-
rknn-toolkit version: 1.7.5
--> Config model
Traceback (most recent call last):
File "onnx2rknn_demo_ZQ.py", line 224, in
outputs = export_rknn_inference(input_img)
File "onnx2rknn_dem…
-
I FoldConstant : 63%|████████████████████████▌ | 806/1277 [00:27
-
在rk3588模拟器对模型做量化的时候报错：
```
--> Building model
2024-08-14 16:24:58.762700412 [E:onnxruntime:, sequential_executor.cc:514 ExecuteKernel] Non-zero status code returned while running Clip node. Name:'c…
-
使用3588的板子，信息如下：
I RKNN: [02:17:34.734] RKNN Runtime Information, librknnrt version: 2.0.0b14 (2d891ba573@2024-05-31T11:36:07)
I RKNN: [02:17:34.734] RKNN Driver Information, version: 0.8.2
W RKNN: …
-
Hello! please tell me how to convert yolov5's own detection model to rknn format?
-
### Search before asking
- [X] I have searched the YOLOv8 [issues](https://github.com/ultralytics/ultralytics/issues) and found no similar feature requests.
### Description
- [x] new integrations …
-
When using jupyter-notebook (ipython) the RKNN module fails loading with:
`NameError: name 'exit' is not defined`
though it runs ok on normal python. Also, pre-defining `from sys import exit` do…
-
将mmpose的一个onnx模型，在simulator上进行转换，转换后进行后处理，正常。
但是将导出的模型在板子上运行，则结果不理想，运行顺利，但是结果和simulator上差异巨大。
pc环境：
Linux version 6.2.0-1019-gcp (buildd@lcy02-amd64-032) (x86_64-linux-gnu-gcc-12 (Ubuntu 12.3.0-1ub…
-
When attempting to run the `build-linux_RK3588.sh` script in the `rknn-cpp-Multithreading` project, the following error occurs:
```
orangepi@orangepi5b:~/Downloads/rknn-cpp-Multithreading-main$ sh…
-
rknn.build()
E build: The input 0 of TopK('/model.23/TopK') need to be constant! It will cause the graph to be a dynamic graph! Remove TopK('/model.23/TopK') manually and try again!