本文主要是介绍Ubuntu18.04 搭建YOLOV4环境，希望对大家解决编程问题提供一定的参考价值，需要的开发者们随着小编来一起学习吧！
Darknet是一个轻型的深度学习和训练框架，从这一点上，它和tensorflow以及pytorch这种没有什么不同，特点在轻型二字，它主要对卷集神经网络进行了底层实现，并且主要用于YOLO的目标检测，特点主要有：
- C语言实现
- 没有依赖项，除了opencv进行视频和UVC摄像头处理
- 容易安装，可移植性好
- 支持CPU于GPU（CUDA)两种计算方式
下面开始实验。
下载代码，编译
git clone https://github.com/AlexeyAB/darknet
cd darknet
make
下载预训练权重:
验证：
caozilong@caozilong-Vostro-3268:~/Workspace/yolo/darknet$ ./darknet detector test ./cfg/coco.data ./cfg/yolov4.cfg ./yolov4.weights data/dog.jpgGPU isn't used OpenCV isn't used - data augmentation will be slow
mini_batch = 1, batch = 8, time_steps = 1, train = 0 layer filters size/strd(dil) input output0 conv 32 3 x 3/ 1 608 x 608 x 3 -> 608 x 608 x 32 0.639 BF1 conv 64 3 x 3/ 2 608 x 608 x 32 -> 304 x 304 x 64 3.407 BF2 conv 64 1 x 1/ 1 304 x 304 x 64 -> 304 x 304 x 64 0.757 BF3 route 1 -> 304 x 304 x 64 4 conv 64 1 x 1/ 1 304 x 304 x 64 -> 304 x 304 x 64 0.757 BF5 conv 32 1 x 1/ 1 304 x 304 x 64 -> 304 x 304 x 32 0.379 BF6 conv 64 3 x 3/ 1 304 x 304 x 32 -> 304 x 304 x 64 3.407 BF7 Shortcut Layer: 4, wt = 0, wn = 0, outputs: 304 x 304 x 64 0.006 BF8 conv 64 1 x 1/ 1 304 x 304 x 64 -> 304 x 304 x 64 0.757 BF9 route 8 2 -> 304 x 304 x 128 10 conv 64 1 x 1/ 1 304 x 304 x 128 -> 304 x 304 x 64 1.514 BF11 conv 128 3 x 3/ 2 304 x 304 x 64 -> 152 x 152 x 128 3.407 BF12 conv 64 1 x 1/ 1 152 x 152 x 128 -> 152 x 152 x 64 0.379 BF13 route 11 -> 152 x 152 x 128 14 conv 64 1 x 1/ 1 152 x 152 x 128 -> 152 x 152 x 64 0.379 BF15 conv 64 1 x 1/ 1 152 x 152 x 64 -> 152 x 152 x 64 0.189 BF16 conv 64 3 x 3/ 1 152 x 152 x 64 -> 152 x 152 x 64 1.703 BF17 Shortcut Layer: 14, wt = 0, wn = 0, outputs: 152 x 152 x 64 0.001 BF18 conv 64 1 x 1/ 1 152 x 152 x 64 -> 152 x 152 x 64 0.189 BF19 conv 64 3 x 3/ 1 152 x 152 x 64 -> 152 x 152 x 64 1.703 BF20 Shortcut Layer: 17, wt = 0, wn = 0, outputs: 152 x 152 x 64 0.001 BF21 conv 64 1 x 1/ 1 152 x 152 x 64 -> 152 x 152 x 64 0.189 BF22 route 21 12 -> 152 x 152 x 128 23 conv 128 1 x 1/ 1 152 x 152 x 128 -> 152 x 152 x 128 0.757 BF24 conv 256 3 x 3/ 2 152 x 152 x 128 -> 76 x 76 x 256 3.407 BF25 conv 128 1 x 1/ 1 76 x 76 x 256 -> 76 x 76 x 128 0.379 BF26 route 24 -> 76 x 76 x 256 27 conv 128 1 x 1/ 1 76 x 76 x 256 -> 76 x 76 x 128 0.379 BF28 conv 128 1 x 1/ 1 76 x 76 x 128 -> 76 x 76 x 128 0.189 BF29 conv 128 3 x 3/ 1 76 x 76 x 128 -> 76 x 76 x 128 1.703 BF30 Shortcut Layer: 27, wt = 0, wn = 0, outputs: 76 x 76 x 128 0.001 BF31 conv 128 1 x 1/ 1 76 x 76 x 128 -> 76 x 76 x 128 0.189 BF32 conv 128 3 x 3/ 1 76 x 76 x 128 -> 76 x 76 x 128 1.703 BF33 Shortcut Layer: 30, wt = 0, wn = 0, outputs: 76 x 76 x 128 0.001 BF34 conv 128 1 x 1/ 1 76 x 76 x 128 -> 76 x 76 x 128 0.189 BF35 conv 128 3 x 3/ 1 76 x 76 x 128 -> 76 x 76 x 128 1.703 BF36 Shortcut Layer: 33, wt = 0, wn = 0, outputs: 76 x 76 x 128 0.001 BF37 conv 128 1 x 1/ 1 76 x 76 x 128 -> 76 x 76 x 128 0.189 BF38 conv 128 3 x 3/ 1 76 x 76 x 128 -> 76 x 76 x 128 1.703 BF39 Shortcut Layer: 36, wt = 0, wn = 0, outputs: 76 x 76 x 128 0.001 BF40 conv 128 1 x 1/ 1 76 x 76 x 128 -> 76 x 76 x 128 0.189 BF41 conv 128 3 x 3/ 1 76 x 76 x 128 -> 76 x 76 x 128 1.703 BF42 Shortcut Layer: 39, wt = 0, wn = 0, outputs: 76 x 76 x 128 0.001 BF43 conv 128 1 x 1/ 1 76 x 76 x 128 -> 76 x 76 x 128 0.189 BF44 conv 128 3 x 3/ 1 76 x 76 x 128 -> 76 x 76 x 128 1.703 BF45 Shortcut Layer: 42, wt = 0, wn = 0, outputs: 76 x 76 x 128 0.001 BF46 conv 128 1 x 1/ 1 76 x 76 x 128 -> 76 x 76 x 128 0.189 BF47 conv 128 3 x 3/ 1 76 x 76 x 128 -> 76 x 76 x 128 1.703 BF48 Shortcut Layer: 45, wt = 0, wn = 0, outputs: 76 x 76 x 128 0.001 BF49 conv 128 1 x 1/ 1 76 x 76 x 128 -> 76 x 76 x 128 0.189 BF50 conv 128 3 x 3/ 1 76 x 76 x 128 -> 76 x 76 x 128 1.703 BF51 Shortcut Layer: 48, wt = 0, wn = 0, outputs这篇关于Ubuntu18.04 搭建YOLOV4环境的文章就介绍到这儿，希望我们推荐的文章对编程师们有所帮助！
