Differences

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

--- products:sbc:edge2:npu:demos:yolov8n [2024/02/17 22:04]
louis
+++ products:sbc:edge2:npu:demos:yolov8n [2025/06/24 06:02] (current)
louis
@@ Line 5: / Line 5: @@
 {{indexmenu_n>2}}
-===== Get Source Code =====
+===== Introduction =====
+YOLOv8n is an object detection model. It uses bounding boxes to precisely draw each object in image.
+Inference results on Edge2.
+{{:products:sbc:edge2:npu:demos:yolov8n-result.jpg?800|}}
+**Inference speed test**: USB camera about **52ms** per frame. MIPI camera about **40ms** per frame.
+===== Train Model =====
 Download YOLOv8 official code [[gh>ultralytics/ultralytics]]
@@ Line 13: / Line 23: @@
 ```
-Refer ''README.md'' to train a YOLOv8n model.
+Refer ''README.md'' to train a YOLOv8n model. My version ''torch==1.10.1'' and ''ultralytics==8.0.86''.
 ===== Convert Model =====
@@ Line 191: / Line 201: @@
 $ bash build.sh
-# Run
+# Run USB camera
+$ cd install/yolov8n_cap
+$ ./yolov8n_cap data/model/yolov8n.rknn usb 60
+# Run MIPI camera
+$ cd install/yolov8n_cap
+$ ./yolov8n_cap data/model/yolov8n.rknn mipi 42
+```
+<WRAP info >
+''60'' and ''42'' are camera device index.
+</WRAP>
+=== Camera input multithreading demo ===
+Put ''yolov8n.rknn'' in ''edge2-npu/C++/yolov8n_cap_multithreading/data/model''.
+```shell
+# Compile
+$ bash build.sh
+# Run USB camera
+$ cd install/yolov8n_cap
+$ ./yolov8n_cap data/model/yolov8n.rknn usb 60 2
+# Run MIPI camera
 $ cd install/yolov8n_cap
-$ ./yolov8n_cap data/model/yolov8n_cap.rknn 33
+$ ./yolov8n_cap data/model/yolov8n.rknn mipi 42 2
 ```
 <WRAP info >
-''33'' is camera device index.
+The last num, ''2'', is the number of threads.
 </WRAP>

Khadas Docs

User Tools

Site Tools

Differences

Page Tools