Comments (4)
OK, get it. NOW not support for converting Prelu in ONNX model,will be added later! (Appreciate that You contribute to this work 😊)
from mnn.
I hava compiled the mnn converter successful. When i convert a onnx model to mnn use :
./MNNConvert -f ONNX --modelFile mobilefacenet.onnx --MNNModel mobilefacenet.mnn --bizCode MNN
and i face this error:
MNNConverter Version: 0.0.0.1 - MNN @ 2018Start to Convert Other Model Format To MNN Model...
[09:36:17] /home/yuanhao/osc/MNN/tools/converter/source/onnx/onnxConverter.cpp:29: ONNX Model ir version: 3
terminate called after throwing an instance of 'Error'
what(): [09:36:17] /home/yuanhao/osc/MNN/tools/converter/source/onnx/onnxConverter.cpp:83: Check failed: opConverter ==> MNN Converter NOT_SUPPORTED_OP: [ PRelu ]
Aborted (core dumped)How can i solve this problem, thanks!
Hi @nullian ,
How (or where) did you get mobilefacenet.onnx model. I have tried to convert original MXNET models (from insightface) to ONNX models but not successful.
Could you please send me your mobilefacenet.onnx model?
Many thanks.
from mnn.
Hi, may I ask how does the Conv op converter registered? Since the Convolution only supported caffe and Tensorflow.
how does onnx conv parsed?
from mnn.
PRELU OP not supported when cvting from TFLITE model
from mnn.
Related Issues (20)
- 无法安装python api pymnn HOT 2
- CONV_TRANSPOSE反卷积算子不支持fp16格式,希望增加支持 HOT 1
- windows编译库太大,按照官网文档编译 HOT 1
- 是否支持鸿蒙 next 系统编译呢 HOT 1
- MNN CUDA后端benchmark运行时间为零且无其他反馈 HOT 4
- ubuntu22.04系统,硬件为i7-12700,对yolo8n模型进行推理。为什么利用AVX512指令集没有推理加速效果, HOT 5
- avx512编译失败 HOT 1
- 同一个模型,2.8.0版本模型转换失败而2.1.0转换成功 HOT 3
- MNN with OpenGL getting segmentation fault
- Resize, padding image to specific size using MNN ImageProcessig HOT 3
- UHDM模型cuda 显存比ORT大很多,耗时是ort的3倍 HOT 1
- can not convert this model to MNN
- MNN有没有windows x86编译好的库
- [Regression]: Performance degradation in MNN 2.8.1 / 2.8.0 for Android CPU HOT 7
- Convert this onnx model to MNN failed
- funasr 模型转换失败 Floating point exception (core dumped) HOT 1
- RK3588 (A76+A55) + Ubuntu 22.04 + MNN_ARM82=ON: "MNNAbsMaxFP16.S:106: Error: operand 1 must be a SIMD vector register" HOT 4
- quantized.out int8量化后的模型在CPU后端运行resnet50出错(已更新到最新commit版本) HOT 8
- 静态shape转换后的模型模型,是否可以计算动态shape的输入 HOT 1
- Windows x64下使用expr进行较大规模卷积计算时崩溃
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 mnn.