Issue while having nested secondary gie

[accbaid]

• Hardware Platform (Jetson / GPU) GPU
• DeepStream Version 5.1
• TensorRT Version 7.2.2
• 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)
Basically while running a model as secondary gie to another model model which is already in secondary gie mode, I am facing this issue related to NvBufSufTransform

0:00:36.192813590 13292 0x558bb97a5640 WARN                 nvinfer gstnvinfer.cpp:1277:convert_batch_and_push_to_input_thread:<secondary_gie_1> error: NvBufSurfTransform failed with error -3 while converting buffer
0:00:36.192923323 13292 0x558bb97a5640 WARN                 nvinfer gstnvinfer.cpp:1984:gst_nvinfer_output_loop:<secondary_gie_0> error: Internal data stream error.
0:00:36.192934510 13292 0x558bb97a5640 WARN                 nvinfer gstnvinfer.cpp:1984:gst_nvinfer_output_loop:<secondary_gie_0> error: streaming stopped, reason error (-5)
ERROR from secondary_gie_1: NvBufSurfTransform failed with error -3 while converting buffer
Debug info: gstnvinfer.cpp(1277): convert_batch_and_push_to_input_thread (): /GstPipeline:pipeline/GstBin:secondary_gie_bin/GstNvInfer:secondary_gie_1
ERROR from secondary_gie_0: Internal data stream error.
Debug info: gstnvinfer.cpp(1984): gst_nvinfer_output_loop (): /GstPipeline:pipeline/GstBin:secondary_gie_bin/GstNvInfer:secondary_gie_0:
streaming stopped, reason error (-5)
Quitting
0:00:36.229604515 13292 0x558bb97a5640 WARN                 nvinfer gstnvinfer.cpp:1277:convert_batch_and_push_to_input_thread:<secondary_gie_1> error: NvBufSurfTransform failed with error -3 while converting buffer
ERROR from secondary_gie_1: NvBufSurfTransform failed with error -3 while converting buffer
Debug info: gstnvinfer.cpp(1277): convert_batch_and_push_to_input_thread (): /GstPipeline:pipeline/GstBin:secondary_gie_bin/GstNvInfer:secondary_gie_1

[yuweiw]

Which app did you run? Besides, could you update the Deepstream to the latest version? The 6.2 GA is available now.
https://developer.nvidia.com/deepstream-getting-started

[accbaid]

This issue persists with DS6.2 as well, I am using a slightly modified version of test-app2 where I have one pgie as detector, sgie1 as another detector and sgie2 runs as a classifier on sgie1.

Something new though, that this is happening on laptops with RTX 3060 GPUs and not on my server which is A5000

[yuweiw]

Ok, could you attach your minimized demo to us? If we can reproduce this problem, it will be easier to analyze.

[accbaid]

A bit difficult to share the code though, I can drop one by recreating the same using deepstream-test3.

[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

OK. Also, If it is convenient, we recommend you upgrade Deepstream to the latest version 6.2.