Running a Quantized UINT8 lstm model generates FlexTensor Error

Viewed 56

Facing Error On running lstm model

ERROR: Fallback unsupported op 32 to TfLite 
Explicitly applied EXTERNAL delegate, and the model graph will be partially executed by the delegate w/ 13 delegate kernels. 
ERROR: Regular TensorFlow ops are not supported by this interpreter. Make sure you apply/link the Flex delegate before inference.
ERROR: Node number 5 (FlexTensorListFromTensor) failed to prepare.

ERROR: Failed to apply the default TensorFlow Lite delegate indexed at 0.
Failed to allocate tensors! 

For solution i found to compile tensorflow by enabling flex support.
Tried compiling the tensorflow using specific toolchain path.
But to activate support of FlexTensor what changes i need to do in cmakelist & build ?
I know to enable flextensor using bazel Tutorial searching how i can do the same using cmake..

0 Answers
Related