Pytorch 版YOLOV3训练自己的数据集
数据是深度学习的灵魂所在，默认你已经准备好数据，哈哈
1、环境搭建
git clone https://github.com/ultralytics/yolov3.git2、安装需要的软件
pip install -r requirements.txt3、准备数据
在data文件下建立上面三个文件（Annotations、images与ImageSets，labels后续我们脚本生成）其中Annotations存放xml文件，images图像，ImageSets新建Main文件存放train与test文件（脚本生成），labels是标签文件
划分训练集与测试集（为了充分利用数据集我们只划分这两个），生成的在ImageSets / Main文件下
import os
import random
trainval_percent = 0.2 #可自行进行调节
train_percent = 1
xmlfilepath = 'Annotations'
txtsavepath = 'ImageSets\Main'
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('ImageSets/Main/test.txt', 'w')
ftrain = open('ImageSets/Main/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()建立voc_labels文件生成labels标签文件
import xml.etree.ElementTree as ET
import pickle
import os
from os import listdir, getcwd
from os.path import join
sets = ['train', 'test']
classes = ['apple','orange'] #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/Main/%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()
四、配置训练文件
在data目录下新建fruit.data，配置训练的数据，fruit.name预测的类别名字
classes=2
train=data/train.txt
valid=data/test.txt
names=data/fruit.names
具体cfg参数的意义可以参考我的博客
[net]
# Testing
#batch=1
#subdivisions=1
# Training
batch=64
subdivisions=16
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 = 50000
policy=steps
steps=4000,45000
scales=.1,.1
[convolutional]
batch_normalize=1
filters=32
size=3
stride=1
pad=1
activation=leaky
# Downsample
[convolutional]
batch_normalize=1
filters=64
size=3
stride=2
pad=1
activation=leaky
[convolutional]
batch_normalize=1
filters=32
size=1
stride=1
pad=1
activation=leaky
。。。。。
[convolutional]
size=1
stride=1
pad=1
filters=21 #3*（类别数+4+1）
activation=linear
[yolo]
mask = 6,7,8
anchors = 10,13, 16,30, 33,23, 30,61, 62,45, 59,119, 116,90, 156,198, 373,326
classes=2 #类别数
num=9
jitter=.3
ignore_thresh = .7
truth_thresh = 1
random=1
[route]
layers = -4
[convolutional]
batch_normalize=1
filters=256
size=1
stride=1
pad=1
activation=leaky
[upsample]
stride=2
[route]
layers = -1, 61
[convolutional]
batch_normalize=1
filters=256
size=1
stride=1
pad=1
activation=leaky
[convolutional]
batch_normalize=1
size=3
stride=1
pad=1
filters=512
activation=leaky
[convolutional]
batch_normalize=1
filters=256
size=1
stride=1
pad=1
activation=leaky
[convolutional]
batch_normalize=1
size=3
stride=1
pad=1
filters=512
activation=leaky
[convolutional]
batch_normalize=1
filters=256
size=1
stride=1
pad=1
activation=leaky
[convolutional]
batch_normalize=1
size=3
stride=1
pad=1
filters=512
activation=leaky
[convolutional]
size=1
stride=1
pad=1
filters=21 #3*（类别数+4+1）
activation=linear
[yolo]
mask = 3,4,5
anchors = 10,13, 16,30, 33,23, 30,61, 62,45, 59,119, 116,90, 156,198, 373,326
classes=2 #类别数
num=9
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, 36
[convolutional]
batch_normalize=1
filters=128
size=1
stride=1
pad=1
activation=leaky
[convolutional]
batch_normalize=1
size=3
stride=1
pad=1
filters=256
activation=leaky
[convolutional]
batch_normalize=1
filters=128
size=1
stride=1
pad=1
activation=leaky
[convolutional]
batch_normalize=1
size=3
stride=1
pad=1
filters=256
activation=leaky
[convolutional]
batch_normalize=1
filters=128
size=1
stride=1
pad=1
activation=leaky
[convolutional]
batch_normalize=1
size=3
stride=1
pad=1
filters=256
activation=leaky
[convolutional]
size=1
stride=1
pad=1
filters=21 # 3*（类别数+4+1）
activation=linear
[yolo]
mask = 0,1,2
anchors = 10,13, 16,30, 33,23, 30,61, 62,45, 59,119, 116,90, 156,198, 373,326
classes=2 #自己的类别
num=9
jitter=.3
ignore_thresh = .7
truth_thresh = 1
random=1
五、训练
python train.py --data data/fruit.data --cfg cfg/yolov3.cfg --epochs 10 #后面的epochs自行更改
六、测试
python detect.py --data data/fruit.data --cfg cfg/yolov3.cfg --weights weights/best.pt7、评估模型
python test.py --data data/fruit.data --cfg cfg/yolov3.cfg --weights weights/latest.pt8、可视化图像
python -c "from utils import utils; utils.plot_results()"emmm.... 接下来.... 没有了...官方指南，值得拥有.... 溜了溜了
未完待续。。。