Nvdspreprocess with custom yolov4_tiny model is giving me error need to solve

Accelerated Computing Intelligent Video Analytics DeepStream SDK
1

Please provide complete information as applicable to your setup.

**• Hardware Platform -------------> GPU
**• DeepStream Version -----------> 7.0
**• TensorRT Version ----------------> 8.6
**• NVIDIA GPU Driver Version -----------> 545

I am using nvpreprocess element with my custom yolo_v4_tiny model which I’m using through Deepstream-yolo github repo. So I am getting an error is “CUDA failure: an illegal memory access was encountered in file yoloPlugins.cpp at line 261”

I will attatch nvdspreprocess.txt for understanding and fix the issue ASAP.
preprocess.txt (4.2 KB)

3

This problem is usually caused by the way the video memory is allocated. Try scaling-pool-memory-type=3.

If it still doesn’t work, I need the full pipeline to try to debug it.

4

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

5

This topic was automatically closed 14 days after the last reply. New replies are no longer allowed.