James Conroy
James Conroy
Hi @MrSherish , Would you mind testing with TF Lite 2.5 please, to eliminate the version you are using as the root cause of the issue? Thanks, James
Hi @liamsun2019 , It's nice to hear that you have achieved correct output through the use of our Arm NN TF Lite Delegate. This is currently the preferred way to...
@liamsun2019 You're correct, both the TF Lite Delegate and TF Lite Parser should have identical results. This suggests that there may be a bug in the TF Lite Parser or...
Hi @steven9046 , Whilst we don't officially support Ubuntu 16.04 anymore, Arm NN should still work on this platform. Could you please build with the latest version of Arm NN...
Hi @liamsun2019 , Many thanks for raising this issue. We no longer support the Arm NN Quantizer since the 21.05 release of Arm NN (May 2021). I'd recommend that you...
No problem :) We support both TF Lite (through the C++ TF Lite Parser API and the C++/Python TF Lite Delegate API) and ONNX (through the C++ ONNX Parser API)...
No bother, thank _you_ for using our software. James
Hi @liamsun2019 @catcor01 is looking into this for you now. We don't have a complete guide for what you want (yet, coming soon!) but Cathal will go through the steps...
Hi ggardet, Thanks for reporting this issue. Could you please provide us with some more information about your environment so we can diagnose this for you. What values are in...
Hi @vn218 , Many thanks for raising this issue. Did you build Arm NN using the build-tool with or without Docker? On a remote machine or on the Odroid board...