• Call camera recognition: Jetson Nano pyTorch Deep Learning _Whujk’s blog -CSDN blog
  • Yolov3 Series Best Practice: GitHub – doubleZ0108/ idea-lab-summer-camp: ZJU IDEA Lab Summer Camp

Core detection Commands

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

# camera
./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"

# Video (not yet successful)./darknet Detecte CFG /yolov3. CFG Yolov3. arg-thresh 0.35-dont_show data/ test.mp4-I 0-out_filename results.aviCopy the code

Prediction effect

About the frame rate

Video can only be <2 FPS

Yolov3-tiny FPS: ~6

Yolov4-tiny FPS: 12 ~ 13