search

terryky / tflite_gles_app

GPU accelerated deep learning inference applications for RaspberryPi / JetsonNano / Linux PC using TensorflowLite GPUDelegate / TensorRT
MIT License
488 stars 130 forks source link

build on ubuntu18.04 with cuda #18

Open Techieali opened 3 years ago

Techieali commented 3 years ago

hi terryky, first of all wonderful work, and thanks a lot for this, previously i build this project on jetson nano and a linux pc and both was done successfully.

right now i trying to build the same on a machine with cuda and cudnn

but i am getting this error Could not find any NvInferVersion.h matching version '7.2' in any subdirectory:

system spec : cuda 11.2, cudnn 8.1, tensorRT 7.2 thanks in advance

Techieali commented 3 years ago

resolve this issues by copying the include file from tensorRT folder to usr/local/cuda-11.2 but now ended up with a flatbuffer issue and compilation terminated

Screenshot from 2021-03-11 18-07-50

laolihaile commented 3 years ago

I have the same problem. Have you solved it?