TeresaARM

Hi @TheChosenStranger, Thank you very much for your contribution to ArmNN, we would really love to review it and merge it. However, instead of a pull request, we expect a...

Hi @TheChosenStranger I see your review in gerrit, but it only has a commit message: https://review.mlplatform.org/c/ml/armnn/+/7659 you can amend that review and add the code, so that we can run...

Hi @Rahn80643, thank you very much for your comment. which backend are you using when you run ArmNN, CpuAcc, GpuAcc or CpuRef?

Hi @Rahn80643, could you give it a go to CpuRef? and see if the results are closer to TensorFlow? The performance will be worse than CpuAcc and GpuAcc, as CpuRef...

Hi @Saikatsaha1996, which version of armnn and android-nn-driver are you using? Regards

Hi, are you following this guide: https://github.com/ARM-software/armnn/blob/branches/armnn_22_02/BuildGuideAndroidNDK.md ?

Hi, please try this patch: https://review.mlplatform.org/c/ml/armnn/+/7393 Regards

Hi, that got fixed here: https://review.mlplatform.org/c/ml/armnn/+/7336 (this is already merged in the main branch, but not part of 22.02, it will be part of 22.05) Could you please apply that...

Hi @Saikatsaha1996 , to build without tensorflow, you should do what you are doing, it is the default. to build with tensorflow, you could use the script [get_tensorflow.sh](https://github.com/ARM-software/armnn/blob/branches/armnn_22_02/scripts/get_tensorflow.sh) and set...

Hi @Saikatsaha1996, so, your last screenshot is setting `-DTENSORFLOW_ROOT=` and your second last, uses the same command but without setting `-DTENSORFLOW_ROOT=` ? or you changed something different? are you unblocked...