This thread has been locked.

If you have a related question, please click the "Ask a related question" button in the top right corner. The newly created question will be automatically linked to this question.

TDA4VM: TVM/Neo-AI-DLR::getting an error , while Inferring with TVM runtime for host(PC)

Part Number: TDA4VM

Dear TI team ,

         I was getting below error , when I am trying to infer the segmentation model using t"est_tidl_j7_deploy.py" script for "Host" - 

Error : TVMError: Cannot open libvx_tidl_rt.so! libvx_tidl_rt.so: cannot open shared object file: No such file or directory" , even though required file is located in ${HOME}/ti-processor-sdk-rtos-j721e-evm-

07_01_00_11/tidl_j7_01_03_00_11/ti_dl/rt/out/J7/A72/LINUX/release.

Kindly help us to resolve the error . Thanks

SDK: ti-processor-sdk-rtos-j721e-evm-07_01_00_11

TVM version: REL.TIDL.J7.01.03.00.11

OS : Ubuntu 18.04

Steps followed for building and inference : ${HOME}/ti-processor-sdk-rtos-j721e-evm-07_01_00_11/tidl_j7_01_03_00_11/ti_dl/docs/user_guide_html/md_tidl_osr_tvm_tidl.html

  • Hi,

        The libvx_tidl_rt.so version you are looking at is built for Arm A72.

        For host emulation, you need to the version built for x86.  It should be in the "ti_dl/rt/out/PC/x86_64/LINUX/release/".  Point environment variable LD_LIBRARY_PATH to this directory, so that the inference can find this shared library.

    -Yuan