apxlwl / mnn-yolov3 Goto Github PK
View Code? Open in Web Editor NEWMNN demo of Strongeryolo, including channel pruning, android support...
MNN demo of Strongeryolo, including channel pruning, android support...
@wlguan 作者您好,我直接运行pb.py转换了仓库中的checkpoint:weights/yolo.ckpt-60-0.7911为pb模型,并转换为mnn模型。然后放到android-demo中替换掉原有的voc544.mnn,结果安卓端APP运行时出现Create Net Failed错误,原有android-demo中的voc544.mnn和voc320_quant.mnn在安卓端运行是没有问题的。
另外,我用v3文件夹中的代码训练了自己的检测模型,并将checkpoint也转化为mnn模型,替换掉android-demo中掉原有的voc544.mnn,也出现Create Net Failed错误。
所以想问下,能否麻烦您再测试下您readme中关于这套代码的使用流程啊,小白按照您的步骤遇到了严重的问题,卡了好几天了试了各种方式都没解决。谢谢您了 @wlguan
如题!
thank you for your yolov3 detection deploy example ,when i compile and run simulate on my android-studio , there are some warning,
Cannot build selected target ABI: x86, no suitable splits configured: armeabi-v7a;
ABIs [x86] set by 'android.injected.build.abi' gradle flag contained 'X86' not targeted by this project.
Can you give a detail information of your config in android studio ? something like NDK version the simulator config ,MNN version.
你好,我用其他其他代码训练出的模型,然后转化成mnn的模型,那么这个模型可以用这份代码进行推理吗
我尝试用MNN量化,会报以下错误,你有没有遇到这个问题
MNN/tools/quantization/calibration.cpp:189: Check failed: inputTensorStatistic != _featureInfo.end() ==> input tensor error!
我的配置文件这么来写 preprocessConfig.json,请问你是怎么写的,先谢了!
{
"format":"RGB",
"mean":[
0.0,
0.0,
0.0
],
"normal":[
0.00392156,
0.00392156,
0.00392156
],
"width":544,
"height":544,
"path":"/path/images",
"used_image_num":500,
"feature_quantize_method":"KL",
"weight_quantize_method":"MAX_ABS"
}
看了大哥的c++以及Python运行666
,由于没有使用过java,请问安卓端的运行的能够仔细说一下吗?谢谢
您好,请问下您有尝试YOLOV3基于MNN进行训练量化吗?
谢谢。
A declarative, efficient, and flexible JavaScript library for building user interfaces.
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
An Open Source Machine Learning Framework for Everyone
The Web framework for perfectionists with deadlines.
A PHP framework for web artisans
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
Some thing interesting about web. New door for the world.
A server is a program made to process requests and deliver data to clients.
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Some thing interesting about visualization, use data art
Some thing interesting about game, make everyone happy.
We are working to build community through open source technology. NB: members must have two-factor auth.
Open source projects and samples from Microsoft.
Google ❤️ Open Source for everyone.
Alibaba Open Source for everyone
Data-Driven Documents codes.
China tencent open source team.