采用u版的pytorchyolo3源码训练自己的数据集
最近一直在研究目标检测这一块的内容。
在导师的建议下学习了yolov3目标检测算法，想着既然学完了就要跑一边看看是啥样子的说干就干。
本文采用的源码为https://github.com/ultralytics/yolov3的版本
由于使用电脑的gpu内存有限，本文运行的为yolov3-tiny
Cython
matplotlib>=3.2.2
numpy>=1.18.5
opencv-python>=4.1.2
Pillow
PyYAML>=5.3
scipy>=1.4.1
tensorboard>=2.2
torch>=1.7.0（笔者为1.6.0也可以跑）
torchvision>=0.8.1
tqdm>=4.41.0
没有对应环境的pip安装一下就完事了
制作数据集方面可以采用labelimg标注工具对自己的图像进行标注，安装包下载地址为：github:https://github.com/tzutalin/labelImg
安装依赖库
pip install PyQt5
pip install PyQt5_tools
pip install lxml
下载完成之后在文件目录中输入cmd进入解压后的文件路径
执行命令
pyrcc5 -o resources.py resources.qrc
python labelImg.py
即可完成安装。
标注生成的将xml文件放置在Annotations文件夹之中，图片文件放置在images文件之中
在数据方面我直接从coco数据集之中提取了一类bicycle，来作为数据集
在https://github.com/ultralytics/yolov3将代码下载下来并解压。采用pycharm打开之后大致的框架如下!
装载数据：我们首先将Annotations和images文件夹复制到data文件夹下，同时在data文件夹下新建2个文件夹，分别命名为ImageSets和labels。
然后在工程目录之下建立一个新的python文件makeTxt.py，代码如下
import os
import random
trainval_percent = 0.2 # 可自行进行调节
train_percent = 1
xmlfilepath = 'data/annotations'
txtsavepath = 'data/images'
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('data/ImageSets/test.txt', 'w')
ftrain = open('data/ImageSets/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()
然后再建立voc_label.py
#!/usr/bin/env python
# -*- 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 = ['bicycle'] # 自己训练的类别
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()
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()
分别运行makeTxt.py和voc_label.py
运行makeTxt.py后会在ImagesSets文件下生成2个文件，如下图
运行voc_label.py后labels后，会在labels文件夹之中生成图片的标签文件
其中0就是对应的标签，后面的4个数字就是标签的位置。
接下来你还要配置2个文件，在data文件下新建bicycle.data文件配置内容如下
classes=1
train=data/train.txt
valid=data/test.txt
names=data/bicycle.names
backup=backup/
eval=coco
再在data文件下新建bicycle.names文件，配置内容如下：
bicycle
修改cfg文件
其实在u版本的cfg文件夹之中有对应的yolov3-tiny3-1cls.cfg有的话就不用管了没有的话就直接复制下面的代码
[net]
# Testing
batch=1
subdivisions=1
# Training
# batch=64
# subdivisions=2
width=416
height=416
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=16
size=3
stride=1
pad=1
activation=leaky
[maxpool]
size=2
stride=2
[convolutional]
batch_normalize=1
filters=32
size=3
stride=1
pad=1
activation=leaky
[maxpool]
size=2
stride=2
[convolutional]
batch_normalize=1
filters=64
size=3
stride=1
pad=1
activation=leaky
[maxpool]
size=2
stride=2
[convolutional]
batch_normalize=1
filters=128
size=3
stride=1
pad=1
activation=leaky
[maxpool]
size=2
stride=2
[convolutional]
batch_normalize=1
filters=256
size=3
stride=1
pad=1
activation=leaky
[maxpool]
size=2
stride=2
[convolutional]
batch_normalize=1
filters=512
size=3
stride=1
pad=1
activation=leaky
[maxpool]
size=2
stride=1
[convolutional]
batch_normalize=1
filters=1024
size=3
stride=1
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
[convolutional]
size=1
stride=1
pad=1
filters=18
activation=linear
[yolo]
mask = 3,4,5
anchors = 10,14, 23,27, 37,58, 81,82, 135,169, 344,319
classes=1
num=6
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, 8
[convolutional]
batch_normalize=1
filters=256
size=3
stride=1
pad=1
activation=leaky
[convolutional]
size=1
stride=1
pad=1
filters=18
activation=linear
[yolo]
mask = 0,1,2
anchors = 10,14, 23,27, 37,58, 81,82, 135,169, 344,319
classes=1
num=6
jitter=.3
ignore_thresh = .7
truth_thresh = 1
random=1
这个是针对单个类别目标检测的，如果是多个类别还需修改其中的filters参数（改为3*（类别数+4+1））将classes改为对应的类别数。最后需要下载yolov3-tiny.weights文件，并且将对应的文件放置在weights文件夹下。
在pycharm的Terminal（终端）运行
python train.py --data data/bicycle.data --cfg cfg/yolov3-tiny-1cls.cfg --epochs 10
#后面的epochs自行更改