Tool/software:
Hi, I'm trying to use the edge ai-tools library for model compilation. I'm using an Ubuntu 22.04 WSL environment and the rel_10_00 TI library version.
I installed the docker using the env variable SOC=am68pa and TIDL_TOOLS_TYPE=GPU.
It seems that the installation went well without any problems, but when I try to make an inference with onnx model I obtain this result:
Accelerator Fatal Error: This file was compiled: -acc=gpu -gpu=cc50 -gpu=cc60 -gpu=cc60 -gpu=cc70 -gpu=cc75 -gpu=cc80 -gpu=cc80 -gpu=cc86 -gpu=cc90 -acc=host o
Rebuild this file with -gpu=cc89 to use NVIDIA Tesla GPU 0
File: /sdk/OSRT/Build/J721E/c7x-mma-tidl/ti_dl/algo/src/tidl_conv2d_base.c
Function: _Z24TIDL_refConv2dKernelFastILi3EhsilEvPT0_PT1_PT2_PT3_S7_S7_iiiiiiiiiiiiiiiiiiiiiiiiii:463
Line: 473
What is the problem?
