Khadas Docs

Amazing Khadas, always amazes you!

User Tools

Site Tools


products:sbc:vim3:npu:vim3_demo_lite:yolov8n

Differences

This shows you the differences between two versions of the page.

Link to this comparison view

Both sides previous revision Previous revision
products:sbc:vim3:npu:vim3_demo_lite:yolov8n [2025/03/12 21:57]
louis
products:sbc:vim3:npu:vim3_demo_lite:yolov8n [2025/04/23 22:35] (current)
louis
Line 12: Line 12:
  
 {{indexmenu_n>2}} {{indexmenu_n>2}}
 +
 +YOLOv8n is an object detection model. It uses bounding boxes to precisely draw each object in image.
 +
 +Inference results on VIM3.
 +
 +{{:products:sbc:vim3:npu:vim3_demo_lite:yolov8n-c-result.png?800|}}
 +
 +**Inference speed test**: USB camera about **137ms** per frame. MIPI camera about **115ms** per frame.
  
 ===== Train the model ===== ===== Train the model =====
Line 234: Line 242:
 $ bash build_vx.sh $ bash build_vx.sh
 $ cd bin_r_cv4 $ cd bin_r_cv4
-$ ./yolov8n_demo_x11_usb -m ../nn_data/yolov8n_88.nb -d /dev/video0+ 
 +# usb 
 +$ ./yolov8n_demo_x11_usb -m ../nn_data/yolov8n_88.nb -t usb -d /dev/video0 
 + 
 +# mipi 
 +$ ./yolov8n_demo_x11_usb -m ../nn_data/yolov8n_88.nb -t mipi -d /dev/video50
 ``` ```
  
  
Last modified: 2025/04/23 22:35 by louis