Other Parts Discussed in Thread: AM69A
Tool/software:
Dear expert team,
I am trying to run inference on an ONNX model compiled with edgeai-tidl-tools on the AM69A. When attempting to execute inference using session.run with ONNXRuntime-tidl on the AM69A, I encounter the following error:
libtidl_onnxrt_EP loaded 0xaaab218f5e40 Final number of subgraphs created are : 1, - Offloaded Nodes - 488, Total Nodes - 488 APP: Init ... !!! APP_LOG: ERROR: Unable to open /dev/mem !!! APP_LOG: ERROR: Unable to map memory @ 0xa90000 of size 512 bytes !!! APP_TIMER: ERROR: Unable to mmap gtc (0xa90000 of 512 bytes) !!! APP: ERROR: Global timer init failed !!! APP_LOG: ERROR: Unable to open /dev/mem !!! APP_LOG: ERROR: Unable to map memory @ 0xaf000000 of size 262144 bytes !!! APP: ERROR: Log writer init failed !!! APP_LOG: ERROR: Unable to open /dev/mem !!! APP_LOG: ERROR: Unable to map memory @ 0xb1000000 of size 3288576 bytes !!! APP: ERROR: File IO writer init failed !!! APP: Init ... Done !!! TIDL_RT_OVX: ERROR: Verifying TIDL graph ... Failed !!! TIDL_RT_OVX: ERROR: Verify OpenVX graph failed MEM: ERROR: Failed to free memory at virt addr = 0x627573204c444954 !!!
Do I need root privileges to perform model inference? Additionally, I believe this issue is related to the following thread, so I am including it here for reference.
regards,
Koki
