caffe fcn训练自己数据集_YOLOv5 配置、训练(自己的数据集)、推理及违规检测样例实现...

1. 环境搭建

git clone https://github.com/ultralytics/yolov5  # clone repo
cd yolov5
pip install -r requirements.txt  # install dependencies

反注释requirements.txt中的# onnx>=1.8.0或者自己安装pip install onnx

2. 训练自己的数据集

• 数据集格式

——data
————Annotations           # 保存Voc数据格式的xml文件
————ImageSets
——————Main              # 保存数据集分割后的txt文件
————images                # 保存图像文件

1）执行split_train_val.py，将数据分割为训练集和验证集(保存在Main/train.txt,Main/test.txt)

import os
import random
 
trainval_percent = 0.2   #可自行进行调节
train_percent = 1
xmlfilepath = 'Annotations'
txtsavepath = 'ImageSetsMain'
total_xml = os.listdir(xmlfilepath)
 
num = len(total_xml)
list = range(num)
tv = int(num * trainval_percent)
tr = int(tv * train_percent)
trainval = random.sample(list, tv)
train = random.sample(trainval, tr)
 
#ftrainval = open('ImageSets/Main/trainval.txt', 'w')
ftest = open('ImageSets/Main/test.txt', 'w')
ftrain = open('ImageSets/Main/train.txt', 'w')
#fval = open('ImageSets/Main/val.txt', 'w')
 
for i in list:
    name = total_xml[i][:-4] + 'n'
    if i in trainval:
        #ftrainval.write(name)
        if i in train:
            ftest.write(name)
        #else:
            #fval.write(name)
    else:
        ftrain.write(name)
 
#ftrainval.close()
ftrain.close()
#fval.close()
ftest.close()

2）执行voc_label.py生成标签文件（class x_center y_center width height）

# -*- coding: utf-8 -*-

import xml.etree.ElementTree as ET
import pickle
import os
from os import listdir, getcwd
from os.path import join
 
sets = ['train', 'test']
classes = ["mask","nomask&