前一篇文章写了如何的安装yolo5。基于上面的一章，记录下用yolo5来训练自己的数据。
split_train_val.py
import os
import random
trainval_percent = 0.1
train_percent = 0.9
xmlfilepath = '/Users/Tony/IdeaProjects/yolov5/data/mydata/xml'
txtsavepath = '/Users/Tony/IdeaProjects/yolov5/data/mydata/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('/Users/Tony/IdeaProjects/yolov5/data/mydata/ImageSets/trainval.txt', 'w')
ftest = open('/Users/Tony/IdeaProjects/yolov5/data/mydata/ImageSets/test.txt', 'w')
ftrain = open('/Users/Tony/IdeaProjects/yolov5/data/mydata/ImageSets/train.txt', 'w')
fval = open('/Users/Tony/IdeaProjects/yolov5/data/mydata/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:
ftest.write(name)
else:
fval.write(name)
else:
ftrain.write(name)
ftrainval.close()
ftrain.close()
fval.close()
ftest.close(）
以下是lable 文件 voc_label.py
import xml.etree.ElementTree as ET
import pickle
import os
from os import listdir, getcwd
from os.path import join
sets = ['train', 'test','val']
# 这里就是标签的名称，比如：dog，cat 等等和你图片标注的匹配好，用vott或者lableimg都可以进行标注。
classes = ['','']
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('/Users/Tony/IdeaProjects/yolov5/data/mydata/xml/%s.xml' % (image_id))
out_file = open('/Users/Tony/IdeaProjects/yolov5/data/mydata/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('/Users/Tony/IdeaProjects/yolov5/data/mydata/labels/'):
os.makedirs('/Users/Tony/IdeaProjects/yolov5/data/mydata/labels/')
image_ids = open('/Users/Tony/IdeaProjects/yolov5/data/mydata/ImageSets/%s.txt' % (image_set)).read().strip().split()
list_file = open('/Users/Tony/IdeaProjects/yolov5/data/mydata/%s.txt' % (image_set), 'w')
for image_id in image_ids:
list_file.write('/Users/Tony/IdeaProjects/yolov5/data/mydata/images/%s.jpg\n' % (image_id))
convert_annotation(image_id)
list_file.close()
最后运行 train.py 文件进行已经打好标注的文件来进行训练，我这里运行的是基于 yolov5s.pt。
运行过程中可以执行
tensorboard --logdir=runs/train
当然自带有有可视化界面参考
train.py 文件执行之后就等着训练结果的生成，最后会在runs/train 产生训练的结果。
我们用自己生成好的.pt 文件来执行 detect.py ，生成路径位于runs/train/exp/weights 下的.pt文件
python detect.py --weights yolov5s.pt --source 0 # webcam
img.jpg # image
vid.mp4 # video
screen # screenshot
path/ # directory
list.txt # list of images
list.streams # list of streams
'path/*.jpg' # glob
'https://youtu.be/Zgi9g1ksQHc' # YouTube
'rtsp://example.com/media.mp4' # RTSP, RTMP, HTTP stream
以上就是训练好自己的pt文件。