-
When I run the official SDK on rock5a test.py in the rknn-tool-lite2 /example/dynamic_shape
I got this
(py310) rock@rock-5a:~/dynamic_shape$ python test.py
--> Load RKNN model
done
--> Init run…
-
Thank you for sharing your great work!
Can you please provide the process by which you created your rknn yolov9 model from the original torch model.
-
Traceback (most recent call last):
File "../../../../../common/rknn_converter/rknn_convert.py", line 99, in
convert(config_dict, args)
File "../../../../../common/rknn_converter/rknn_conve…
-
报错如下：
W Verbose file path is invalid, debug info will not dump to file.
D Using CPPUTILS: True
........................................
...........此处省略...........
................................…
-
Hi!
I tried a conversion of this model starting from torch to ONNX to RKNN to use that on OrangePi 5 NPUs. I noticied that going from ONNX to RKNN is possible only using opset
-
Hello, I would like to run faster rcnn on rockpi5b using NPU? is it possible to convert .pth models to .rknn using toolkit?
Thank you for your answer!!
-
/home/linaro/rknn-toolkit2-master/rknn_toolkit_lite2/examples/inference_with_lite/rknn-cpp-Multithreading-main
模型名称: ./model/RK3588/yolov5s-640-640_rm_transpose_rk3588.rknn
线程数: 1
Loading mod…
-
我再使用https://github.com/rockchip-linux/rknn-toolkit/releases项目进行rv1126的pt模型转rknn模型的时候。运行指令
python ../../../../../common/rknn_converter/rknn_convert.py --yml_path ./yolov5_6_7_backup.yml --python_api…
-
When trying out the Radxa Linux 6.1 (bookworm) builds for [Rock 5B](https://github.com/radxa-build/rock-5b-6_1) and [CM5](https://github.com/radxa-build/radxa-cm5-io-6_1) I experience an error with th…
swdee updated
5 months ago
-
I use these instruction https://github.com/rockchip-linux/rknpu2/issues/57
clone this repo https://github.com/airockchip/yolov5
then,
$ python3 export.py --weights yolov5s.pt --rknpu "RK3588" --i…