YOLOv4配置
需要修改配置的地方主要有三处:cfg
文件,data
文件,names
文件。
配置完后的整体目录结构
├── cfg
├── data
│ ├── Annotations
│ ├── images
│ ├── ImageSets
│ ├── JPEGImages
│ └── labels
├── images
├── models
│ └── __pycache__
├── __pycache__
├── runs
├── utils
│ └── __pycache__
└── weights
数据集准备
数据集文件夹准备
将标注好的数据Annotations和JPEGImages放入yolov4下的data目录下,并新建文件ImageSets,labels,复制JPEGImages,并进行重命名
划分训练集、验证集、测试集
在根目录
下新建makeTxt.py
,用以将数据分成训练集
,测试集
和验证集
,
import os
import random
trainval_percent = 0.9
train_percent = 0.8
xmlfilepath = ‘data/Annotations’
txtsavepath = ‘data/ImageSets’
total_xml = os.listdir(xmlfilepath)
num=len(total_xml)
list=range(num)
tv=int(numtrainval_percent)
tr=int(tvtrain_percent)
trainval= random.sample(list,tv)
train=random.sample(trainval,tr)
ftrainval = open(‘data/ImageSets/trainval.txt’, ‘w’)
ftest = open(‘data/ImageSets/test.txt’, ‘w’)
ftrain = open(‘data/ImageSets/train.txt’, ‘w’)
fval = open(‘data/ImageSets/val.txt’, ‘w’)
for i in list:
name=total_xml[i][:-4]+‘\n’
if i in trainval:
ftrainval.write(name)
if i in train:
ftrain.write(name)
else:
fval.write(name)
else:
ftest.write(name)
ftrainval.close()
ftrain.close()
fval.close()
ftest.close()
运行上述代码,在ImageSets
得到四个文件,其中我们主要关注的是train.txt
,test.txt
,val.txt
,文件里主要存储图片名称。
生成训练集、测试集
在根目录
下新建voc_label.py
,得到labels的具体内容以及data目录下的train.txt
,test.txt
,val.txt。
voc_label.py的代码如下:
# -*- 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’,‘val’]
classes = [“car”,“person”,“bird”] # 自己数据的类别
def convert(size, box):
dw = 1. / size[0]
dh = 1. / size[1]
x = (box[0] + box[1]) / 2.0
y = (box[2] + box[3]) / 2.0
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(image_id):
in_file = open(‘data/Annotations/%s.xml’ % (image_id))
out_file = open(‘data/labels/%s.txt’ % (image_id), ‘w’)
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()
print(wd)
for image_set in sets:
if not os.path.exists(‘data/labels/’):
os.makedirs(‘data/labels/’)
image_ids = open(‘data/ImageSets/%s.txt’ % (image_set)).read().strip().split()
list_file = open(‘data/%s.txt’ % (image_set), ‘w’)
for image_id in image_ids:
list_file.write(‘data/images/%s.jpg\n’ % (image_id))
convert_annotation(image_id)
list_file.close()
准备完成进行训练
python train.py --device 0 --batch-size 16 --img 640 640 --data coco.yaml --cfg cfg/yolov4.cfg --weights weights/yolov4.weights --name yolov4-pacsp