Pablo Marquez Tello

Hi @lyz9801 Could you please share the command you used to build the program? Please see the documenation on how to build the examples: https://arm-software.github.io/ComputeLibrary/latest/how_to_build.xhtml#S1_2_2_examples Hope this helps

Hi @lyz9801 > I havn't built the program yet, just directly use the library in the hompage , the linked address is https://github.com/ARM-software/ComputeLibrary/releases/download/v22.05/arm_compute-v22.05-bin-android-arm64-v8a-cl.tar.gz Could you please elaborate and explain how...

Hi @xdliangdi Could you please share the complete error you get and the version of the NDK you're using?

Hi @xdliangdi What version of NDK are you using? The error shows that your compiler does not support SVE, this could be either because the NDK you use is too...

Hi @asharma-ampere The best option is to use ArmNN's ExecuteNetwork tool to run a tflite model through ACL. Please see https://github.com/ARM-software/armnn/tree/branches/armnn_22_05/tests/ExecuteNetwork Using ExecuteNetwork you can run tflite models as shown...

Hi @asharma-ampere ACL does not provide a solution out of the box to go from a tensorflow model to an ACL graph example. The best way to run a tflite...

Hi @asharma-ampere The problem is fixed with the following ArmNN patch: https://review.mlplatform.org/c/ml/armnn/+/7944 Hope this helps.

Hi @abhajaswal Could you please try with the latest release 22.05? There have been some improvements in the startup time since 20.02. In general, both for CPU and GPU, the...

Hi @abhajaswal Glad to hear you improved the load time using prebuilt opencl kernels. >This .bin file i will have to generate for N number of models , so wont...

Hi @TheChosenStranger please open an issue and we will help you to fix the problem with the credentials.