Linux、Windows下试用DarkNet之YoLo CPU物体识别

关于YOLO：

YOLO——You Only Look Once
Faster RCNN需要对20k个anchor box进行判断是否是物体，然后再进行物体识别，分成了两步。 
YOLO(You Only Look Once)则把物体框的选择与识别进行了结合，一步输出，即变成”You Only Look Once”。 
所以识别速度非常快，达到每秒45帧，而在快速版YOLO(Fast YOLO，卷积层更少)中，可以达到每秒155帧。

关于DarkNet：

#Darknet#
Darknet is an open source neural network framework written in C and CUDA. It is fast, easy to install, and supports CPU and GPU computation.
For more information see the [Darknet project website](http://pjreddie.com/darknet or https://github.com/pjreddie/darknet).

安装指南：http://pjreddie.com/darknet/install/

这个是我见过安装最简单的开源库了！！！

linux下，解压后直接make就可以了，如果你想实时可视化，开启OPENCV=1，关于这里配置OPENCV时需要注意下：

ifeq ($(OPENCV), 1) 
COMMON+= -DOPENCV -I/usr/local/include
CFLAGS+= -DOPENCV
LDFLAGS+= -L/usr/local/lib -lopencv_core -lopencv_highgui -lopencv_imgproc
endif

编译好后，下载训练好的权值数据yolo.weights(我下的是700M左右的），同时使用了相应的yolo.cfg，从官网下的没运行成功！！！

贴一下yolo.cfg

[net]batch=1subdivisions=1height=448width=448channels=3momentum=0.9decay=0.0005saturation=1.5exposure=1.5hue=.1learning_rate=0.0005policy=stepssteps=200,400,600,20000,30000scales=2.5,2,2,.1,.1max_batches = 40000[convolutional]batch_normalize=1filters=64size=7stride=2pad=1activation=leaky[maxpool]size=2stride=2[convolutional]batch_normalize=1filters=192size=3stride=1pad=1activation=leaky[maxpool]size=2stride=2[convolutional]batch_normalize=1filters=128size=1stride=1pad=1activation=leaky[convolutional]batch_normalize=1filters=256size=3stride=1pad=1activation=leaky[convolutional]batch_normalize=1filters=256size=1stride=1pad=1activation=leaky[convolutional]batch_normalize=1filters=512size=3stride=1pad=1activation=leaky[maxpool]size=2stride=2[convolutional]batch_normalize=1filters=256size=1stride=1pad=1activation=leaky[convolutional]batch_normalize=1filters=512size=3stride=1pad=1activation=leaky[convolutional]batch_normalize=1filters=256size=1stride=1pad=1activation=leaky[convolutional]batch_normalize=1filters=512size=3stride=1pad=1activation=leaky[convolutional]batch_normalize=1filters=256size=1stride=1pad=1activation=leaky[convolutional]batch_normalize=1filters=512size=3stride=1pad=1activation=leaky[convolutional]batch_normalize=1filters=256size=1stride=1pad=1activation=leaky[convolutional]batch_normalize=1filters=512size=3stride=1pad=1activation=leaky[convolutional]batch_normalize=1filters=512size=1stride=1pad=1activation=leaky[convolutional]batch_normalize=1filters=1024size=3stride=1pad=1activation=leaky[maxpool]size=2stride=2[convolutional]batch_normalize=1filters=512size=1stride=1pad=1activation=leaky[convolutional]batch_normalize=1filters=1024size=3stride=1pad=1activation=leaky[convolutional]batch_normalize=1filters=512size=1stride=1pad=1activation=leaky[convolutional]batch_normalize=1filters=1024size=3stride=1pad=1activation=leaky#######[convolutional]batch_normalize=1size=3stride=1pad=1filters=1024activation=leaky[convolutional]batch_normalize=1size=3stride=2pad=1filters=1024activation=leaky[convolutional]batch_normalize=1size=3stride=1pad=1filters=1024activation=leaky[convolutional]batch_normalize=1size=3stride=1pad=1filters=1024activation=leaky[local]size=3stride=1pad=1filters=256activation=leaky[dropout]probability=.5[connected]output= 1715activation=linear[detection]classes=20coords=4rescore=1side=7num=3softmax=0sqrt=1jitter=.2object_scale=1noobject_scale=.5class_scale=1coord_scale=5

键入命令：

$>./darknet yolo test cfg/yolo.cfg yolo.weights data/dog.jpg

Windows下更简单了，直接使用https://github.com/AlexeyAB/yolo-windows

可见CPU下Debug耗时太长啊！