在Jetson nano中使用yolov4进行目标检测

下载地址

git clone https://github.com/AlexeyAB/darknet.git

相关配置

编辑Makefile

cd darknet
sudo vim Makefile   

修改Makefile

GPU=1
CUDNN=1
OPENCV=1

编译

在darknet路径下编译

make  -j4

下载权重文件

# yolov4-tiny.weights
wget https://github.com/AlexeyAB/darknet/releases/download/darknet_yolo_v4_pre/yolov4-tiny.weights

测试

Yolov4-tiny图片检测

./darknet detect cfg/yolov4-tiny.cfg yolov4-tiny.weights data/dog.jpg # 简写版
./darknet detector test cfg/coco.data cfg/yolov4-tiny.cfg yolov4-tiny.weights data/dog.jpg # 完整版

Yolov4-tiny视频检测

./darknet detector demo cfg/coco.data cfg/yolov4-tiny.cfg yolov4-tiny.weights data/test_video.mp4

Yolov4-tiny CSI摄像头实时检测

# 使用CSI摄像头前，要安装GStreamer
sudo add-apt-repository universe
sudo add-apt-repository multiverse
sudo apt-get update
sudo apt-get install gstreamer1.0-tools gstreamer1.0-alsa gstreamer1.0-plugins-base gstreamer1.0-plugins-good gstreamer1.0-plugins-bad gstreamer1.0-plugins-ugly gstreamer1.0-libav
sudo apt-get install libgstreamer1.0-dev libgstreamer-plugins-base1.0-dev libgstreamer-plugins-good1.0-dev libgstreamer-plugins-bad1.0-dev 
# 配置GStreamer管道，并使用Yolov4-tiny模型进行检测
./darknet detector demo cfg/coco.data cfg/yolov4-tiny.cfg yolov4-tiny.weights "nvarguscamerasrc ! video/x-raw(memory:NVMM), width=1280, height=720, format=NV12, framerate=30/1 ! nvvidconv flip-method=0 ! video/x-raw, width=1280, height=720, format=BGRx ! videoconvert ! video/x-raw, format=BGR ! appsink"