Comments (7)
@rpvelloso Look at my reply above
from rknpu2.
Hello, is there a way to address this issue? @rpvelloso
Don't know. I'm still waiting for an answer...
Okay, I have encountered the same problem as you and need to run multiple models in sequence, but it has not been successful so far. The later models will close the previously opened models
from rknpu2.
Hello, is there a way to address this issue? @rpvelloso
Don't know. I'm still waiting for an answer...
Okay, I have encountered the same problem as you and need to run multiple models in sequence, but it has not been successful so far. The later models will close the previously opened models
That's what I was afraid, I haven't got a board because they didn't answer me. I guess I'll look up other NPU manufacturers
Okay, I'll see if there are any other ways to achieve it. Good luck!
from rknpu2.
Hello, is there a way to address this issue? @rpvelloso
from rknpu2.
Hello, is there a way to address this issue? @rpvelloso
Don't know. I'm still waiting for an answer...
from rknpu2.
Hello, is there a way to address this issue? @rpvelloso
Don't know. I'm still waiting for an answer...
Okay, I have encountered the same problem as you and need to run multiple models in sequence, but it has not been successful so far. The later models will close the previously opened models
That's what I was afraid, I haven't got a board because they didn't answer me. I guess I'll look up other NPU manufacturers
from rknpu2.
I have implemented a method of loading two models simultaneously: in the create method, regarding the ctx attribute during initialization, each model should correspond to a different ctx object, so that multiple models can be successfully initialized. As for the sequential reasoning of multiple models, I have not yet verified this aspect.
from rknpu2.
Related Issues (20)
- 多核推理性能下降 HOT 1
- 怎么用npu跑stable diffusion? HOT 1
- 导出rknn模型出现错误
- docker上显示无法找到npu HOT 2
- Meet unsupported input_2_t dtype for matmul
- rknn_init with flag RKNN_FLAG_SHARE_WEIGHT_MEM failed
- RV1106 PaddleOCRV2 检测模型输出为空 HOT 1
- Unsupported operator "ReduceSumSquare" // 不支持的运算符"ReduceSumSquare"
- 有多模型推理的例子吗
- onnx模型转rknn离线模型,中途没报错,但是模型没转成功。
- rknn_set_core_mask(m_ctx, RKNN_NPU_CORE_1)后,NPU飙升到100%,识别失败,最后系统卡死 HOT 3
- RKNPU 矩阵乘法性能远低于标称值,水分很大!
- RKNPU 1.6.0 - Core 2 and Core 3 can not work HOT 4
- rknn yolov5 android
- rknn_destory()函数释放模型内存不彻底
- 去量化矩阵乘法 有没有example啊
- can not success start rknn_server
- Failed to call RockChipRga interface
- BUG Report: rknpu2/examples/rknn_yolov5_demo/src/postprocess.cc
- 关于适用paddle里面FastDeploy推理rknn的问题
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 rknpu2.