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=1
subdivisions=1
height=448
width=448
channels=3
momentum=0.9
decay=0.0005
saturation=1.5
exposure=1.5
hue=.1

learning_rate=0.0005
policy=steps
steps=200,400,600,20000,30000
scales=2.5,2,2,.1,.1
max_batches = 40000

[convolutional]
batch_normalize=1
filters=64
size=7
stride=2
pad=1
activation=leaky

[maxpool]
size=2
stride=2

[convolutional]
batch_normalize=1
filters=192
size=3
stride=1
pad=1
activation=leaky

[maxpool]
size=2
stride=2

[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

[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

[maxpool]
size=2
stride=2

[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

[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

[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

[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

[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

[maxpool]
size=2
stride=2

[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

[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

#######

[convolutional]
batch_normalize=1
size=3
stride=1
pad=1
filters=1024
activation=leaky

[convolutional]
batch_normalize=1
size=3
stride=2
pad=1
filters=1024
activation=leaky

[convolutional]
batch_normalize=1
size=3
stride=1
pad=1
filters=1024
activation=leaky

[convolutional]
batch_normalize=1
size=3
stride=1
pad=1
filters=1024
activation=leaky

[local]
size=3
stride=1
pad=1
filters=256
activation=leaky

[dropout]
probability=.5

[connected]
output= 1715
activation=linear

[detection]
classes=20
coords=4
rescore=1
side=7
num=3
softmax=0
sqrt=1
jitter=.2

object_scale=1
noobject_scale=.5
class_scale=1
coord_scale=5

$>./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！