- ubuntu20.04
- cuda11.0
- cudnn8.0.4
- python3.8
- torch1.12.0
- torchvision0.11.0
(1)把yolov7克隆到本地
git clone https://github.com/WongKinYiu/yolov7.git
(2)指定格式存放数据集
在data目录下新建Annotations, images, ImageSets, labels 四个文件夹
images目录下存放数据集的图片文件
Annotations目录下存放图片的xml文件(labelImg标注)
目录结构如下所示
.
├── ./data
│ ├── ./data/Annotations
│ │ ├── ./data/Annotations/fall_0.xml
│ │ ├── ./data/Annotations/fall_1000.xml
│ │ ├── ./data/Annotations/fall_1001.xml
│ │ ├── ./data/Annotations/fall_1002.xml
│ │ ├── ./data/Annotations/fall_1003.xml
│ │ ├── ./data/Annotations/fall_1004.xml
│ │ ├── ...
│ ├── ./data/images
│ │ ├── ./data/images/fall_0.jpg
│ │ ├── ./data/images/fall_1000.jpg
│ │ ├── ./data/images/fall_1001.jpg
│ │ ├── ./data/images/fall_1002.jpg
│ │ ├── ./data/images/fall_1003.jpg
│ │ ├── ./data/images/fall_1004.jpg
│ │ ├── ...
│ ├── ./data/ImageSets
│ └── ./data/labels
│ ├── ./data/coco.yaml
│ ├── ./data/hyp.scratch.p5.yaml
│ ├── ./data/hyp.scratch.p6.yaml
│ ├── ./data/hyp.scratch.tiny.yaml
├── ./cfg
├── ./detect.py
├── ./figure
├── ./hubconf.py
├── ./inference
├── ./models
├── ./README.md
├── ....
(3)按比例划分数据集
在yolov7根目录下新建一个文件splitDataset.py
随机分配训练/验证/测试集图片,代码如下所示:
import os
import random
trainval_percent = 0.9
train_percent = 0.9
xmlfilepath = 'data/Annotations'
txtsavepath = 'data/ImageSets'
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('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()
(4)将xml文件转换成YOLO系列标准读取的txt文件
在同级目录下再新建一个文件XML2TXT.py
注意classes = [“…”]一定需要填写自己数据集的类别,在这里我是一个类别”fall”,因此classes = [“fall”],代码如下所示:
如果数据集中的类别比较多不想手敲类别的,可以使用(5)中的脚本直接获取类别,同时还能查看各个类别的数据量,如果不想可以直接跳过(5)。
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 = ['fall']
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):
'''
将对应文件名的xml文件转化为label文件,xml文件包含了对应的bunding框以及图片长款大小等信息,
通过对其解析,然后进行归一化最终读到label文件中去,也就是说
一张图片文件对应一个xml文件,然后通过解析和归一化,能够将对应的信息保存到唯一一个label文件中去
labal文件中的格式:calss x y w h 同时,一张图片对应的类别有多个,所以对应的bunding的信息也有多个
'''
in_file = open('data/Annotations/%s.xml' % (image_id), encoding='utf-8')
out_file = open('data/labels/%s.txt' % (image_id), 'w', encoding='utf-8')
tree = ET.parse(in_file)
root = tree.getroot()
size = root.find('size')
if size != None:
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))
print(image_id, cls, b)
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:
'''
对所有的文件数据集进行遍历
做了两个工作:
1.将所有图片文件都遍历一遍,并且将其所有的全路径都写在对应的txt文件中去,方便定位
2.同时对所有的图片文件进行解析和转化,将其对应的bundingbox 以及类别的信息全部解析写到label 文件中去
最后再通过直接读取文件,就能找到对应的label 信息
'''
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()
(5)查看自定义数据集标签类别及数量
在同级目录下再新建一个文件ViewCategory.py,将代码复制进去
import os
from unicodedata import name
import xml.etree.ElementTree as ET
import glob
def count_num(indir):
label_list = []
os.chdir(indir)
annotations = os.listdir('.')
annotations = glob.glob(str(annotations) + '*.xml')
dict = {}
for i, file in enumerate(annotations):
in_file = open(file, encoding='utf-8')
tree = ET.parse(in_file)
root = tree.getroot()
for obj in root.iter('object'):
name = obj.find('name').text
if (name in dict.keys()):
dict[name] += 1
else:
dict[name] = 1
print("各类标签的数量分别为:")
for key in dict.keys():
print(key + ': ' + str(dict[key]))
label_list.append(key)
print("标签类别如下:")
print(label_list)
if __name__ == '__main__':
indir = 'data/Annotations'
count_num(indir)
至此数据集的准备已经就绪,索引文件在data目录下的train.txt/val.txt/test.txt
(1)安装requirements
首先需要先利用终端进入yolov7文件夹,创建python环境,这里以Anaconda举例
cd yolov7
conda create -n yolov7 python=3.8
conda activate yolov7
pip install -r requirements.txt
(2)修改模型配置文件
进入cfg/training文件夹,选择需要训练的模型配置文件,这里选择yolov7.yaml,将其中的nc修改为自己的类别数量,这里修改为1
nc: 1
depth_multiple: 1.0
width_multiple: 1.0
anchors:
- [12,16, 19,36, 40,28]
- [36,75, 76,55, 72,146]
- [142,110, 192,243, 459,401]
backbone:
[[-1, 1, Conv, [32, 3, 1]],
[-1, 1, Conv, [64, 3, 2]],
[-1, 1, Conv, [64, 3, 1]],
[-1, 1, Conv, [128, 3, 2]],
[-1, 1, Conv, [64, 1, 1]],
[-2, 1, Conv, [64, 1, 1]],
[-1, 1, Conv, [64, 3, 1]],
[-1, 1, Conv, [64, 3, 1]],
[-1, 1, Conv, [64, 3, 1]],
[-1, 1, Conv, [64, 3, 1]],
[[-1, -3, -5, -6], 1, Concat, [1]],
[-1, 1, Conv, [256, 1, 1]],
[-1, 1, MP, []],
[-1, 1, Conv, [128, 1, 1]],
[-3, 1, Conv, [128, 1, 1]],
[-1, 1, Conv, [128, 3, 2]],
[[-1, -3], 1, Concat, [1]],
[-1, 1, Conv, [128, 1, 1]],
[-2, 1, Conv, [128, 1, 1]],
[-1, 1, Conv, [128, 3, 1]],
[-1, 1, Conv, [128, 3, 1]],
[-1, 1, Conv, [128, 3, 1]],
[-1, 1, Conv, [128, 3, 1]],
[[-1, -3, -5, -6], 1, Concat, [1]],
[-1, 1, Conv, [512, 1, 1]],
[-1, 1, MP, []],
[-1, 1, Conv, [256, 1, 1]],
[-3, 1, Conv, [256, 1, 1]],
[-1, 1, Conv, [256, 3, 2]],
[[-1, -3], 1, Concat, [1]],
[-1, 1, Conv, [256, 1, 1]],
[-2, 1, Conv, [256, 1, 1]],
[-1, 1, Conv, [256, 3, 1]],
[-1, 1, Conv, [256, 3, 1]],
[-1, 1, Conv, [256, 3, 1]],
[-1, 1, Conv, [256, 3, 1]],
[[-1, -3, -5, -6], 1, Concat, [1]],
[-1, 1, Conv, [1024, 1, 1]],
[-1, 1, MP, []],
[-1, 1, Conv, [512, 1, 1]],
[-3, 1, Conv, [512, 1, 1]],
[-1, 1, Conv, [512, 3, 2]],
[[-1, -3], 1, Concat, [1]],
[-1, 1, Conv, [256, 1, 1]],
[-2, 1, Conv, [256, 1, 1]],
[-1, 1, Conv, [256, 3, 1]],
[-1, 1, Conv, [256, 3, 1]],
[-1, 1, Conv, [256, 3, 1]],
[-1, 1, Conv, [256, 3, 1]],
[[-1, -3, -5, -6], 1, Concat, [1]],
[-1, 1, Conv, [1024, 1, 1]],
]
head:
[[-1, 1, SPPCSPC, [512]],
[-1, 1, Conv, [256, 1, 1]],
[-1, 1, nn.Upsample, [None, 2, 'nearest']],
[37, 1, Conv, [256, 1, 1]],
[[-1, -2], 1, Concat, [1]],
[-1, 1, Conv, [256, 1, 1]],
[-2, 1, Conv, [256, 1, 1]],
[-1, 1, Conv, [128, 3, 1]],
[-1, 1, Conv, [128, 3, 1]],
[-1, 1, Conv, [128, 3, 1]],
[-1, 1, Conv, [128, 3, 1]],
[[-1, -2, -3, -4, -5, -6], 1, Concat, [1]],
[-1, 1, Conv, [256, 1, 1]],
[-1, 1, Conv, [128, 1, 1]],
[-1, 1, nn.Upsample, [None, 2, 'nearest']],
[24, 1, Conv, [128, 1, 1]],
[[-1, -2], 1, Concat, [1]],
[-1, 1, Conv, [128, 1, 1]],
[-2, 1, Conv, [128, 1, 1]],
[-1, 1, Conv, [64, 3, 1]],
[-1, 1, Conv, [64, 3, 1]],
[-1, 1, Conv, [64, 3, 1]],
[-1, 1, Conv, [64, 3, 1]],
[[-1, -2, -3, -4, -5, -6], 1, Concat, [1]],
[-1, 1, Conv, [128, 1, 1]],
[-1, 1, MP, []],
[-1, 1, Conv, [128, 1, 1]],
[-3, 1, Conv, [128, 1, 1]],
[-1, 1, Conv, [128, 3, 2]],
[[-1, -3, 63], 1, Concat, [1]],
[-1, 1, Conv, [256, 1, 1]],
[-2, 1, Conv, [256, 1, 1]],
[-1, 1, Conv, [128, 3, 1]],
[-1, 1, Conv, [128, 3, 1]],
[-1, 1, Conv, [128, 3, 1]],
[-1, 1, Conv, [128, 3, 1]],
[[-1, -2, -3, -4, -5, -6], 1, Concat, [1]],
[-1, 1, Conv, [256, 1, 1]],
[-1, 1, MP, []],
[-1, 1, Conv, [256, 1, 1]],
[-3, 1, Conv, [256, 1, 1]],
[-1, 1, Conv, [256, 3, 2]],
[[-1, -3, 51], 1, Concat, [1]],
[-1, 1, Conv, [512, 1, 1]],
[-2, 1, Conv, [512, 1, 1]],
[-1, 1, Conv, [256, 3, 1]],
[-1, 1, Conv, [256, 3, 1]],
[-1, 1, Conv, [256, 3, 1]],
[-1, 1, Conv, [256, 3, 1]],
[[-1, -2, -3, -4, -5, -6], 1, Concat, [1]],
[-1, 1, Conv, [512, 1, 1]],
[75, 1, RepConv, [256, 3, 1]],
[88, 1, RepConv, [512, 3, 1]],
[101, 1, RepConv, [1024, 3, 1]],
[[102,103,104], 1, IDetect, [nc, anchors]],
]
(3)修改数据加载配置文件
进入data/文件夹,新建fall.yaml,内容如下:
train: ./data/train.txt
val: ./data/val.txt
test: ./data/test.txt
nc: 1
names: ['fall']
至此,配置文件修改完成
yolov7仓库中有两个训练脚本,一个叫train.py,一个叫train_aux.py,前者是训练P5的模型,包含yolov7-tiny、yolov7-tiny-silu、yolov7、yolov7x,后者是训练P6的模型,包含yolov7-w6、yolov7-e6、yolov7-d6、yolov7-e6e。
python train.py --weights yolov7.pt --data data/fall.yaml --epochs 300 --batch-size 8 --cfg cfg/training/yolov7.yaml --workers 0 --device 0 --img-size 640 640
python train_aux.py --weights yolov7-e6e.pt --data data/fall.yaml --epochs 300 --batch-size 8 --cfg cfg/training/yolov7-e6e.yaml --workers 0 --device 0 --img-size 1280 1280
其中,–weights是指预训练模型权重,可以去yolov7官方链接下载,指定到相应目录下(推荐),如果没有配置网络可能会存在git不了权重文件
–data是指数据加载文件路径
–epoch是指模型训练轮次
–batch-size是指一批次输入多少数据一起训练,根据自己显卡的显存决定
–cfg是指模型加载文件路径,关于–cfg中的training和deploy可以参考这篇文章:training和deploy的区别
–workers是指dataloader同时读取多少个进程,如果num_worker设为0,意味着每一轮迭代时,dataloader不再有自主加载数据到RAM这一步骤(因为没有worker了),而是在RA中找batch,找不到时再加载相应的batch。缺点当然是速度慢。设置为0可以避免一些错误发生
–device是指选用几号GPU
–img-size是指训练集和测试集图像大小,可选640或1280等
–rect是指是否采用矩阵推理的方式去训练模型,采用矩阵推理就不要求送入的训练的图片是正方形
–resume断点续训
–evolve超参数进化,模型提供的默认参数是通过在COCO数据集上使用超参数进化得来的
–linear-lr利用余弦函数对训练中的学习率进行调整
如果计算机上存在多张GPU卡,则可以使用分布式训练方法:
python -m torch.distributed.launch --nproc_per_node 4 --master_port 9527 train.py --workers 8 --device 0,1,2,3 --sync-bn --batch-size 8 --data data/fall.yaml --img 640 640 --cfg cfg/training/yolov7.yaml --weights '' --name yolov7 --hyp data/hyp.scratch.p5.yaml
python -m torch.distributed.launch --nproc_per_node 8 --master_port 9527 train_aux.py --workers 8 --device 0,1,2,3,4,5,6,7 --sync-bn --batch-size 8 --data data/fall.yaml --img 1280 1280 --cfg cfg/training/yolov7-e6e.yaml --weights '' --name yolov7-w6 --hyp data/hyp.scratch.p6.yaml
使用test.py文件可以对训练出的模型进行测试,与训练命令基本类似,但是这里需要注意的是,需要把:
python test.py --weights exp/best.pt --data data/fall.yaml --batch-size 8 --device 0 --img-size 640 640
python detect.py --weights runs/train/exp/weights/best.pt --source 0
使用export.py脚本,可以导出成中间格式的onnx模型
python export.py --weights runs/train/exp/best.pt
–weights是通过yolov7训练得到的pt文件,一般存在于runs/train下面的文件夹中,导出后,方便后续部署(onnx/tensorrt/openvino/coreml)
Original: https://blog.csdn.net/weixin_45921929/article/details/126448031
Author: Patience�
Title: YOLOV7训练专属于自己的目标检测模型(保姆级教程,含数据集预处理)
原创文章受到原创版权保护。转载请注明出处:https://www.johngo689.com/647532/
转载文章受原作者版权保护。转载请注明原作者出处!