Ubuntu16.04下实现darknet-yolov3训练自己的数据（含loss图、mAP计算）

记录一下本地编译darknet并用自己的数据集来训练yolov3的过程，最后补充了mAP的计算方法。

1.环境配置

首先CUDA和Cudnn是必备的，安装有很多教程就不多写了，opencv安装比较麻烦可以不用装

2.本地编译darknet

从github获取darknet

git clone https://github.com/pjreddie/darknet
cd darknet

修改Makefile文件

GPU=1 #如果使用GPU设置为1，CPU设置为0
CUDNN=1  #如果使用CUDNN设置为1，否则为0
OPENCV=0 #如果调用摄像头，还需要设置OPENCV为1，否则为0
OPENMP=0  #如果使用OPENMP设置为1，否则为0
DEBUG=0  #如果使用DEBUG设置为1，否则为0

在darknet文件夹下编译

make

下载yolov3的预训练模型

wget https://pjreddie.com/media/files/yolov3.weights

测试是否编译成功

./darknet detector test cfg/coco.data cfg/yolov3.cfg yolov3.weights data/dog.jpg

3.准备数据集

一般是先准备VOC格式的数据集，然后通过一些脚本文件转化成可用于训练的版本

在darknet文件夹下创建dateset文件夹，内部结构为：

dataset
  ---JPEGImages#存放原图像（名字只要和xml对应就行，不用规范化）
 
  ---Annotations#存放图像对应的xml文件
 
  ---ImageSets/Main # 存放训练/验证图像的txt文件（脚本生成）

将图像数据放入JPEGImages，xml的标注文件放入Annotations，然后新建一个py文件，随便命名（如：maketxt.py）

import os
import random

trainval_percent = 0.1
train_percent = 0.9
xmlfilepath = 'Annotations'
txtsavepath = 'ImageSets\Main'
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()

运行后会在ImageSets/Main路径下生成train.txt,val.txt,test.txt和trainval.txt四个必备的txt文件

转换VOC格式的数据集为darknet的格式（点坐标进行归一化https://blog.csdn.net/hesongzefairy/article/details/104443573）

在darknet文件夹中创建一个py文件，随便命名，需要修改的地方看注释（修改自darknet/scripts/voc_label.py）

import xml.etree.ElementTree as ET
import pickle
import os
from os import listdir, getcwd
from os.path import join
 
#源代码sets=[('2012', 'train'), ('2012', 'val'), ('2007', 'train'), ('2007', 'val'), ('2007', 'test')]
sets=[('dataset', 'train')]  # 改成自己建立的文件夹名字，若生成测试的train改成test
 
classes = ["person", "car"] # 改成自己的类别，和fastrcnn系不同，不用+1
 
def convert(size, box):
    dw = 1./(size[0])
    dh = 1./(size[1])
    x = (box[0] + box[1])/2.0 - 1
    y = (box[2] + box[3])/2.0 - 1
    w = box[1] - box[0]
    h = box[3] - box[2]
    x = x*dw
    w = w*dw
    y = y*dh
    h = h*dh
    return (x,y,w,h)
 
def convert_annotation(year, image_id):
    in_file = open('myData/Annotations/%s.xml'%(image_id))  VOCdevkit/VOC%s/Annotations/%s.xml
    out_file = open('myData/labels/%s.txt'%(image_id), 'w')  VOCdevkit/VOC%s/labels/%s.txt
    tree=ET.parse(in_file)
    root = tree.getroot()
    size = root.find('size')
    w = int(size.find('width').text)
    h = int(size.find('height').text)
 
    for obj in root.iter('object'):
        difficult = obj.find('difficult').text
        cls = obj.find('name').text
        if cls not in classes or int(difficult)==1:
            continue
        cls_id = classes.index(cls)
        xmlbox = obj.find('bndbox')
        b = (float(xmlbox.find('xmin').text), float(xmlbox.find('xmax').text), float(xmlbox.find('ymin').text), float(xmlbox.find('ymax').text))
        bb = convert((w,h), b)
        out_file.write(str(cls_id) + " " + " ".join([str(a) for a in bb]) + '\n')
 
# wd = getcwd()
 
# for year, image_set in sets:
#    if not os.path.exists('/labels/'):  # 改成自己建立的myData
#       os.makedirs('myData/labels/')
#    image_ids = open('myData/ImageSets/Main/%s.txt'%(image_set)).read().strip().split()
#    list_file = open('myData/%s_%s.txt'%(year, image_set), 'w')
#    for image_id in image_ids:
#        list_file.write('%s/myData/JPEGImages/%s.jpg\n'%(wd, image_id))
#        convert_annotation(year, image_id)
#    list_file.close()

运行之后，会在dataset文件夹中生成dataset_train.txt（记录了训练数据的绝对路径）

4.修改配置文件

修改cfg/voc.data

classes= 2 #改为自己的分类个数

train  = /home/XXX/darknet/dataset/dataset_train.txt # 记录绝对路径的txt
names = /home/XXX/darknet/dataset/myData.names       # 自己创建，记录类别名称
backup = /home/XXX/darknet/dataset/weights           # 权重保存路径

修改cfg/yolov3-voc.cfg

通过vim打开，用/yolo搜索

对每个yolo搜索点上的conv层，修改filter为3*（5+len（classes）），yolo层修改classes即可

同时文件最上部分可修改一些训练参数

# Testing            ### 测试模式                                          
# batch=1
# subdivisions=1
# Training           ### 训练模式，每次前向的图片数目 = batch/subdivisions 
batch=64
subdivisions=16
width=416            ### 网络的输入宽、高、通道数
height=416
channels=3
momentum=0.9         ### 动量 
decay=0.0005         ### 权重衰减
angle=0
saturation = 1.5     ### 饱和度
exposure = 1.5       ### 曝光度 
hue=.1               ### 色调
learning_rate=0.001  ### 学习率 
burn_in=1000         ### 学习率控制的参数
max_batches = 50200  ### 迭代次数                                          
policy=steps         ### 学习率策略 
steps=40000,45000    ### 学习率变动步长

5.开始训练

准备darknet权重

wget https://pjreddie.com/media/files/darknet53.conv.74

启动训练（指定gpu）

./darknet detector train cfg/voc.data cfg/yolov3-voc.cfg darknet53.conv.74 -gpu 1

启动训练（保存训练log，用于后续画图）

./darknet detector train cfg/voc.data cfg/yolov3-voc.cfg darknet53.conv.74 -gpu 1 2>&1 | tee logs/train_yolov3.log

从停止处重新训练

./darknet detector train cfg/voc.data cfg/yolov3-voc.cfg darknet53.conv.74 -gups 0 myData/weights/my_yolov3.backup

6.训练完成后加载log文件画loss图和iou图

# coding=utf-8
import os
import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
import logging
 
logging.basicConfig(
    level=logging.DEBUG,
    format='%(asctime)s %(levelname)s: %(message)s',
    datefmt='%Y-%m-%d %H:%M:%S'
)
logger = logging.getLogger(__name__)
 
 
class Yolov3LogVisualization:
 
    def __init__(self, log_path, result_dir):
 
        self.log_path = log_path
        self.result_dir = result_dir
 
    def extract_log(self, save_log_path, key_word):
        with open(self.log_path, 'r') as f:
            with open(save_log_path, 'w') as train_log:
                next_skip = False
                for line in f:
                    if next_skip:
                        next_skip = False
                        continue
                    # 去除多gpu的同步log
                    if 'Syncing' in line:
                        continue
                    # 去除除零错误的log
                    if 'nan' in line:
                        continue
                    if 'Saving weights to' in line:
                        next_skip = True
                        continue
                    if key_word in line:
                        train_log.write(line)
        f.close()
        train_log.close()
 
    def parse_loss_log(self, log_path, line_num=2000):
        # 用于设置忽略前多少步，上千几百的太大了，所以从几一下开始。 
        result = pd.read_csv(log_path,skiprows=[x for x in range(line_num) if (x<1500)],
                             error_bad_lines=False, names=['loss', 'avg', 'rate', 'seconds', 'images'])
        result['loss'] = result['loss'].str.split(' ').str.get(1)
        result['avg'] = result['avg'].str.split(' ').str.get(1)
        result['rate'] = result['rate'].str.split(' ').str.get(1)
        result['seconds'] = result['seconds'].str.split(' ').str.get(1)
        result['images'] = result['images'].str.split(' ').str.get(1)
 
        result['loss'] = pd.to_numeric(result['loss'])
        result['avg'] = pd.to_numeric(result['avg'])
        result['rate'] = pd.to_numeric(result['rate'])
        result['seconds'] = pd.to_numeric(result['seconds'])
        result['images'] = pd.to_numeric(result['images'])
        return result
 
    def gene_loss_pic(self, pd_loss):
        fig = plt.figure()
        ax = fig.add_subplot(1, 1, 1)
        ax.plot(pd_loss['avg'].values, label='avg_loss')
        ax.legend(loc='best')
        ax.set_title('The loss curves')
        ax.set_xlabel('batches')
        fig.savefig(self.result_dir + '/avg_loss')
        logger.info('save iou loss done')
 
    def loss_pic(self):
        train_log_loss_path = os.path.join(self.result_dir, 'train_log_loss.txt')
        self.extract_log(train_log_loss_path, 'images')
        pd_loss = self.parse_loss_log(train_log_loss_path)
        self.gene_loss_pic(pd_loss)
 
    def parse_iou_log(self, log_path, line_num=2000):
        result = pd.read_csv(log_path, skiprows=[x for x in range(line_num) if (x % 10 == 0 or x % 10 == 9)],
                             error_bad_lines=False,
                             names=['Region Avg IOU', 'Class', 'Obj', 'No Obj', 'Avg Recall', 'count'])
        result['Region Avg IOU'] = result['Region Avg IOU'].str.split(': ').str.get(1)
        result['Class'] = result['Class'].str.split(': ').str.get(1)
        result['Obj'] = result['Obj'].str.split(': ').str.get(1)
        result['No Obj'] = result['No Obj'].str.split(': ').str.get(1)
        result['Avg Recall'] = result['Avg Recall'].str.split(': ').str.get(1)
        result['count'] = result['count'].str.split(': ').str.get(1)
 
        result['Region Avg IOU'] = pd.to_numeric(result['Region Avg IOU'])
        result['Class'] = pd.to_numeric(result['Class'])
        result['Obj'] = pd.to_numeric(result['Obj'])
        result['No Obj'] = pd.to_numeric(result['No Obj'])
        result['Avg Recall'] = pd.to_numeric(result['Avg Recall'])
        result['count'] = pd.to_numeric(result['count'])
        return result
 
    def gene_iou_pic(self, pd_loss):
        fig = plt.figure()
        ax = fig.add_subplot(1, 1, 1)
        ax.plot(pd_loss['Region Avg IOU'].values, label='Region Avg IOU')
        # ax.plot(result['Class'].values,label='Class')
        # ax.plot(result['Obj'].values,label='Obj')
        # ax.plot(result['No Obj'].values,label='No Obj')
        # ax.plot(result['Avg Recall'].values,label='Avg Recall')
        # ax.plot(result['count'].values,label='count')
        ax.legend(loc='best')
        ax.set_title('The Region Avg IOU curves')
        ax.set_xlabel('batches')
        fig.savefig(self.result_dir + '/region_avg_iou')
        logger.info('save iou pic done')
 
    def iou_pic(self):
        train_log_loss_path = os.path.join(self.result_dir, 'train_log_iou.txt')
        self.extract_log(train_log_loss_path, 'IOU')
        pd_loss = self.parse_iou_log(train_log_loss_path)
        self.gene_iou_pic(pd_loss)
 
 
if __name__ == '__main__':
    log_path = '/home/studieren/论文/darknet/log_analysis/train_yolov3.log'
    result_dir = '/home/studieren/论文/darknet/log_analysis'
    logVis = Yolov3LogVisualization(log_path, result_dir)
    logVis.loss_pic()
    logVis.iou_pic()

7.mAP计算

参考方法https://blog.csdn.net/Gentleman_Qin/article/details/84800188

这个代码运行需要python2.7，但是现在都是python3了，谁还用2

需要修改的地方：

1. print的用法，注释掉或者修改成python3格式都可以

2. 读写文件的方法，open仅用r或者w会报错，改成rb和wb（readline的位置不要改）

具体的根据报错来修改一下就行了，最终会输出AP值

 

本文地址：https://blog.csdn.net/hesongzefairy/article/details/107183162