基于卷积神经网络的交通标志识别(pytorch，opencv，yolov5)

文章目录

数据集介绍：
resnet18模型代码
加载数据集（Dataset与Dataloader）
模型训练
训练准确率及损失函数：
resnet18交通标志分类源码
yolov5检测与识别（交通标志）

本文共包含两部分，
第一部分是用resnet18对交通标志分类，仅仅只是交通标志分类
文末附有yolov5和resnet18结合的源码，yolov5复制检测交通标志位置，然后使用resnet18对交通标志进行分类。

数据集介绍：

本文使用的数据集共有6000多张，共包含58个类别。部分数据集如下：

在这里插入图片描述

resnet18模型代码

使用pytorch自带的resnet18模型，代码如下：

from torchvision import models
import torch.nn as nn

#加载resnet18模型
net=models.resnet18(weights=None)
#因为分类个数为58，所以需要修改模型最后一层全连接层
net.fc=nn.Linear(in_features=512, out_features=58, bias=True)
# print(net)

加载数据集（Dataset与Dataloader）

from torch.utils.data import Dataset,DataLoader
import numpy as np
import cv2
import imgaug.augmenters as iaa
from imgaug.augmentables.segmaps import SegmentationMapsOnImage
from PIL import Image
import os
from torchvision import transforms
import torch
import random

a=[]
class Mydata(Dataset):
    def __init__(self,lines,train=True):
        super(Mydata, self).__init__()
        self.lines=lines
        random.shuffle(self.lines)
        self.train=train


    def __len__(self):
        return len(self.lines)
    def __getitem__(self, index):

        txts=self.lines[index].strip().split(';')
        src_path='pic/'+txts[0]
        w=int(txts[1])
        h=int(txts[2])
        x1=int(txts[3])
        y1=int(txts[4])
        x2=int(txts[5])
        y2=int(txts[6])

        new_x1=random.randint(0,x1)
        new_y1=random.randint(0,y1)
        new_x2=random.randint(x2,w-1)
        new_y2=random.randint(y2,h-1)

        lab=int(txts[7])
        # if lab in a:
        #     pass
        # else:a.append(lab)
        #
        # a.sort()
        # print(len(a))
        # print(a)
        img = Image.open(src_path)
        img=np.array(img)[...,:3]
        img=img[new_y1:new_y2,new_x1:new_x2]


        #数据增强
        if self.train:
            img=self.get_random_data(img)
        else:
            img = cv2.resize(img, (128, 128))
        # cv2.imshow('img',img[...,::-1])
        # cv2.waitKey(0)

        #归一化
        img=(img/255.0).astype('float32')
        img=np.transpose(img,(2,0,1))

        img=torch.from_numpy(img)
        return img,lab
    def get_random_data(self,img):
        seq = iaa.Sequential([
            # iaa.Flipud(0.5),  # flip up and down (vertical)
            # iaa.Fliplr(0.5),  # flip left and right (horizontal)
            iaa.Multiply((0.8, 1.2)),  # change brightness, doesn't affect BBs(bounding boxes)
            iaa.GaussianBlur(sigma=(0, 1.0)),  # 标准差为0到3之间的值

            iaa.Crop(percent=(0, 0.2)),
            iaa.Affine(
                translate_px={"x": (0,15), "y": (0,15)},  # 平移
                scale=(0.8, 1.2),  # 尺度变换
                rotate=(-20, 20),
                mode='constant',
                cval=(125)
                ),
            iaa.Resize(128)
        ])

        img= seq(image=img)
        return img
if __name__ == '__main__':
    lines=open('data.txt','r').readlines()
    my=Mydata(lines=lines,train=True)
    myloader=DataLoader(dataset=my,batch_size=3,shuffle=False)

    for i,j in myloader:
        print(i.shape,j.shape)

模型训练

经过60个epoch训练后，模型准确率基本上达到百分百

from mymodel import net
from myDataset import Mydata
import random
from torch.utils.data import DataLoader
import torch.nn as nn
import torch.optim as optim
import torch
from tqdm import tqdm
import matplotlib.pylab as plt

batch_size=32
Epoch=60
lr=0.001

lines=open('data.txt','r').readlines()
random.shuffle(lines)
val_lines=random.sample(lines,int(len(lines)*0.1))
train_lines=list(set(lines)-set(val_lines))


train_data=Mydata(lines=train_lines)
val_data=Mydata(lines=val_lines,train=False)
train_loader=DataLoader(dataset=train_data,batch_size=batch_size,shuffle=True)
val_loader=DataLoader(dataset=val_data,batch_size=batch_size,shuffle=False)

num_train   = len(train_lines)
epoch_step  = num_train // batch_size
BCE_loss     = nn.CrossEntropyLoss()
optimizer  = optim.Adam(net.parameters(), lr=lr, betas=(0.5, 0.999))
lr_scheduler  = optim.lr_scheduler.StepLR(optimizer, step_size=1, gamma=0.99)
#获取学习率函数
def get_lr(optimizer):
    for param_group in optimizer.param_groups:
        return param_group['lr']
#计算准确率函数
def metric_func(pred,lab):
    _,index=torch.max(pred,dim=-1)
    acc=torch.where(index==lab,1.,0.).mean()
    return acc
device=torch.device('cuda:0' if torch.cuda.is_available() else 'cpu')
net=net.to(device)
#设置损失函数
loss_fun     = nn.CrossEntropyLoss()

if __name__ == '__main__':

    T_acc=[]
    V_acc=[]
    T_loss=[]
    V_loss=[]

    # 设置迭代次数200次
    epoch_step = num_train // batch_size
    for epoch in range(1, Epoch + 1):
        net.train()

        total_loss = 0
        loss_sum = 0.0
        train_acc_sum=0.0

        with tqdm(total=epoch_step, desc=f'Epoch {epoch}/{Epoch}', postfix=dict, mininterval=0.3) as pbar:
            for step, (features, labels) in enumerate(train_loader, 1):
                features = features.to(device)
                labels = labels.to(device)
                batch_size = labels.size()[0]

                optimizer.zero_grad()
                predictions = net(features)
                loss = loss_fun(predictions, labels)
                loss.backward()
                optimizer.step()
                total_loss += loss
                train_acc = metric_func(predictions, labels)
                train_acc_sum+=train_acc
                pbar.set_postfix(**{'loss': total_loss.item() / (step),
                                    "acc":train_acc_sum.item()/(step),
                                    'lr': get_lr(optimizer)})
                pbar.update(1)
        T_acc.append(train_acc_sum.item()/(step))
        T_loss.append(total_loss.item() / (step))
        # 验证
        net.eval()
        val_acc_sum = 0
        val_loss_sum=0
        for val_step, (features, labels) in enumerate(val_loader, 1):
            with torch.no_grad():
                features = features.to(device)
                labels = labels.to(device)
                predictions = net(features)

                val_metric = metric_func(predictions, labels)
                loss=loss_fun(predictions,labels)
            val_acc_sum += val_metric.item()
            val_loss_sum+=loss.item()
        print('val_acc=%.4f' % (val_acc_sum / val_step))
        V_acc.append(round(val_acc_sum / val_step,2))
        V_loss.append(val_loss_sum/val_step)

        # 保存模型
        if (epoch) % 2 == 0:
            torch.save(net.state_dict(), 'logs/Epoch%d-Loss%.4f_.pth' % (
                epoch, total_loss / (epoch_step + 1)))

        lr_scheduler.step()

    plt.figure()
    plt.plot(T_acc,'r')
    plt.plot(V_acc,'b')
    plt.title('Training and validation Acc')
    plt.xlabel("Epochs")
    plt.ylabel("Acc")
    plt.legend(["Train_acc", "Val_acc"])
    # plt.show()
    plt.savefig("ACC.png")

    plt.figure()
    plt.plot(T_loss, 'r')
    plt.plot(V_loss, 'b')
    plt.title('Training and validation loss')
    plt.xlabel("Epochs")
    plt.ylabel("loss")
    plt.legend(["Train_loss", "Val_loss"])

    plt.savefig("LOSS.png")
    plt.show()