Jetson Nano跑通Yolov3

• 調用攝像頭識別：Jetson nano之pytorch 深度學習_whujk的博客-CSDN博客
• Yolov3系列最佳實踐：GitHub - doubleZ0108/IDEA-Lab-Summer-Camp: ZJU IDEA Lab Summer Camp

核心檢測命令

# 圖片
./darknet detect cfg/yolov3.cfg yolov3.weights data/test.jpg

# 攝像頭
./darknet detector demo cfg/coco.data cfg/yolov3.cfg yolov3.weights "nvarguscamerasrc ! video/x-raw(memory:NVMM), width=1280, height=720, format=NV12, framerate=30/1 ! nvvidconv flip-method=2 ! video/x-raw, width=1280, height=720, format=BGRx ! videoconvert ! video/x-raw, format=BGR ! appsink"

# 視頻(暫未成功)
./darknet detecte cfg/yolov3.cfg yolov3.weights -thresh 0.35 -dont_show data/test.mp4 -i 0 -out_filename results.avi

複製代碼

預測效果

關於幀率

視頻只能達到<2 FPS

yolov3-tiny 幀率FPS: ~6

yolov4-tiny 幀率FPS：12～13