darknet yolov3训练
训练环境:
win10
cuda 10.1
cudnn 10.1
darknet https://github.com/pjreddie/darknet
conda3
标注数据
1、工具labelimg
github的安装包地址:https://github.com/tzutalin/labelImg
conda install pyqt=5
pyrcc5 -o libs/resources.py resources.qrc
python labelImg.py
将自己图片标注出来
开始训练模型
我编译后的目录在这个位置C:\darknet\build\darknet\x64 进入这里构建目录结构
目录结构
base) PS C:\darknet\build\darknet\x64\VOCdevkit> tree
文件夹 PATH 列表
卷序列号为 EE6F-0ADF
C:.
└─VOC2007
├─Annotations 放所有的训练和测试图片
├─ImageSets
│ └─Main
├─JPEGImages 放所有的训练和测试图片
└─labels
建立test.py
C:\darknet\build\darknet\x64\VOCdevkit\VOC2007\test.py

import os import random trainval_percent = 0.1 train_percent = 0.9 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()
执行后生成四个文件
(base) PS C:\darknet\build\darknet\x64\VOCdevkit\VOC2007\ImageSets\Main> ls
目录: C:\darknet\build\darknet\x64\VOCdevkit\VOC2007\ImageSets\Main
Mode LastWriteTime Length Name
---- ------------- ------ ----
-a---- 2020/12/24 10:50 21374 test.txt
-a---- 2020/12/24 10:50 208265 train.txt
-a---- 2020/12/24 10:50 23712 trainval.txt
-a---- 2020/12/24 10:50 2338 val.txt
获取权重文件
wget https://pjreddie.com/media/files/yolov3.weights
检测测试
./darknet detect cfg/yolov3.cfg yolov3.weights data/dog.jpg
转换yolov3格式的label文件(C:\darknet\build\darknet\x64\voc_label.py)

sets和classes,classes根据自己需要修改
sets=[('2007', 'train'), ('2007', 'val'), ('2007', 'test')]
我们的目录下会生成三个txt文件2007_train.txt,2007_val.txt,2007_test.txt,VOCdevkit下的VOC2007也会多生成一个labels文件夹,下面是真正会使用到的label,点开看发现已经转化成YOLOV3需要的格式了。
可以把2007_train.txt,2007_test.txt 的数据复制到一个文件中这样训练的数据可以多一些
创建voc.data voc-mask.names yolov3-voc-mask.cfg文件
目录 C:\darknet\build\darknet\x64\data\voc.data
voc.data 文件
classes= 2
train = C:\darknet\build\darknet\x64\train.txt
valid = C:\darknet\build\darknet\x64\2007_test.txt
#difficult = data/difficult_2007_test.txt
names = data/voc.names
backup = backup/
voc-mask.names 文件 类定义的文件
nomask
mask
目录C:\darknet\build\darknet\x64\cfg
yolov3-voc-mask.cfg

[net] # Testing # batch=1 # subdivisions=1 # Training batch=64 subdivisions=16 width=608 height=608 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 = 10000 policy=steps steps=8000,9000 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=21 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 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=21 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 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=21 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 num=9 jitter=.3 ignore_thresh = .5 truth_thresh = 1 random=1
开始训练
wget https://pjreddie.com/media/files/darknet53.conv.74
此过程比较慢
./darknet detector train cfg/voc.data cfg/yolov3-voc-mask.cfg darknet53.conv.74
我这实现了PyTouch 写了一个识别人是否戴口罩样例 ,支持监控 rstp 引流进行实时分析
链接: https://pan.baidu.com/s/1NqG2RHz7hWzvZIk9Eyh9WA
有兴趣的可以加我VX 186463333118