yolov5训练custom数据集
github地址
https://github.com/ultralytics/yolov5/wiki/Train-Custom-Data
1.制作数据集
(1)划分数据
# coding:utf-8
import os
import random
import argparse
parser = argparse.ArgumentParser()
#xml文件的地址,根据自己的数据进行修改 xml一般存放在Annotations下
parser.add_argument('--xml_path', default='label', type=str, help='input xml label path')
#数据集的划分,地址选择自己数据下的ImageSets/Main
parser.add_argument('--txt_path', default='Main', type=str, help='output txt label path')
opt = parser.parse_args()
trainval_percent = 1.0
train_percent = 0.9
xmlfilepath = opt.xml_path
txtsavepath = opt.txt_path
total_xml = os.listdir(xmlfilepath)
if not os.path.exists(txtsavepath):
os.makedirs(txtsavepath)
num = len(total_xml)
list_index = range(num)
tv = int(num * trainval_percent)
tr = int(tv * train_percent)
trainval = random.sample(list_index, tv)
train = random.sample(trainval, tr)
file_trainval = open(txtsavepath + '/trainval.txt', 'w')
file_test = open(txtsavepath + '/test.txt', 'w')
file_train = open(txtsavepath + '/train.txt', 'w')
file_val = open(txtsavepath + '/val.txt', 'w')
for i in list_index:
name = total_xml[i][:-4] + '\n'
if i in trainval:
file_trainval.write(name)
if i in train:
file_train.write(name)
else:
file_val.write(name)
else:
file_test.write(name)
file_trainval.close()
file_train.close()
file_val.close()
file_test.close()
(2)假设已经将图片标注好。需要将xml转成txt。
如下代码将xml文件转成txt
# -*- coding: utf-8 -*-
import xml.etree.ElementTree as ET
import os
from os import getcwd
sets = ['train', 'val', 'test']
classes = ["rock"] # 改成自己的类别
abs_path = os.getcwd()
print(abs_path)
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(image_id):
in_file = open('Annotations/%s.xml' % (image_id), encoding='UTF-8')
out_file = open('worktxt/%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
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))
b1, b2, b3, b4 = b
# 标注越界修正
if b2 > w:
b2 = w
if b4 > h:
b4 = h
b = (b1, b2, b3, b4)
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('worktxt/'):
os.makedirs('worktxt/')
image_ids = open('ImageSets/Main/%s.txt' % (image_set)).read().strip().split()
list_file = open('%s.txt' % (image_set), 'w')
for image_id in image_ids:
list_file.write(abs_path + '/images/%s.jpg\n' % (image_id))
convert_annotation(image_id)
list_file.close()
2.按照格式存放数据
按照github地址提供的coco128的格式存放
/home/xuekelou420/hw/yolov5/coco128/images/train2017
/home/xuekelou420/hw/yolov5/coco128/labels/train2017
3.更改配置文件
主要是做自己的coco.yaml文件
# train and val data as 1) directory: path/images/, 2) file: path/images.txt, or 3) list: [path1/images/, path2/images/]
train: /home/xuekelou420/hw/yolov5/dataset/images/train2017 # 118287 images
val: /home/xuekelou420/hw/yolov5/dataset/images/val2017 # 5000 images
# number of classes
nc: 1
# class names
names: [ 'rock' ]
可以参考此博文
4.训练代码
训练代码,根据自己情况更改参数,yolov5s写种类。
python train.py --batch 4 --epoch 300 --data data/rock.yaml --cfg models/yolov5s.yaml --weights weights/yolov5s.pt --device '0'
5.测试图片
根据自己情况更改detect.py 文件参数
修改图片大小(720,1280)写720,不然报错
–save-txt 会生成txt文件
python detect.py --weights runs/exp1/weights/best.pt --source inference/images/ --device 0 --save-txt