Linux、Windows下試用DarkNet之YoLo CPU物體識別
關於YOLO：
YOLO——You Only Look Once
Faster RCNN需要對20k個anchor box進行判斷是否是物體，然後再進行物體識別，分成了兩步。
YOLO(You Only Look Once)則把物體框的選擇與識別進行了結合，一步輸出，即變成”You Only Look Once”。
所以識別速度非常快，達到每秒45幀，而在快速版YOLO(Fast YOLO，卷積層更少)中，可以達到每秒155幀。
關於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).
安裝指南：http://pjreddie.com/darknet/install/
這個是我見過安裝最簡單的開源庫了！！！
linux下，解壓後直接make就可以了，如果你想實時視覺化，開啟OPENCV=1，關於這裡配置OPENCV時需要注意下：
ifeq ($(OPENCV), 1)
COMMON+= -DOPENCV
-I/usr/local/include
CFLAGS+= -DOPENCV
LDFLAGS+= -L/usr/local/lib -lopencv_core -lopencv_highgui -lopencv_imgproc
endif
編譯好後，下載訓練好的權值資料yolo.weights(我下的是700M左右的），同時使用了相應的yolo.cfg，從官網下的沒執行成功！！！
貼一下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
鍵入命令：
$>./darknet yolo test cfg/yolo.cfg yolo.weights data/dog.jpg
可見CPU下Debug耗時太長啊！