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
上一篇: 最快捷方便的python安装库方法(适用于初学者)
下一篇: python之进程学习(二)