Nvinfer aborts when using an NGC .etlt model

[samfarfar]

Please provide complete information as applicable to your setup.

Hardware Platform : GPU
DeepStream Version 6.3
TensorRT Version 530.41.03
NVIDIA GPU Driver Version 535.54.03
When attempting to run the following gst-launch command:
GST_DEBUG=*:3 USE_NEW_NVSTREAMMUX=yes gst-launch-1.0 v4l2src ! videoconvert ! nvvideoconvert ! “vide
o/x-raw(memory:NVMM)” ! streammux.sink_0 nvstreammux name=streammux batch-size=1 ! nvinfer config-file-path=emotions.config uniqu
e-id=15 ! nvvideoconvert ! nvdsosd ! nvvideoconvert ! glimagesink sync=false

that uses the following config file:
[property]
gpu-id=0
net-scale-factor=0.0039215697906911373
tlt-encoded-model=/emotionNet/model.etlt
labelfile-path=/emotionNet/labels.txt
tlt-model-key=nvidia_tlt
batch-size=1
network-mode=0
num-detected-classes=6
gie-unique-id=1
cluster-mode=3
[class-attrs-all]
pre-cluster-threshold=0.2
eps=0.2
group-threshold=1

I receive the following output:

max_fps_dur 8.33333e+06 min_fps_dur 2e+08
Setting pipeline to PAUSED …
0:00:00.371517660 299978 0x55e4169c2e30 INFO nvinfer gstnvinfer.cpp:682:gst_nvinfer_logger: NvDsInferContext[UID 15]: Info from NvDsInferContextImpl::buildModel() <nvdsinfer_context_impl.cpp:2002> [UID = 15]: Trying to create engine from model files
Aborted (core dumped)

I am confused as to why it would just randomly abort without any warnings or errors.

[yuweiw]

1.Could you help to use the gdb tool to do a preliminary debug?
2.You can also refer to the link below to open more log about nvinfer: Add TensorRT Verbose log .

[samfarfar]

Heres the output of the gdb debug:
0:07:28.076214890 310635 0x55555600e950 INFO nvinfer gstnvinfer.cpp:682:gst_nvinfer_logger: NvDsInferContext[UID 15]: Info from NvDsInferContextImpl::buildModel() <nvdsinfer_context_impl.cpp:2002> [UID = 15]: Trying to create engine from model files
Downloading separate debug info for /lib64/libnvinfer_builder_resource.so.8.6.1

Thread 1 “gst-launch-1.0” received signal SIGABRT, Aborted.
__pthread_kill_implementation (threadid=, signo=signo@entry=6, no_tid=no_tid@entry=0)
at pthread_kill.c:44
Downloading source file /usr/src/debug/glibc-2.37-4.fc38.x86_64/nptl/pthread_kill.c
44 return INTERNAL_SYSCALL_ERROR_P (ret) ? INTERNAL_SYSCALL_ERRNO (ret) : 0;

And when i tried to use the verbose log it would abort before displaying anything.

[yuweiw]

There is no update from you for a period, assuming this is not an issue anymore. Hence we are closing this topic. If need further support, please open a new one. Thanks

Do you use the model from our NGC? Could you attach the link?