NVIDIA Developer Forums

TF_TRT unsupported Constant Type

AI & Data Science Deep Learning (Training & Inference) TensorRT

tom.huang January 18, 2019, 1:33am 3

Hi,

Which TRT version should I use to compile TF 1.12, in order to solve this problem.

Topic		Replies	Views	Activity
[TFTRT 4.0.1.6] TFTRT 4.0.1.6 optimize Inception i3d network failure on FP32 mode TensorRT	6	1224	September 25, 2018
Does TensorRT 4.0 support layers for models trained with Keras framework (TensorFlow backend) TensorRT	8	1862	October 8, 2018
TF-TRT failing to convert with INT32 values TensorRT	8	1151	April 15, 2019
No improvement in inference performance after Opt. with TensorRT TensorRT	6	1313	April 15, 2020
Error while optimizing frozen Tensorflow graph TensorRT	4	1248	February 26, 2019
Keeping a tensor that only consists of constant values while converting Tensorflow Graph_Def model to TensorRT model TensorRT tensorrt , tensorflow	5	668	August 26, 2020
Conversion with no speed improvement, TRT-TF TensorRT	2	1194	October 12, 2021
TRT issue with Graph Creation - TRTEngineOP TensorRT	12	3339	November 4, 2019
Don't get any 'TRTEngineOp' after optimizing model via TensorRT in Jeton TX2 TensorRT	17	3823	October 12, 2021
Create inference graph failed on Agx Xavier Jetson AGX Xavier	32	2398	October 18, 2021