opencv3.2 安装
下载
http://opencv.org/releases.html
安装介绍
http://www.cnblogs.com/xiaomanon/p/5490281.html
http://www.cnblogs.com/asmer-stone/p/5089764.html
CUDA8.0安装
查询GPU是否支持CUDA
https://developer.nvidia.com/cuda-gpus
安装介绍
http://blog.csdn.net/masa_fish/article/details/51882183
下载地址
https://developer.nvidia.com/cuda-downloads
具体安装过程在别的文章里已经具体说明了,这里不再提及
借鉴官网进行安装https://pjreddie.com/darknet/yolo/
1.配置darknet
git clone https://github.com/pjreddie/darknet
cd darknet
make
看到如下输出表示成功
mkdir -p obj
gcc -I/usr/local/cuda/include/ -Wall -Wfatal-errors -Ofast....
gcc -I/usr/local/cuda/include/ -Wall -Wfatal-errors -Ofast....
gcc -I/usr/local/cuda/include/ -Wall -Wfatal-errors -Ofast....
.....
gcc -I/usr/local/cuda/include/ -Wall -Wfatal-errors -Ofast -lm....
如果没有报错输入
./darknet
得到输出
usage: ./darknet <function>
说明darknet配置成功
打开Makefile文件,将开头几行改为
GPU=1 #确保已经配置好
CUDNN=1
OPENCV=1
之后重新编译,就可以实现基于cuda和opencv的编译
2. 下载预训练文件
wget https://pjreddie.com/media/files/yolo.weights
3. 测试
./darknet detect cfg/yolo.cfg yolo.weights data/dog.jpg
你可以得到以下输出
layer filters size input output
0 conv 32 3 x 3 / 1 416 x 416 x 3 -> 416 x 416 x 32
1 max 2 x 2 / 2 416 x 416 x 32 -> 208 x 208 x 32
.......
29 conv 425 1 x 1 / 1 13 x 13 x1024 -> 13 x 13 x 425
30 detection
Loading weights from yolo.weights...Done!
data/dog.jpg: Predicted in 0.016287 seconds.
car: 54%
bicycle: 51%
dog: 56%
说明yolo2能顺利实现功能