Hi ,
I working on Imx8 plus board. (zeus-5.4.70-2.3.0).
I trying to execute my models with Tensorflow Lite (version imx_5.4.70_2.3.0 ) via XNNPack delegate. looks like in Makefile there is default value CXXFLAGS += -DTFLITE_WITHOUT_XNNPACK
Is there a reason XNNPack disabled?
解決済! 解決策の投稿を見る。
Hello,
For TFLITE_WITHOUT_XNNPACK, it's disabled because not built with Makefile as below.
commit b9b739285e46ca0bdc54641bf7351463cf8aa928
Author: Terry Heo <terryheo@google.com>
Date: Thu Mar 19 05:03:41 2020 -0700
Fix Makefile build
Since XNNPACK isn't buildable with Makefile, it should be disabled for Makefile build.
For 1# and 3#, BSP 5.10.9_1.0.0 is embedded with Tensorflow v2.4 and XNNPACK is enabled by default.
As for 2#, from 5.10.9 user guide (IMXMLUG), XNNPACK goes through CPU but not NPU.
Regards
Hello dnozik,
The XNNPack is disable in the actual version of tensorflow lite, however with the TensorFlow 2.3 release, XNNPACK backend is included with the pre-built TensorFlow Lite binaries for Linux and Android BSP.
Regards
Hi ,
thanks for reply .
1. Where can I find tensorflow lite prebuild library.
2.Does this prebuild library will also support IMX8 plus NPU delegate ?
3.We building all our libraries as part of image yocto recipe build , is there recipe with tensorflow branch with NNAPI and XNNPack for NPU/CPU ?
thanks
Hello,
For TFLITE_WITHOUT_XNNPACK, it's disabled because not built with Makefile as below.
commit b9b739285e46ca0bdc54641bf7351463cf8aa928
Author: Terry Heo <terryheo@google.com>
Date: Thu Mar 19 05:03:41 2020 -0700
Fix Makefile build
Since XNNPACK isn't buildable with Makefile, it should be disabled for Makefile build.
For 1# and 3#, BSP 5.10.9_1.0.0 is embedded with Tensorflow v2.4 and XNNPACK is enabled by default.
As for 2#, from 5.10.9 user guide (IMXMLUG), XNNPACK goes through CPU but not NPU.
Regards