1、下载代码
git clone https://github.com/pjreddie/darknet
cd darknet
vi Makefile #打开文件
GPU=1 #使用GPU训练
CUDNN=0
make
遇到问题：nvcc找不到
vi ~/.bashrc
export PATH=$PATH:/usr/local/cuda-10.0/bin export LD_LIBRARY_PATH=$LD_LIBRARY_PATH:/usr/local/cuda-10.0/lib64
在scripts文件夹下创建文件夹 VOCdevkit，在 VOCdevkit文件夹下建立 VOC2019 文件夹。 在 VOC2019 文件夹下建立 Annotations 、ImageSets、JPEGImages三个文件夹。在ImageSets文件夹下建立Main文件夹。
在VOC2019文件夹下建立dir.py，用于分训练集、测试集、验证集
import os
import random
trainval_percent = 0.9995
train_percent = 0.9995
xmlfilepath = 'Annotations'
#xmlfilepath='1jpgTest'
txtsavepath = 'ImageSetsMain'
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]+'
'
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()
scrips文件夹下 voc_label.by 修改
sets=[('2019', 'train'), ('2019', 'val')]
classes = ["eye", "closed", "hand", "phone", "smoke", "mouth"]
os.system("cat 2019_train.txt 2019_val.txt > train.txt")
运行 python voc_label.py ，VOC数据转成yolov3格式数据
生成labels文件夹，2019_train.txt，2019_val.txt，train.txt
预训练权重
wget https://pjreddie.com/media/files/darknet53.conv.74
修改cfg/voc.data
classes= 6 train = /home/***/workspace/yolov3/darknet-master/scripts/2019_train.txt valid = /home/***/workspace/yolov3/darknet-master/scripts/2019_val.txt names = data/voc.names backup = backup
修改data/voc.name
eye closed hand phone smoke mouth
修改cfg/yolov3-voc.cfg
[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 = 50200 policy=steps steps=40000,45000 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] batch_normalize=1 filters=64 size=3 stride=1 pad=1 activation=leaky [shortcut] from=-3 activation=linear # Downsample [convolutional] batch_normalize=1 filters=128 size=3 stride=2 pad=1 activation=leaky [convolutional] batch_normalize=1 filters=64 size=1 stride=1 pad=1 activation=leaky [convolutional] batch_normalize=1 filters=128 size=3 stride=1 pad=1 activation=leaky [shortcut] from=-3 activation=linear [convolutional] batch_normalize=1 filters=64 size=1 stride=1 pad=1 activation=leaky [convolutional] batch_normalize=1 filters=128 size=3 stride=1 pad=1 activation=leaky [shortcut] from=-3 activation=linear # Downsample [convolutional] batch_normalize=1 filters=256 size=3 stride=2 pad=1 activation=leaky [convolutional] batch_normalize=1 filters=128 size=1 stride=1 pad=1 activation=leaky [convolutional] batch_normalize=1 filters=256 size=3 stride=1 pad=1 activation=leaky [shortcut] from=-3 activation=linear [convolutional] batch_normalize=1 filters=128 size=1 stride=1 pad=1 activation=leaky [convolutional] batch_normalize=1 filters=256 size=3 stride=1 pad=1 activation=leaky [shortcut] from=-3 activation=linear [convolutional] batch_normalize=1 filters=128 size=1 stride=1 pad=1 activation=leaky [convolutional] batch_normalize=1 filters=256 size=3 stride=1 pad=1 activation=leaky [shortcut] from=-3 activation=linear [convolutional] batch_normalize=1 filters=128 size=1 stride=1 pad=1 activation=leaky [convolutional] batch_normalize=1 filters=256 size=3 stride=1 pad=1 activation=leaky [shortcut] from=-3 activation=linear [convolutional] batch_normalize=1 filters=128 size=1 stride=1 pad=1 activation=leaky [convolutional] batch_normalize=1 filters=256 size=3 stride=1 pad=1 activation=leaky [shortcut] from=-3 activation=linear [convolutional] batch_normalize=1 filters=128 size=1 stride=1 pad=1 activation=leaky [convolutional] batch_normalize=1 filters=256 size=3 stride=1 pad=1 activation=leaky [shortcut] from=-3 activation=linear [convolutional] batch_normalize=1 filters=128 size=1 stride=1 pad=1 activation=leaky [convolutional] batch_normalize=1 filters=256 size=3 stride=1 pad=1 activation=leaky [shortcut] from=-3 activation=linear [convolutional] batch_normalize=1 filters=128 size=1 stride=1 pad=1 activation=leaky [convolutional] batch_normalize=1 filters=256 size=3 stride=1 pad=1 activation=leaky [shortcut] from=-3 activation=linear # Downsample [convolutional] batch_normalize=1 filters=512 size=3 stride=2 pad=1 activation=leaky [convolutional] batch_normalize=1 filters=256 size=1 stride=1 pad=1 activation=leaky [convolutional] batch_normalize=1 filters=512 size=3 stride=1 pad=1 activation=leaky [shortcut] from=-3 activation=linear [convolutional] batch_normalize=1 filters=256 size=1 stride=1 pad=1 activation=leaky [convolutional] batch_normalize=1 filters=512 size=3 stride=1 pad=1 activation=leaky [shortcut] from=-3 activation=linear [convolutional] batch_normalize=1 filters=256 size=1 stride=1 pad=1 activation=leaky [convolutional] batch_normalize=1 filters=512 size=3 stride=1 pad=1 activation=leaky [shortcut] from=-3 activation=linear [convolutional] batch_normalize=1 filters=256 size=1 stride=1 pad=1 activation=leaky [convolutional] batch_normalize=1 filters=512 size=3 stride=1 pad=1 activation=leaky [shortcut] from=-3 activation=linear [convolutional] batch_normalize=1 filters=256 size=1 stride=1 pad=1 activation=leaky [convolutional] batch_normalize=1 filters=512 size=3 stride=1 pad=1 activation=leaky [shortcut] from=-3 activation=linear [convolutional] batch_normalize=1 filters=256 size=1 stride=1 pad=1 activation=leaky [convolutional] batch_normalize=1 filters=512 size=3 stride=1 pad=1 activation=leaky [shortcut] from=-3 activation=linear [convolutional] batch_normalize=1 filters=256 size=1 stride=1 pad=1 activation=leaky [convolutional] batch_normalize=1 filters=512 size=3 stride=1 pad=1 activation=leaky [shortcut] from=-3 activation=linear [convolutional] batch_normalize=1 filters=256 size=1 stride=1 pad=1 activation=leaky [convolutional] batch_normalize=1 filters=512 size=3 stride=1 pad=1 activation=leaky [shortcut] from=-3 activation=linear # Downsample [convolutional] batch_normalize=1 filters=1024 size=3 stride=2 pad=1 activation=leaky [convolutional] batch_normalize=1 filters=512 size=1 stride=1 pad=1 activation=leaky [convolutional] batch_normalize=1 filters=1024 size=3 stride=1 pad=1 activation=leaky [shortcut] from=-3 activation=linear [convolutional] batch_normalize=1 filters=512 size=1 stride=1 pad=1 activation=leaky [convolutional] batch_normalize=1 filters=1024 size=3 stride=1 pad=1 activation=leaky [shortcut] from=-3 activation=linear [convolutional] batch_normalize=1 filters=512 size=1 stride=1 pad=1 activation=leaky [convolutional] batch_normalize=1 filters=1024 size=3 stride=1 pad=1 activation=leaky [shortcut] from=-3 activation=linear [convolutional] batch_normalize=1 filters=512 size=1 stride=1 pad=1 activation=leaky [convolutional] batch_normalize=1 filters=1024 size=3 stride=1 pad=1 activation=leaky [shortcut] from=-3 activation=linear ###################### [convolutional] batch_normalize=1 filters=512 size=1 stride=1 pad=1 activation=leaky [convolutional] batch_normalize=1 size=3 stride=1 pad=1 filters=1024 activation=leaky [convolutional] batch_normalize=1 filters=512 size=1 stride=1 pad=1 activation=leaky [convolutional] batch_normalize=1 size=3 stride=1 pad=1 filters=1024 activation=leaky [convolutional] batch_normalize=1 filters=512 size=1 stride=1 pad=1 activation=leaky [convolutional] batch_normalize=1 size=3 stride=1 pad=1 filters=1024 activation=leaky [convolutional] size=1 stride=1 pad=1 filters=33 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=6 num=9 jitter=.3 ignore_thresh = .5 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=33 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=6 num=9 jitter=.3 ignore_thresh = .5 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=33 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=6 num=9 jitter=.3 ignore_thresh = .5 truth_thresh = 1 random=1
1、605行，filters=75 修改 3*（classes+5） 2、689行 filters=75 修改 3*（classes+5） 3、773行 filters=75 修改 3*（classes+5） 4、3行 Testing 注释掉batch=1 subdivisions=1 5、611行 classes=20 类别修改成自己的类别 6、695行 classes=20 类别修改成自己的类别 7、779行 classes=20 类别修改成自己的类别
训练
./darknet detector train cfg/voc.data cfg/yolov3-voc.cfg scripts/darknet53.conv.74 -gpus 0,1
测试
backup文件夹下生成权重文件
./darknet detector test cfg/voc.data cfg/yolov3-voc.cfg backup/yolov3-voc_600.weights data/210.jpg