-
pth>onnx:
env：pc 、python3.7、onnx=1.6.0、torch=1.8.1
onnx>rknn:
env：rk3399+rk1808、python3.7、onnx=1.6.0、rknn_toolkit=1.6.0、torch=1.6.0
Related file links：链接：https://pan.baidu.com/s/1C6hSnbGKn…
-
W rknn-toolkit version: 1.7.5
W Verbose file path is invalid, debug info will not dump to file.
D Using CPPUTILS: True
--> config model
done
--> Loading model
I Start importing pytorch...
./mod…
-
源码：
```python
import numpy as np
import cv2
from rknn.api import RKNN
import torchvision.models as models
import torch
if __name__ == '__main__':
model = './hybridnets.pt'
input_s…
-
**Area of Concern**
- [ ] Server
- [x] Behaviour of one or more Modules [Object Detection Yolo v5 RKNN]
- [ ] Installer
- [ ] Runtime [e.g. Python3.7, .NET]
- [ ] Module packages [e.g. PyTorch)
…
-
### Description
iOS Notifications not occurring for this blueprint for iOS anymore. I have other android devices that are still getting the alerts with snapshots, but none of my iOS devices are getti…
-
Hi, I am using a `TimeDistributed` Layer in model which has an input shape of {10, 150, 180, 3} (10 frames of (w:150, h:180, colors : 3 ) ).
Since my device support a maximum of 4 dimensions, I w…
-
请问一下大佬，我在运行examples/rknn_yolov5_demo/convert_rknn_demo/yolov5/onnx2rknn.py这个文件，到Building model那一步就开始报错了，报错提示为下面的内容，请问我要如何处理这个报错。
E Catch exception when building RKNN model!
E Traceback (most recent …
-
同样的模型，input channel==1转换失败，input channel==3转换成功。失败信息：
D:\Users\xxxxx\Miniconda3\envs\rknn_v1.75\lib\site-packages\numpy\_distributor_init.py:32: UserWarning: loaded more than 1 DLL from .libs:
D…
-
请教下rk官方有试过部署depthanythingv2吗？我看了下网上有人尝试转换成功了而且用python的rknn跑通了，但是我尝试用python3.11的rknn_toolkit2-2.1.0+708089d1-cp311-cp311-linux_x86_64.whl转换没有成功，跪求指点
-
A transformed yolo model does Object Detection on RKNN, there is no reason we can't just support running this same model without the help of the NPU on other platforms, albeit, at worse performance. I…