.utils.data.DataLoader(
    SVHNDataset(train_path, train_label,
                transforms.Compose([
                    transforms.Resize((64, 128)),
                    transforms.RandomCrop((60, 120)),
                    transforms.ColorJitter(0.3, 0.3, 0.2),
                    transforms.RandomRotation(10),
                    transforms.ToTensor(),
                    transforms.Normalize([0.485, 0.456, 0.406], [0.229, 0.224, 0.225])
    ])), 
    batch_size=40, 
    shuffle=True, 
    num_workers=10,
)

val_path = glob.glob(/mchar_val/*.png')
val_path.sort()
val_json = json.load(open('/mchar_val.json'))
val_label = [val_json[x]['label'] for x in val_json]
print(len(val_path), len(val_label))

val_loader = torch.utils.data.DataLoader(
    SVHNDataset(val_path, val_label,
                transforms.Compose([
                    transforms.Resize((60, 120)),
                    # transforms.ColorJitter(0.3, 0.3, 0.2),
                    # transforms.RandomRotation(5),
                    transforms.ToTensor(),
                    transforms.Normalize([0.485, 0.456, 0.406], [0.229, 0.224, 0.225])
    ])), 
    batch_size=40, 
    shuffle=False, 
    num_workers=10,
)
#這裏使用ResNet18的模型進行特徵提取，精度更高
class SVHN_Model1(nn.Module):
    def __init__(self):
        super(SVHN_Model1, self).__init__()
                
        model_conv = models.resnet18(pretrained=True)
        model_conv.avgpool = nn.AdaptiveAvgPool2d(1)
        model_conv = nn.Sequential(*list(model_conv.children())[:-1])
        self.cnn = model_conv
        
        self.fc1 = nn.Linear(512, 11)
        self.fc2 = nn.Linear(512, 11)
        self.fc3 = nn.Linear(512, 11)
        self.fc4 = nn.Linear(512, 11)
        self.fc5 = nn.Linear(512, 11)
    
    def forward(self, img):        
        feat = self.cnn(img)
        # print(feat.shape)
        feat = feat.view(feat.shape[0], -1)
        c1 = self.fc1(feat)
        c2 = self.fc2(feat)
        c3 = self.fc3(feat)
        c4 = self.fc4(feat)
        c5 = self.fc5(feat)
        return c1, c2, c3, c4, c5
      
def train(train_loader, model, criterion, optimizer, epoch):
    # 切換模型爲訓練模式
    model.train()
    train_loss = []
    
    for i, (input, target) in enumerate(train_loader):
        if use_cuda:
            input = input.cuda()
            target = target.cuda()
            
        c0, c1, c2, c3, c4 = model(input)
        loss = criterion(c0, target[:, 0]) + \
                criterion(c1, target[:, 1]) + \
                criterion(c2, target[:, 2]) + \
                criterion(c3, target[:, 3]) + \
                criterion(c4, target[:, 4])
        
        # loss /= 6
        #訓練神經網絡的時候，使用loss.backward()來反向傳遞修正，修正之後的結果保存在.grad中，因此每輪迭代執行loss.backward()的時候要先對.grad清零
        optimizer.zero_grad()
        loss.backward()
        optimizer.step()
        
        train_loss.append(loss.item())
    return np.mean(train_loss)

def validate(val_loader, model, criterion):
    # 切換模型爲預測模型
    model.eval()
    val_loss = []

    # 不記錄模型梯度信息
    with torch.no_grad():
        for i, (input, target) in enumerate(val_loader):
            if use_cuda:
                input = input.cuda()
                target = target.cuda()
            
            c0, c1, c2, c3, c4 = model(input)
            loss = criterion(c0, target[:, 0]) + \
                    criterion(c1, target[:, 1]) + \
                    criterion(c2, target[:, 2]) + \
                    criterion(c3, target[:, 3]) + \
                    criterion(c4, target[:, 4])
            # loss /= 6
            val_loss.append(loss.item())
    return np.mean(val_loss)

def predict(test_loader, model, tta=10):
    model.eval()
    test_pred_tta = None
    
    # TTA 次數
    for _ in range(tta):
        test_pred = []
    
        with torch.no_grad():
            for i, (input, target) in enumerate(test_loader):
                if use_cuda:
                    input = input.cuda()
                
                c0, c1, c2, c3, c4 = model(input)
                if use_cuda:
                    output = np.concatenate([
                        c0.data.cpu().numpy(), 
                        c1.data.cpu().numpy(),
                        c2.data.cpu().numpy(), 
                        c3.data.cpu().numpy(),
                        c4.data.cpu().numpy()], axis=1)
                else:
                    output = np.concatenate([
                        c0.data.numpy(), 
                        c1.data.numpy(),
                        c2.data.numpy(), 
                        c3.data.numpy(),
                        c4.data.numpy()], axis=1)
                
                test_pred.append(output)
        
        test_pred = np.vstack(test_pred)
        if test_pred_tta is None:
            test_pred_tta = test_pred
        else:
            test_pred_tta += test_pred
    
    return test_pred_tta
model = SVHN_Model1()
#損失函數
criterion = nn.CrossEntropyLoss()
#優化器
optimizer = torch.optim.Adam(model.parameters(), 0.001)
best_loss = 1000.0

use_cuda = True#使用GPU加速
if use_cuda:
    model = model.cuda()

for epoch in range(20):#迭代20次
    train_loss = train(train_loader, model, criterion, optimizer, epoch)
    val_loss = validate(val_loader, model, criterion)
    
    val_label = [''.join(map(str, x)) for x in val_loader.dataset.img_label]
    val_predict_label = predict(val_loader, model, 1)
    val_predict_label = np.vstack([
        val_predict_label[:, :11].argmax(1),
        val_predict_label[:, 11:22].argmax(1),
        val_predict_label[:, 22:33].argmax(1),
        val_predict_label[:, 33:44].argmax(1),
        val_predict_label[:, 44:55].argmax(1),
    ]).T
    val_label_pred = []
    for x in val_predict_label:
        val_label_pred.append(''.join(map(str, x[x!=10])))
    
    val_char_acc = np.mean(np.array(val_label_pred) == np.array(val_label))
    
    print('Epoch: {0}, Train loss: {1} \t Val loss: {2}'.format(epoch, train_loss, val_loss))
    print('Val Acc', val_char_acc)
    # 記錄下驗證集精度
    if val_loss < best_loss:
        best_loss = val_loss
        # print('Find better model in Epoch {0}, saving model.'.format(epoch))
        torch.save(model.state_dict(), '/model.pt')