• Hardware Platform (Jetson / GPU) : Jetson AGX Orin
• DeepStream Version : 7.1
• JetPack Version (valid for Jetson only): 6.2.1
• TensorRT Version: 10.3.0
• Issue Type( questions, new requirements, bugs): bug
I am working with my jetson agx orin from remote GUI access as depicted in What is the best way to control the jetson Orin GUI remotely? - #5 by KevinFFF . I tried to run deepstream sample reference application but it raised following error.
shift@ubuntu:/media/shift/d881e74a-0565-477f-b8f1-bb4f576d281f/opt/nvidia/deepstream/deepstream-7.1/samples/configs/deepstream-app$ deepstream-app -c source30_1080p_dec_infer-resnet_tiled_display_int8.txt
libEGL warning: DRI2: failed to authenticate
libEGL warning: DRI2: failed to authenticate
libEGL warning: DRI2: failed to authenticate
Setting min object dimensions as 16x16 instead of 1x1 to support VIC compute mode.
WARNING: [TRT]: Using an engine plan file across different models of devices is not recommended and is likely to affect performance or even cause errors.
0:00:00.431713003 3863 0xaaaad3246760 INFO nvinfer gstnvinfer.cpp:684:gst_nvinfer_logger:<primary_gie> NvDsInferContext[UID 1]: Info from NvDsInferContextImpl::deserializeEngineAndBackend() <nvdsinfer_context_impl.cpp:2092> [UID = 1]: deserialized trt engine from :/media/shift/d881e74a-0565-477f-b8f1-bb4f576d281f/opt/nvidia/deepstream/deepstream-7.1/samples/configs/deepstream-app/../../models/Primary_Detector/resnet18_trafficcamnet_pruned.onnx_b30_gpu0_int8.engine
INFO: [FullDims Engine Info]: layers num: 3
0 INPUT kFLOAT input_1:0 3x544x960 min: 1x3x544x960 opt: 30x3x544x960 Max: 30x3x544x960
1 OUTPUT kFLOAT output_cov/Sigmoid:0 4x34x60 min: 0 opt: 0 Max: 0
2 OUTPUT kFLOAT output_bbox/BiasAdd:0 16x34x60 min: 0 opt: 0 Max: 00:00:00.432025665 3863 0xaaaad3246760 INFO nvinfer gstnvinfer.cpp:684:gst_nvinfer_logger:<primary_gie> NvDsInferContext[UID 1]: Info from NvDsInferContextImpl::generateBackendContext() <nvdsinfer_context_impl.cpp:2195> [UID = 1]: Use deserialized engine model: /media/shift/d881e74a-0565-477f-b8f1-bb4f576d281f/opt/nvidia/deepstream/deepstream-7.1/samples/configs/deepstream-app/../../models/Primary_Detector/resnet18_trafficcamnet_pruned.onnx_b30_gpu0_int8.engine
nvbufsurface: Failed to create EGLImage.
0:00:00.453844414 3863 0xaaaad3246760 WARN nvinfer gstnvinfer.cpp:1010:gst_nvinfer_start:<primary_gie> error: Failed to set buffer pool to active
** ERROR: <main:713>: Failed to set pipeline to PAUSED
Quitting
ERROR from primary_gie: Failed to set buffer pool to active
Debug info: /dvs/git/dirty/git-master_linux/deepstream/sdk/src/gst-plugins/gst-nvinfer/gstnvinfer.cpp(1010): gst_nvinfer_start (): /GstPipeline:pipeline/GstBin:primary_gie_bin/GstNvInfer:primary_gie
But that sample reference application works without any issue when I connected jetson into a monitor. But I want to work it in remote GUI access. How to resolve this issue?