failed to get func NvDsInferParseCustomYolo pointer

[fastyangmh]

@marcoslucianops Thank you very much for creating the great project. When I try to use yolor_csp pretrained model in docker, it encountered this error. My container image uses nvcr.io/nvidia/deepstream:6.1-triton. Please help, thank you.

0:00:39.562139762  7770 0x55f1befea460 ERROR                nvinfer gstnvinfer.cpp:640:gst_nvinfer_logger:<primary_gie> NvDsInferContext[UID 1]: Error in NvDsInferContextImpl::initResource() <nvdsinfer_context_impl.cpp:769> [UID = 1]: Detect-postprocessor failed to init resource because dlsym failed to get func NvDsInferParseCustomYolo pointer
ERROR: nvdsinfer_context_impl.cpp:1065 Infer Context failed to initialize post-processing resource, nvinfer error:NVDSINFER_CUSTOM_LIB_FAILED
ERROR: nvdsinfer_context_impl.cpp:1271 Infer Context prepare postprocessing resource failed., nvinfer error:NVDSINFER_CUSTOM_LIB_FAILED
0:00:39.591324265  7770 0x55f1befea460 WARN                 nvinfer gstnvinfer.cpp:846:gst_nvinfer_start:<primary_gie> error: Failed to create NvDsInferContext instance
0:00:39.591334724  7770 0x55f1befea460 WARN                 nvinfer gstnvinfer.cpp:846:gst_nvinfer_start:<primary_gie> error: Config file path: /opt/nvidia/deepstream/deepstream-6.1/sources/objectDetector_Yolo/config_infer_primary_yoloR.txt, NvDsInfer Error: NVDSINFER_CUSTOM_LIB_FAILED
[NvMultiObjectTracker] De-initialized
** ERROR: <main:716>: Failed to set pipeline to PAUSED
Quitting
ERROR from primary_gie: Failed to create NvDsInferContext instance
Debug info: gstnvinfer.cpp(846): gst_nvinfer_start (): /GstPipeline:pipeline/GstBin:primary_gie_bin/GstNvInfer:primary_gie:
Config file path: /opt/nvidia/deepstream/deepstream-6.1/sources/objectDetector_Yolo/config_infer_primary_yoloR.txt, NvDsInfer Error: NVDSINFER_CUSTOM_LIB_FAILED
App run failed

[marcoslucianops]

Did you compile the nvdsinfer_custom_impl_Yolo?

[fastyangmh]

The problem is solved. I modify your config_inferprimary.txt instead of the official config_inferprimary.txt. Thank you.