-
![image](https://user-images.githubusercontent.com/65638983/184795423-7b1e3041-b910-4ffa-a3b6-7b970098c3fe.png)
Hisense Nie, transferred to mobilenet V2, reported an error in the optimization stage, …
-
Vannie.
@Vqnnie
~~----~~
-
Why does the way to handle the value of classScore on NNIE have to be multiplied by SAMPLE_SVP_NNIE_QUANT_BASE (4096) but on coffee there is no need?
-
你好,我把你的代码进行了部分更改,部署到hi3521dv200上,在进行模型推理的时候报错:
[Level]:Error,[Func]:NNIE_Forward [Line]:203 [Info]:Error,HI_MPI_SVP_NNIE_Forward failed!
[Level]:Error,[Func]:NNIE_Forward_From_Data [Line]:331 [Inf…
-
I have converted the model on ubuntu ,and I am able to run the model on Hisi3516 cpu mode ,but when running in a GPU mode ,I am meeting this problems :
./benchmark --modelFile=../../../mindspore…
-
https://github.com/D-evante-n/-d-nnie/pull/1#issuecomment-2080743803_
- [✓ ] @602-1111-**0**5
-
网络多数时候运行是正常的,偶尔会输出远超4096的值。
https://github.com/RaySue/NNIE-lite/blob/daf0dc19f47bc1e286308d137e1e636c2ef98da7/src/nnie_core.c#L272
```
for (n = 0; n < pstNnieParam->astSegData[u32Se…
-
大佬你好,我将yolov4模型转化成了nnie wk文件,利用nnie-lite进行推理的时候,我修改了anchors部分,修改如下:
![image](https://user-images.githubusercontent.com/34532224/103864772-22c23400-50fe-11eb-8805-f5c3c111ee55.png)
请问
![image](https…
-
大佬,可以分享以下您在caffe转nnie时使用的caffe网络模型吗?想确认一下我的是否正确。
-
Hi,大佬们,同样的C++代码和模型,在PC端验证推理结果是正常的,为啥移植到海思平台跑结果就溢出啦,有谁遇到过吗?我交叉编译的方式就是根据文档编译的,模型onnx和caffe的mobilenet v2,两种方式编译的模型在PC端结果都对,就是板端有问题