Comments (8)
有更多信息吗?
from rknn-toolkit2.
推理报错没有更多的信息,init runtime成功后推理时直接Segmentation fault:
D RKNN: [02:20:24.071] Total Weight Memory : 10767872
D RKNN: [02:20:24.071] Total Internal Memory: 15777792
D RKNN: [02:20:24.071] Total Memory: 26545664
D RKNN: [02:20:24.072] Total Allocate Memory: 31314216
--> Init runtime environment done
--> inference
D RKNN: [02:20:24.151] argb mode info: chw: [3, 384, 384], stride: 384, tile chw: [3, 384, 74], startxyz: [0, 0, 0]
D RKNN: [02:20:24.152] argb mode info: chw: [3, 384, 384], stride: 384, tile chw: [3, 384, 74], startxyz: [0, 74, 0]
D RKNN: [02:20:24.152] argb mode info: chw: [3, 384, 384], stride: 384, tile chw: [3, 384, 74], startxyz: [0, 148, 0]
D RKNN: [02:20:24.152] argb mode info: chw: [3, 384, 384], stride: 384, tile chw: [3, 384, 74], startxyz: [0, 222, 0]
D RKNN: [02:20:24.152] argb mode info: chw: [3, 384, 384], stride: 384, tile chw: [3, 384, 74], startxyz: [0, 296, 0]
D RKNN: [02:20:24.152] argb mode info: chw: [3, 384, 384], stride: 384, tile chw: [3, 384, 14], startxyz: [0, 370, 0]
D RKNN: [02:20:24.152] normalize target: NPU
D RKNN: [02:20:24.154] Get NPU frequency: 600MHz
Segmentation fault (core dumped)
使用的模型:https://drive.google.com/file/d/1QoZieqroca5cPoChgLbv41_ovaqFCPho/view?usp=sharing
from rknn-toolkit2.
这样暂时看不出问题原因,建议更新最新版本,看是否已经修复该问题
from rknn-toolkit2.
这样暂时看不出问题原因,建议更新最新版本,看是否已经修复该问题
暂时没有看到有更新的版本;此外,尝试更换模型,同样的,模型转换环境:rknn-toolkit2 1.2.0-f7bb160f,推理环境:rknn-toolkit-lite2 1.2.0,在模拟器中可以正常推理,在开发板上推理报错:E RKNN: [06:15:37.184] ERROR: unsuport Equal op in cunrrent
from rknn-toolkit2.
近期将会出新的版本,不过你这里的Equal op还是不支持
from rknn-toolkit2.
rknn-toolkit2支持的操作与实际推理时支持的操作可能存在不对齐的情况是吗
from rknn-toolkit2.
对实际板端推理阶段还不支持,但是toolkit2阶段支持
from rknn-toolkit2.
好的,谢谢
from rknn-toolkit2.
Related Issues (20)
- 能不能将多个onnx切片文件转化为合并一个rknn文件
- RKNN NPU Depth Anything Conversion HOT 3
- Run Multiple Models at the same time on RK3588 HOT 6
- Trouble with install req.txt and whl file for my RK3588
- 为什么QQ 3群加不进去啊
- Unsupport CPU op: ReduceL2 in this librknnrt.so HOT 4
- 自定义GPU算子测试时RKNN内部报错
- ch_ppstructure_mobile_v2.0_SLANet表格识别模型转rknn模型报错 HOT 1
- RK3588 YOLOv8-seg量化异常 HOT 1
- Clarification
- Not a supported wheel on this platform. HOT 1
- RKNN不支持 GatherND HOT 1
- RK3588使用yoloV8的P2-P4层导出的模型,推理不准确
- [rknn result error] rknn result cannot aligned to onnx result
- Issue with Initializing Runtime Environment on Ubuntu PC
- rknntoolkits2.0.0导出yoloworld模型,量化的过程报错
- 请问这是什么问题?
- 离谱,python logging内部变量被你们框架修改了 HOT 2
- Multi-batch support?
- onnx转rknn中出现 Reshape OP is not supported HOT 1
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from rknn-toolkit2.