ERROR from element primary-nvinference-engine: Buffer conversion failed

[spedevops]

Please provide complete information as applicable to your setup.

jetpack 6.2
Tensorrt 10.3.0.30
cuda 12.6.68
cudnn 9.3.0.75
Driver Version: 540.4.0

• Hardware Platform (Jetson / GPU) Orin Nano Super Developer Kit
• DeepStream Version 7.1
• JetPack Version (valid for Jetson only) 6.2
• TensorRT Version 10.3.0.30
• NVIDIA GPU Driver Version (valid for GPU only)
• Issue Type( questions, new requirements, bugs)
• How to reproduce the issue ? (This is for bugs. Including which sample app is using, the configuration files content, the command line used and other details for reproducing)

Normal object detection using YOLOV5 converted to ONNX using deepstream-yolo giving following error randomly and crashing on Orin Nano Super Developer Kit having deepstream 7.1. This is successfully running on Jetson Nano, dGPU A4000 since 3-4 years. When tested it on Orin Nano giving following errors.

[2025-02-13 17:14:57.402] [error] ERROR from element primary-nvinference-engine: Buffer conversion failed
[2025-02-13 17:14:57.402] [error] Error details: /dvs/git/dirty/git-master_linux/deepstream/sdk/src/gst-plugins/gst-nvinfer/gstnvinfer.cpp(1576): gst_nvinfer_process_full_frame (): /GstPipeline:LogicMo-Queue-Buster/GstNvInfer:primary-nvinference-engine
[2025-02-13 17:14:57.402] [info] Returned, stopping playback

• Requirement details( This is for new requirement. Including the module name-for which plugin or for which sample application, the function description)

[junshengy]

For DS-7.1, we have only tested it on Jetpack 6.1.

There may be some unknown issues with JP-6.2 on Orin nano super, Can you try to burn JP-6.1?

[spedevops]

Will try to use JP-6.1 and revert. Thanks

[yingliu]

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