Comments (11)
Hi @zesty4 thanks for reporting this, we'll look into it.
To help us diagnose the problem, what options have you used when building ArmNN? Which modules have you built, out of Compute Library OpenCL, Compute Library NEON, ArmNN Tensorflow Parser, and ArmNN Caffe Parser?
Many thanks,
Matthew
from armnn.
Hi Matthew ,
I used the ndk16b build version,
In version arm_compute_library_18.05, I gave the CAFFE_PARSER option.
arm_compute_library has tested neon, neon + cl, and cl versions, but has seen errors in the last posting message.
However, we have succeeded Unitests on the hikey-960 board and are conducting the yolo-> caffe model convert.
If you check the above,
Thank you.
from armnn.
Hi @zesty4 ,
We've built ArmNN with Caffe Parser, Tensorflow Parser, Compute Library OpenCL & NEON and Android NDK r14 and succeeded in running the Unit Tests program on Mate 10.
Could you please try using the steps mentioned https://github.com/ARM-software/armnn/blob/master/BuildGuideAndroidNDK.md and let us know if they work for you.
Thanks,
Surabhi
from armnn.
Hi Surabhi,
Quick response Thank you.
The way you told me is similar to the builder tree I did.
However, the ACL library uses a prebuilt version, and the suspicion is the boost part, and I will inform you by testing again (S9 / MATE) with the method that I gave.
from armnn.
I followed the https://github.com/ARM-software/armnn/blob/master/BuildGuideAndroidNDK.md
however, compiler gives following error:
*/toolchain/aarch64-linux-android-ndk-r16b/bin/../lib/gcc/aarch64-linux-android/4.9.x/../../../../aarch64-linux-android/bin/ld: libarmnnUtils.a(Logging.cpp.o): undefined reference to symbol '__android_log_write'
*/toolchain/aarch64-linux-android-ndk-r16b/bin/../sysroot/usr/lib/liblog.so: error adding symbols: DSO missing from command line
clang50++: error: linker command failed with exit code 1 (use -v to see invocation)
these solutions (https://stackoverflow.com/questions/4455941/undefined-reference-to-android-log-print) don't work
what is the problem?
from armnn.
Hi @pcub,
Thanks for pointing this out, we'll fix the documentation in our future release.
As a workaround, when building ArmNN, if you replace -DCMAKE_SYSTEM_NAME=Linux with -DCMAKE_SYSTEM_NAME=Android, the error goes away.
I hope this helps,
Surabhi
from armnn.
It does not help
from armnn.
Hi pcub,
Could you provide some more information with the error you are currently getting? Surabhi was able to get this working by changing the -DCMAKE_SYSTEM_NAME=Linux
to -DCMAKE_SYSTEM_NAME=Android
Thanks,
Telmo
from armnn.
Hi @pcub,
Did you manage to solve the problem? Let me know if you need further help on this.
Thanks,
Surabhi
from armnn.
Thanks guys, currently I am not working on that, I will inform if I need to work on that part.
from armnn.
Hi @pcub thank you, please reopen this ticket or create a new issue if you have any more problems.
from armnn.
Related Issues (20)
- Unsupported Operation "Transpose" in armNN::OnnxParser while loading the onnx model file (in the goal to run inference) HOT 8
- Build Issues -Werrors on armbian 24 HOT 1
- nvalid attempt to construct ConstTensor from non-constant TensorInfo HOT 1
- Profiler service warnings seen in ArmNN v24.02 HOT 4
- Does ExecuteNetwork support "GpuAcc" runtime ? HOT 13
- Running YOLOv5 ONNX model with onnx parser of armnn fails with unsupported operation HOT 2
- Crash when support ArmNN AIDL backend based on a shim over the NNAPI Support Library
- Crash when support ArmNN AIDL backend based on a shim over the NNAPI Support Library HOT 2
- Unitests failed HOT 3
- understanding the onnx parser HOT 2
- Whisper tflite doesn't work HOT 4
- Error compiling `OnnxMnist-Armnn.cpp` HOT 2
- How to set priority of the application running on GPU? HOT 2
- Onnx Parser: Function AddConvLayerWithDepthwiseConv with bias has logical error HOT 1
- memory alignment HOT 1
- Build-tool failure due to unaddressed -Werror=conversion HOT 3
- Arm NN Build Tool does not support 32-bit ARM v7 HOT 1
- UnidirectionalSequenceLSTMLayer's inferShape is wrong written! HOT 1
- `clGetEventProfileInfo` raises error in `ClConvolution2dWorkload` HOT 5
- Unable to execute GPT-2 onnx model HOT 6
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 armnn.