yolov5训练自己的VOC数据集
一.VOC数据准备
voc数据集目录结构 ：
----voc
----Annotations
----ImageSets
----Main
----JPEGImages
在根目录下新建makeTXT.py，将数据集划分，并且在Main文件夹下构建4个TXT：train.txt，test.txt，trainval.txt，val.txt。代码如下：
import os
import random
trainval_percent = 0.1
train_percent = 0.9
xmlfilepath = 'voc/Annotations'
txtsavepath = 'voc/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('voc/ImageSets/Main/trainval.txt', 'w')
ftest = open('voc/ImageSets/Main/test.txt', 'w')
ftrain = open('voc/ImageSets/Main/train.txt', 'w')
fval = open('data/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()在根目录下新建voc_label.py，生成labels文件夹，及用于yolov5训练的train.txt，text.txt，val.txt。代码如下：
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 = ["aeroplane"]
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()
print(wd)
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()用于训练的数据集如下图：
其中images里面存放的是JPEGImages的全部图片。
二.环境搭建
（1）git clone https://github.com/ultralytics/yolov5.git
（2）pip install -U -r requirements.txt
（3）在项目根目录下新建weights文件夹，下载权重文件，将其放入weights文件夹中。
三.训练自己的模型
（1）在data文件夹里面新建test.yaml，
# train and val data as 1) directory: path/images/, 2) file: path/images.txt, or 3) list: [path1/images/, path2/images/]
train: data/train.txt # voclabel.py生成的train.txt的路径
val: data/train.txt # voclabel.py生成的val.txt的路径
# number of classes
nc: 1
# class names
names: ['person']（2）在models文件夹里面找到自己需要的
# parameters
nc: 1 # number of classes
depth_multiple: 0.33 # model depth multiple
width_multiple: 0.50 # layer channel multiple
# anchors
anchors:
- [10,13, 16,30, 33,23] # P3/8
- [30,61, 62,45, 59,119] # P4/16
- [116,90, 156,198, 373,326] # P5/32
# YOLOv5 backbone
backbone:
# [from, number, module, args]
[[-1, 1, Focus, [64, 3]], # 0-P1/2
[-1, 1, Conv, [128, 3, 2]], # 1-P2/4
[-1, 3, BottleneckCSP, [128]],
[-1, 1, Conv, [256, 3, 2]], # 3-P3/8
[-1, 9, BottleneckCSP, [256]],
[-1, 1, Conv, [512, 3, 2]], # 5-P4/16
[-1, 9, BottleneckCSP, [512]],
[-1, 1, Conv, [1024, 3, 2]], # 7-P5/32
[-1, 1, SPP, [1024, [5, 9, 13]]],
[-1, 3, BottleneckCSP, [1024, False]], # 9
]
# YOLOv5 head
head:
[[-1, 1, Conv, [512, 1, 1]],
[-1, 1, nn.Upsample, [None, 2, 'nearest']],
[[-1, 6], 1, Concat, [1]], # cat backbone P4
[-1, 3, BottleneckCSP, [512, False]], # 13
[-1, 1, Conv, [256, 1, 1]],
[-1, 1, nn.Upsample, [None, 2, 'nearest']],
[[-1, 4], 1, Concat, [1]], # cat backbone P3
[-1, 3, BottleneckCSP, [256, False]], # 17 (P3/8-small)
[-1, 1, Conv, [256, 3, 2]],
[[-1, 14], 1, Concat, [1]], # cat head P4
[-1, 3, BottleneckCSP, [512, False]], # 20 (P4/16-medium)
[-1, 1, Conv, [512, 3, 2]],
[[-1, 10], 1, Concat, [1]], # cat head P5
[-1, 3, BottleneckCSP, [1024, False]], # 23 (P5/32-large)
[[17, 20, 23], 1, Detect, [nc, anchors]], # Detect(P3, P4, P5)
]（3）训练模型：python train.py --data data/test.yaml --cfg models/
device=0表示用第1个GPU训练
中断后，恢复训练：python train.py --data data/test.yaml --cfg models/
注意：
官方的训练：
python train.py --data coco.yaml --cfg yolov5s.yaml --weights '' --batch-size 64
yolov5m 40
yolov5l 24
yolov5x 16（4）训练之后，权重会保存在 ./runs 文件夹里面的每个 exp 文件里面的 weights文件夹下。
（5）推理：图片结果会保存在 ./inferenct/output/ 文件夹下：python detect.py --source 图片路径 --weights ./weights/（自己训练的模型）.pt
python detect.py --source 0 # webcam
file.jpg # image
file.mp4 # video
path/ # directory
path/*.jpg # glob
四：生成ONNX
（1）pip install onnx
（2）python ./models/export.py --weights ./weights/（自己训练的模型）.pt --img 640 --batch 4