背景
源码克隆于https://github.com/ultralytic...(现在最新版本cfg文件夹删了，我给的是以前的版本链接)，刚克隆下来训练自己的数据集有点无从下手，看其github源码主页提供的教程也是摸不着头脑，研究了两天搞定，记录一下，希望可以帮助到和我相同情况的小伙伴，觉得有用的话可以点赞收藏一下，有错误评论区指正！另外介绍下我是mac作为本地电脑，在有4块gpu的服务器上远程训练的。
1. 克隆yolov3源码，准备自己数据集，准备预训练权重文件
这里使用voc数据集，记得解压到你想放的位置
wget -c http://host.robots.ox.ac.uk/pascal/VOC/voc2012/VOCtrainval_11-May-2012.tar预训练权重文件下载
wget -c https://pjreddie.com/media/files/darknet53.conv.74我是直接把它解压至项目根目录下的，你们可以自己决定路径，但是后面会有些代码部分需要相应修改对应此路径。
get_train_val_txt.py(脚本代码如下，自行拷贝，并适当修改)
import os
import random
random.seed(0)
xmlfilepath=r'./VOC2012/Annotations' # 改成你自己的Annotations路径
saveBasePath=r"./VOC2012/ImageSets/Main/" # 改成你自己的ImageSets/Main路径
# 值可以自己取，决定你各个数据集的占比数
trainval_percent=.8
train_percent=.7
temp_xml = os.listdir(xmlfilepath)
total_xml = []
for xml in temp_xml:
if xml.endswith(".xml"):
total_xml.append(xml)
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(os.path.join(saveBasePath,'trainval.txt'), 'w')
ftest = open(os.path.join(saveBasePath,'test.txt'), 'w')
ftrain = open(os.path.join(saveBasePath,'train.txt'), 'w')
fval = open(os.path.join(saveBasePath,'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() 3. 在data文件夹里新建两个文件
新建voc2012.data文件，里面配置如下
classes=20 # 改成你数据集总共的类别
train=data/train.txt
valid=data/val.txt
names=data/voc2012.names
backup=backup/新建voc2012.names文件，因为我是voc数据集，所以配置如下，你需要改成你自己数据集的类别名字
person
bird
cat
cow
dog
horse
sheep
aeroplane
bicycle
boat
bus
car
motorbike
train
bottle
chair
diningtable
pottedplant
sofa
tvmonitor4. 新建voc_label.py脚本
# -*- coding: utf-8 -*-
"""
需要修改的地方：
1. sets中替换为自己的数据集
2. classes中替换为自己的类别
"""
import xml.etree.ElementTree as ET
import pickle
import os
from os import listdir, getcwd
from os.path import join
sets = [('2012','train'), ('2012','test'),('2012','val')] #替换为自己的数据集,格式[(year,image_id)]
classes = ["aeroplane", "bicycle", "bird", "boat", "bottle", "bus", "car", "cat", "chair", "cow", "diningtable", "dog", "horse", "motorbike", "person", "pottedplant", "sheep", "sofa", "train", "tvmonitor"] #修改为自己的类别名称
# 转化为yolov3的数据格式提供的方法
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)
# 根据annotation的文件转换成yolov3数据格式
def convert_annotation(year, image_id):
in_file = open('VOC%s/Annotations/%s.xml'%(year, image_id)) # 改成自己annotation的xml文件位置
out_file = open('VOC%s/labels/%s.txt'%(year, image_id), 'w') # 存生成labels文件夹的路径，根据自己情况修改，我是打算存在./VOC2012/labels
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()
# 下面代码路径要相应你自己的数据集存放路径、labels存放路径去修改
for year,image_set in sets:
if not os.path.exists('VOC%s/labels/'%(year)):
os.makedirs('VOC%s/labels/'%(year))
image_ids = open('VOC%s/ImageSets/Main/%s.txt'%(year, image_set)).read().strip().split()
list_file = open('data/%s.txt'%(image_set), 'w')
for image_id in image_ids:
list_file.write('VOC%s/JPEGImages/%s.jpg\n'%(year, image_id))
convert_annotation(year, image_id)
list_file.close() 运行该脚本，就会在我设定的VOC2012/lables下生成各个图片对应的txt文件
因为我的labels里的txt文件路径是在VOC2012/labels/下的，我的图片文件是在VOC2012/JPEGImages/下的，所以应该是把JPEGImages替换成labels
6. 修改网络配置文件yolov3.cfg
主要修改这几个地方：
如果你有gpu，就像我一样修改
batch=64
subdivisions=16没有就都是1这两项
在在该文件搜索classes，一共有三处，数值都修改成你数据集里的类别总数，并把classes所在层的上一层的[convolutional]网络的filters修改，修改值按此公式计算：$(classes+5)*3$，我把自己的cfg文件贴在下面
[net]
# Testing
#batch=1
#subdivisions=1
# Training
batch=64
subdivisions=16
width=608
height=608
channels=3
momentum=0.9
decay=0.0005
angle=0
saturation = 1.5
exposure = 1.5
hue=.1
learning_rate=0.001
burn_in=1000
max_batches = 500200
policy=steps
steps=400000,450000
scales=.1,.1
[convolutional]
batch_normalize=1
filters=32
size=3
stride=1
pad=1
activation=leaky
# Downsample
[convolutional]
batch_normalize=1
filters=64
size=3
stride=2
pad=1
activation=leaky
[convolutional]
batch_normalize=1
filters=32
size=1
stride=1
pad=1
activation=leaky
[convolutional]
batch_normalize=1
filters=64
size=3
stride=1
pad=1
activation=leaky
[shortcut]
from=-3
activation=linear
# Downsample
[convolutional]
batch_normalize=1
filters=128
size=3
stride=2
pad=1
activation=leaky
[convolutional]
batch_normalize=1
filters=64
size=1
stride=1
pad=1
activation=leaky
[convolutional]
batch_normalize=1
filters=128
size=3
stride=1
pad=1
activation=leaky
[shortcut]
from=-3
activation=linear
[convolutional]
batch_normalize=1
filters=64
size=1
stride=1
pad=1
activation=leaky
[convolutional]
batch_normalize=1
filters=128
size=3
stride=1
pad=1
activation=leaky
[shortcut]
from=-3
activation=linear
# Downsample
[convolutional]
batch_normalize=1
filters=256
size=3
stride=2
pad=1
activation=leaky
[convolutional]
batch_normalize=1
filters=128
size=1
stride=1
pad=1
activation=leaky
[convolutional]
batch_normalize=1
filters=256
size=3
stride=1
pad=1
activation=leaky
[shortcut]
from=-3
activation=linear
[convolutional]
batch_normalize=1
filters=128
size=1
stride=1
pad=1
activation=leaky
[convolutional]
batch_normalize=1
filters=256
size=3
stride=1
pad=1
activation=leaky
[shortcut]
from=-3
activation=linear
[convolutional]
batch_normalize=1
filters=128
size=1
stride=1
pad=1
activation=leaky
[convolutional]
batch_normalize=1
filters=256
size=3
stride=1
pad=1
activation=leaky
[shortcut]
from=-3
activation=linear
[convolutional]
batch_normalize=1
filters=128
size=1
stride=1
pad=1
activation=leaky
[convolutional]
batch_normalize=1
filters=256
size=3
stride=1
pad=1
activation=leaky
[shortcut]
from=-3
activation=linear
[convolutional]
batch_normalize=1
filters=128
size=1
stride=1
pad=1
activation=leaky
[convolutional]
batch_normalize=1
filters=256
size=3
stride=1
pad=1
activation=leaky
[shortcut]
from=-3
activation=linear
[convolutional]
batch_normalize=1
filters=128
size=1
stride=1
pad=1
activation=leaky
[convolutional]
batch_normalize=1
filters=256
size=3
stride=1
pad=1
activation=leaky
[shortcut]
from=-3
activation=linear
[convolutional]
batch_normalize=1
filters=128
size=1
stride=1
pad=1
activation=leaky
[convolutional]
batch_normalize=1
filters=256
size=3
stride=1
pad=1
activation=leaky
[shortcut]
from=-3
activation=linear
[convolutional]
batch_normalize=1
filters=128
size=1
stride=1
pad=1
activation=leaky
[convolutional]
batch_normalize=1
filters=256
size=3
stride=1
pad=1
activation=leaky
[shortcut]
from=-3
activation=linear
# Downsample
[convolutional]
batch_normalize=1
filters=512
size=3
stride=2
pad=1
activation=leaky
[convolutional]
batch_normalize=1
filters=256
size=1
stride=1
pad=1
activation=leaky
[convolutional]
batch_normalize=1
filters=512
size=3
stride=1
pad=1
activation=leaky
[shortcut]
from=-3
activation=linear
[convolutional]
batch_normalize=1
filters=256
size=1
stride=1
pad=1
activation=leaky
[convolutional]
batch_normalize=1
filters=512
size=3
stride=1
pad=1
activation=leaky
[shortcut]
from=-3
activation=linear
[convolutional]
batch_normalize=1
filters=256
size=1
stride=1
pad=1
activation=leaky
[convolutional]
batch_normalize=1
filters=512
size=3
stride=1
pad=1
activation=leaky
[shortcut]
from=-3
activation=linear
[convolutional]
batch_normalize=1
filters=256
size=1
stride=1
pad=1
activation=leaky
[convolutional]
batch_normalize=1
filters=512
size=3
stride=1
pad=1
activation=leaky
[shortcut]
from=-3
activation=linear
[convolutional]
batch_normalize=1
filters=256
size=1
stride=1
pad=1
activation=leaky
[convolutional]
batch_normalize=1
filters=512
size=3
stride=1
pad=1
activation=leaky
[shortcut]
from=-3
activation=linear
[convolutional]
batch_normalize=1
filters=256
size=1
stride=1
pad=1
activation=leaky
[convolutional]
batch_normalize=1
filters=512
size=3
stride=1
pad=1
activation=leaky
[shortcut]
from=-3
activation=linear
[convolutional]
batch_normalize=1
filters=256
size=1
stride=1
pad=1
activation=leaky
[convolutional]
batch_normalize=1
filters=512
size=3
stride=1
pad=1
activation=leaky
[shortcut]
from=-3
activation=linear
[convolutional]
batch_normalize=1
filters=256
size=1
stride=1
pad=1
activation=leaky
[convolutional]
batch_normalize=1
filters=512
size=3
stride=1
pad=1
activation=leaky
[shortcut]
from=-3
activation=linear
# Downsample
[convolutional]
batch_normalize=1
filters=1024
size=3
stride=2
pad=1
activation=leaky
[convolutional]
batch_normalize=1
filters=512
size=1
stride=1
pad=1
activation=leaky
[convolutional]
batch_normalize=1
filters=1024
size=3
stride=1
pad=1
activation=leaky
[shortcut]
from=-3
activation=linear
[convolutional]
batch_normalize=1
filters=512
size=1
stride=1
pad=1
activation=leaky
[convolutional]
batch_normalize=1
filters=1024
size=3
stride=1
pad=1
activation=leaky
[shortcut]
from=-3
activation=linear
[convolutional]
batch_normalize=1
filters=512
size=1
stride=1
pad=1
activation=leaky
[convolutional]
batch_normalize=1
filters=1024
size=3
stride=1
pad=1
activation=leaky
[shortcut]
from=-3
activation=linear
[convolutional]
batch_normalize=1
filters=512
size=1
stride=1
pad=1
activation=leaky
[convolutional]
batch_normalize=1
filters=1024
size=3
stride=1
pad=1
activation=leaky
[shortcut]
from=-3
activation=linear
######################
[convolutional]
batch_normalize=1
filters=512
size=1
stride=1
pad=1
activation=leaky
[convolutional]
batch_normalize=1
size=3
stride=1
pad=1
filters=1024
activation=leaky
[convolutional]
batch_normalize=1
filters=512
size=1
stride=1
pad=1
activation=leaky
[convolutional]
batch_normalize=1
size=3
stride=1
pad=1
filters=1024
activation=leaky
[convolutional]
batch_normalize=1
filters=512
size=1
stride=1
pad=1
activation=leaky
[convolutional]
batch_normalize=1
size=3
stride=1
pad=1
filters=1024
activation=leaky
[convolutional]
size=1
stride=1
pad=1
filters=75
activation=linear
[yolo]
mask = 6,7,8
anchors = 10,13, 16,30, 33,23, 30,61, 62,45, 59,119, 116,90, 156,198, 373,326
classes=20
num=9
jitter=.3
ignore_thresh = .7
truth_thresh = 1
random=1
[route]
layers = -4
[convolutional]
batch_normalize=1
filters=256
size=1
stride=1
pad=1
activation=leaky
[upsample]
stride=2
[route]
layers = -1, 61
[convolutional]
batch_normalize=1
filters=256
size=1
stride=1
pad=1
activation=leaky
[convolutional]
batch_normalize=1
size=3
stride=1
pad=1
filters=512
activation=leaky
[convolutional]
batch_normalize=1
filters=256
size=1
stride=1
pad=1
activation=leaky
[convolutional]
batch_normalize=1
size=3
stride=1
pad=1
filters=512
activation=leaky
[convolutional]
batch_normalize=1
filters=256
size=1
stride=1
pad=1
activation=leaky
[convolutional]
batch_normalize=1
size=3
stride=1
pad=1
filters=512
activation=leaky
[convolutional]
size=1
stride=1
pad=1
filters=75
activation=linear
[yolo]
mask = 3,4,5
anchors = 10,13, 16,30, 33,23, 30,61, 62,45, 59,119, 116,90, 156,198, 373,326
classes=20
num=9
jitter=.3
ignore_thresh = .7
truth_thresh = 1
random=1
[route]
layers = -4
[convolutional]
batch_normalize=1
filters=128
size=1
stride=1
pad=1
activation=leaky
[upsample]
stride=2
[route]
layers = -1, 36
[convolutional]
batch_normalize=1
filters=128
size=1
stride=1
pad=1
activation=leaky
[convolutional]
batch_normalize=1
size=3
stride=1
pad=1
filters=256
activation=leaky
[convolutional]
batch_normalize=1
filters=128
size=1
stride=1
pad=1
activation=leaky
[convolutional]
batch_normalize=1
size=3
stride=1
pad=1
filters=256
activation=leaky
[convolutional]
batch_normalize=1
filters=128
size=1
stride=1
pad=1
activation=leaky
[convolutional]
batch_normalize=1
size=3
stride=1
pad=1
filters=256
activation=leaky
[convolutional]
size=1
stride=1
pad=1
filters=75
activation=linear
[yolo]
mask = 0,1,2
anchors = 10,13, 16,30, 33,23, 30,61, 62,45, 59,119, 116,90, 156,198, 373,326
classes=20
num=9
jitter=.3
ignore_thresh = .7
truth_thresh = 1
random=1
7. 进到yolov3文件夹，就是你自己的项目根文件夹下，运行脚本
注意运行命令中的文件路径，请根据自己的实际情况修改，--epochs迭代次数你们可自行修改
python3 train.py --data ./data/voc2012.data --cfg ./cfg/yolov3.cfg --epochs 3 --weights ./weights/darknet53.conv.74搞定！训练结果如图，我执行了三次迭代，为了示例快点有结果，另外训练好模型的权重文件存在./weights/best.pt里，如果你也是用远程服务器训练的，想在本地浏览器查看tensorboard监控面板，可以看我的另一篇博文
https://segmentfault.com/a/11...。