[Inference Error] Segmentation Fault in Jetson Nano

Hello, Thanks for the great project for running yolo series with deepstream library. I'm experiencing an error when trying to perform inference using Deepstream-yolo on a Jetson Nano (4GB).

Problem Description The main issue seems to appear Deepstream library building error and an error related to the Jetson Nano device. When attempting to perform inference, the system crashes with a "Segmentation Fault".

Steps to Reproduce The problem occurs when I perform the following steps:

Convert a Pytorch model to ONNX using Ultralytics frameworks.
- The conversion is successful when using the Ultralytics framework; however, it fails when using the Deepstream-yolo framework. Thus, we are using the previous one.
Attempt Deepstream inference.
- Running the provided deepstream config txt
  - 'deepstream-app-config.txt' results in a Segmentation Fault.
  - 'config-infer-yolov8.txt' also results in a Segmentation Fault.

Tried Solutions I have tried several solutions to mitigate the problem:

I have attempted using different model conversion frameworks.
I have followed the Deepstream-yolo tutorial carefully to ensure the steps were followed correctly.
I have tried various configurations in the Deepstream-app and yolov8 inference configuration files. Unfortunately, none of these steps have resolved the issue.

Request I would greatly appreciate any suggestions or guidance on how to fix these issues. I'm particularly interested in understanding why the system crashes with a Segmentation Fault when attempting inference.

Environment TensorRT Version: 8.2.1.9+cuda10.2 GPU Type: Jetson Nano Tegra210 JetPack : 4.6.1 CUDA Version: 10.2 CUDNN Version: 8.2.1+cuda10.2 arm64 Operating System + Version: Ubuntu 18.04 Python Version (if applicable): 3.8 (conda virtual enviroment) TensorFlow Version (if applicable): NA PyTorch Version (if applicable): 1.11.0

Configuration file deepstream_app_config.txt

[application]
enable-perf-measurement=1
perf-measurement-interval-sec=5

[tiled-display]
enable=1
rows=1
columns=1
width=1280
height=720
gpu-id=0
nvbuf-memory-type=0

[source0]
enable=1
type=3
#uri=file:///opt/nvidia/deepstream/deepstream/samples/streams/sample_1080p_h264.mp4
uri=file:///home/bass/DeepStream-Yolo/test_video/10sec_1080p.mp4
num-sources=1
gpu-id=0
cudadec-memtype=0

[sink0]
enable=0 #1
type=2
sync=0
gpu-id=0
nvbuf-memory-type=0

[osd]
enable=1
gpu-id=0
border-width=5
text-size=15
text-color=1;1;1;1;
text-bg-color=0.3;0.3;0.3;1
font=Serif
show-clock=0
clock-x-offset=800
clock-y-offset=820
clock-text-size=12
clock-color=1;0;0;0
nvbuf-memory-type=0

[streammux]
gpu-id=0
live-source=0
batch-size=1
batched-push-timeout=40000
width=1920
height=1080
enable-padding=0
nvbuf-memory-type=0

[primary-gie]
enable=1
gpu-id=0
gie-unique-id=1
nvbuf-memory-type=0
config-file=config_infer_primary_yoloV8.txt

[tests]
file-loop=0

config_infer_primary_yoloV8.txt

[property]
gpu-id=0
net-scale-factor=0.0039215697906911373
model-color-format=0
#onnx-file=yolov8n_best.onnx
model-engine-file=yolov8n_best.engine
#int8-calib-file=calib.table
labelfile-path=labels.txt
batch-size=1
network-mode=0
num-detected-classes=1
interval=0
gie-unique-id=1
process-mode=1
network-type=0
cluster-mode=2
maintain-aspect-ratio=1
symmetric-padding=1
#force-implicit-batch-dim=1
#workspace-size=1000
parse-bbox-func-name=NvDsInferParseYolo
#parse-bbox-func-name=NvDsInferParseYoloCuda
custom-lib-path=nvdsinfer_custom_impl_Yolo/libnvdsinfer_custom_impl_Yolo.so
engine-create-func-name=NvDsInferYoloCudaEngineGet

[class-attrs-all]
nms-iou-threshold=0.45
pre-cluster-threshold=0.25
topk=300

marcoslucianops / DeepStream-Yolo

[Inference Error] Segmentation Fault in Jetson Nano #408