Open fasih0001 opened 4 weeks ago
You didn't follow the instructions on the docs/YOLOv5.md
.
I actually did follow the instructions, still this error occurs.
You need to generate the onnx file using the exporter file available on this repo. And generate the engine from the onnx file you exported.
I used the same yolov5 configuration files provided in this https://github.com/marcoslucianops/DeepStream-Yolo.git with my own custom trained yolov5. Initially, I exported the .pt weight file to .onnx using the export.py file in the official ultralytics yolov5 github reepository and using the following settings:
Then the created file best.onnx was converted to the .engine file format using the following command:
I have updated the configuration files respectively as follows: config_infer_primary_yoloV5.txt
deepstream_app_config.txt
When I ran it with the following configurations using the command:
The following segmentation fault occured:
Can someone suggest a fix to this problem as I am unable to understand what is causing the Segmentation fault error?