Thank you for your reply.
I have tried both methods and I have also done a comparison.
original network: 0.062 sec
tensorrt network FP16(frozen meta graph and checkpoint): 0.063 sec
tensorrt network FP16(SavedModel): 0.073 sec
My result is getting worse.
I confirmed that the pb model is correct.
I am running face feature capture on Nvidia Xavier, JerryJia is used GV100 with tensor cores.
My TensorRT version is 5.0.3
TF-TRT will fallback implementation into TensorFlow if a layer is not supported.
Would you mind to profile how many layers in your model is accelerated with TensorRT first?
If the ratio is too small, the overhead to switch frameworks may even decrease the performance.
Ex. TF → TRT → TF → TRT → TF → TRT → TF → TRT → TF
Thank you for your reply.
Is there any tool or method that allows me to get the converted layer?
Or is the message displayed on the terminal at the time of conversion the conversion content?