HongChuang/ultralytics-ascend
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions 3

Add note on failing RKNN inference on select Rockchip hardware (#18964)

Browse source 
Signed-off-by: Glenn Jocher <glenn.jocher@ultralytics.com>
Co-authored-by: Glenn Jocher <glenn.jocher@ultralytics.com>
This commit is contained in:
Lakshantha Dissanayake 2025-02-03 06:17:42 -08:00 • committed by GitHub
parent efc3c392a9
commit 5db36db822
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
1 changed files with 6 additions and 0 deletions
Download patch file Download diff file Expand all files Collapse all files

6
docs/en/integrations/rockchip-rknn.md
View file

@ -133,6 +133,12 @@ To install the required packages, run:
yolo predict model='./yolo11n_rknn_model' source='https://ultralytics.com/images/bus.jpg'
```
!!! note
If you encounter a log message indicating that the RKNN runtime version does not match the RKNN Toolkit version and the inference fails, please replace `/usr/lib/librknnrt.so` with official [librknnrt.so file](https://github.com/airockchip/rknn-toolkit2/blob/master/rknpu2/runtime/Linux/librknn_api/aarch64/librknnrt.so).
![RKNN export screenshot](https://github.com/ultralytics/assets/releases/download/v0.0.0/rknn-npu-log.avif)
## Benchmarks
YOLO11 benchmarks below were run by the Ultralytics team on Radxa Rock 5B based on Rockchip RK3588 with `rknn` model format measuring speed and accuracy.