Can not run deepstream_test_rt_src_add_del with yolov5

Accelerated Computing Intelligent Video Analytics DeepStream SDK
1

Please provide complete information as applicable to your setup.

• Hardware Platform (Jetson / GPU)
**• DeepStream Version 6.0
**• JetPack Version 4.6.1

LD_PRELOAD=./libmyplugins.so ./deepstream-test-rt-src-add-del rtsp://admin:111111@192.168.1.120:554/Streaming/Channels/10```

but deepstream-app works well.

creating uridecodebin for [rtsp://admin:zw123456@11111:554/Streaming/Channels/102]
Unknown key ‘enable-past-frame’ for group [tracker]Unknown key ‘display-tracking-id’ for group [tracker]WARNING: Overriding infer-config batch-size (2) with number of sources (1)

Using winsys: x11
gstnvtracker: Loading low-level lib at /opt/nvidia/deepstream/deepstream/lib/libnvds_nvmultiobjecttracker.so
~~ CLOG[/dvs/git/dirty/git-master_linux/deepstream/sdk/src/utils/nvmultiobjecttracker/include/modules/NvMultiObjectTracker/NvTrackerParams.hpp, getConfigRoot() @line 54]: [NvTrackerParams::getConfigRoot()] !!![WARNING] Invalid low-level config file caused an exception, but will go ahead with the default config values
gstnvtracker: Batch processing is ON
gstnvtracker: Past frame output is OFF
~~ CLOG[/dvs/git/dirty/git-master_linux/deepstream/sdk/src/utils/nvmultiobjecttracker/include/modules/NvMultiObjectTracker/NvTrackerParams.hpp, getConfigRoot() @line 54]: [NvTrackerParams::getConfigRoot()] !!![WARNING] Invalid low-level config file caused an exception, but will go ahead with the default config values
[NvMultiObjectTracker] Initialized
0:00:06.973724761 15559 0x55afaf4160 INFO nvinfer gstnvinfer.cpp:638:gst_nvinfer_logger: NvDsInferContext[UID 1]: Info from NvDsInferContextImpl::deserializeEngineAndBackend() <nvdsinfer_context_impl.cpp:1900> [UID = 1]: deserialized trt engine from :/opt/nvidia/deepstream/deepstream-6.0/sources/apps/sample_apps/deepstream_reference_apps/runtime_source_add_delete/yolov5s.engine
INFO: [Implicit Engine Info]: layers num: 2
0 INPUT kFLOAT data 3x640x640
1 OUTPUT kFLOAT prob 6001x1x1

0:00:06.993705943 15559 0x55afaf4160 WARN nvinfer gstnvinfer.cpp:635:gst_nvinfer_logger: NvDsInferContext[UID 1]: Warning from NvDsInferContextImpl::checkBackendParams() <nvdsinfer_context_impl.cpp:1833> [UID = 1]: Backend has maxBatchSize 1 whereas 4 has been requested
0:00:06.993843545 15559 0x55afaf4160 WARN nvinfer gstnvinfer.cpp:635:gst_nvinfer_logger: NvDsInferContext[UID 1]: Warning from NvDsInferContextImpl::generateBackendContext() <nvdsinfer_context_impl.cpp:2012> [UID = 1]: deserialized backend context :/opt/nvidia/deepstream/deepstream-6.0/sources/apps/sample_apps/deepstream_reference_apps/runtime_source_add_delete/yolov5s.engine failed to match config params, trying rebuild
0:00:07.038958918 15559 0x55afaf4160 INFO nvinfer gstnvinfer.cpp:638:gst_nvinfer_logger: NvDsInferContext[UID 1]: Info from NvDsInferContextImpl::buildModel() <nvdsinfer_context_impl.cpp:1914> [UID = 1]: Trying to create engine from model files
Begin cuda engine build…
Yolo type is not defined from config file name:#rd
ERROR: Failed to create network using custom network creation function
ERROR: Failed to get cuda engine from custom library API
0:00:07.879822883 15559 0x55afaf4160 ERROR nvinfer gstnvinfer.cpp:632:gst_nvinfer_logger: NvDsInferContext[UID 1]: Error in NvDsInferContextImpl::buildModel() <nvdsinfer_context_impl.cpp:1934> [UID = 1]: build engine file failed
0:00:07.902917727 15559 0x55afaf4160 ERROR nvinfer gstnvinfer.cpp:632:gst_nvinfer_logger: NvDsInferContext[UID 1]: Error in NvDsInferContextImpl::generateBackendContext() <nvdsinfer_context_impl.cpp:2020> [UID = 1]: build backend context failed
0:00:07.903118401 15559 0x55afaf4160 ERROR nvinfer gstnvinfer.cpp:632:gst_nvinfer_logger: NvDsInferContext[UID 1]: Error in NvDsInferContextImpl::initialize() <nvdsinfer_context_impl.cpp:1257> [UID = 1]: generate backend failed, check config file settings
0:00:07.903779591 15559 0x55afaf4160 WARN nvinfer gstnvinfer.cpp:841:gst_nvinfer_start: error: Failed to create NvDsInferContext instance
0:00:07.903828519 15559 0x55afaf4160 WARN nvinfer gstnvinfer.cpp:841:gst_nvinfer_start: error: Config file path: dstest_pgie_config.txt, NvDsInfer Error: NVDSINFER_CONFIG_FAILED
[NvMultiObjectTracker] De-initialized
Now playing: rtsp://admin:zw123456@192.168.1.120:554/Streaming/Channels/102
gstnvtracker: Loading low-level lib at /opt/nvidia/deepstream/deepstream/lib/libnvds_nvmultiobjecttracker.so
~~ CLOG[/dvs/git/dirty/git-master_linux/deepstream/sdk/src/utils/nvmultiobjecttracker/include/modules/NvMultiObjectTracker/NvTrackerParams.hpp, getConfigRoot() @line 54]: [NvTrackerParams::getConfigRoot()] !!![WARNING] Invalid low-level config file caused an exception, but will go ahead with the default config values
gstnvtracker: Batch processing is ON
gstnvtracker: Past frame output is OFF
~~ CLOG[/dvs/git/dirty/git-master_linux/deepstream/sdk/src/utils/nvmultiobjecttracker/include/modules/NvMultiObjectTracker/NvTrackerParams.hpp, getConfigRoot() @line 54]: [NvTrackerParams::getConfigRoot()] !!![WARNING] Invalid low-level config file caused an exception, but will go ahead with the default config values
[NvMultiObjectTracker] Initialized
0:00:08.976402047 15559 0x55afaf4160 INFO nvinfer gstnvinfer.cpp:638:gst_nvinfer_logger: NvDsInferContext[UID 1]: Info from NvDsInferContextImpl::deserializeEngineAndBackend() <nvdsinfer_context_impl.cpp:1900> [UID = 1]: deserialized trt engine from :/opt/nvidia/deepstream/deepstream-6.0/sources/apps/sample_apps/deepstream_reference_apps/runtime_source_add_delete/yolov5s.engine
INFO: [Implicit Engine Info]: layers num: 2
0 INPUT kFLOAT data 3x640x640
1 OUTPUT kFLOAT prob 6001x1x1

0:00:08.997769290 15559 0x55afaf4160 WARN nvinfer gstnvinfer.cpp:635:gst_nvinfer_logger: NvDsInferContext[UID 1]: Warning from NvDsInferContextImpl::checkBackendParams() <nvdsinfer_context_impl.cpp:1833> [UID = 1]: Backend has maxBatchSize 1 whereas 4 has been requested
0:00:08.997948300 15559 0x55afaf4160 WARN nvinfer gstnvinfer.cpp:635:gst_nvinfer_logger: NvDsInferContext[UID 1]: Warning from NvDsInferContextImpl::generateBackendContext() <nvdsinfer_context_impl.cpp:2012> [UID = 1]: deserialized backend context :/opt/nvidia/deepstream/deepstream-6.0/sources/apps/sample_apps/deepstream_reference_apps/runtime_source_add_delete/yolov5s.engine failed to match config params, trying rebuild
0:00:09.045003499 15559 0x55afaf4160 INFO nvinfer gstnvinfer.cpp:638:gst_nvinfer_logger: NvDsInferContext[UID 1]: Info from NvDsInferContextImpl::buildModel() <nvdsinfer_context_impl.cpp:1914> [UID = 1]: Trying to create engine from model files
Begin cuda engine build…
Yolo type is not defined from config file name:
x
ERROR: Failed to create network using custom network creation function
ERROR: Failed to get cuda engine from custom library API
0:00:09.577420690 15559 0x55afaf4160 ERROR nvinfer gstnvinfer.cpp:632:gst_nvinfer_logger: NvDsInferContext[UID 1]: Error in NvDsInferContextImpl::buildModel() <nvdsinfer_context_impl.cpp:1934> [UID = 1]: build engine file failed
0:00:09.610329003 15559 0x55afaf4160 ERROR nvinfer gstnvinfer.cpp:632:gst_nvinfer_logger: NvDsInferContext[UID 1]: Error in NvDsInferContextImpl::generateBackendContext() <nvdsinfer_context_impl.cpp:2020> [UID = 1]: build backend context failed
0:00:09.610554861 15559 0x55afaf4160 ERROR nvinfer gstnvinfer.cpp:632:gst_nvinfer_logger: NvDsInferContext[UID 1]: Error in NvDsInferContextImpl::initialize() <nvdsinfer_context_impl.cpp:1257> [UID = 1]: generate backend failed, check config file settings
0:00:09.611124242 15559 0x55afaf4160 WARN nvinfer gstnvinfer.cpp:841:gst_nvinfer_start: error: Failed to create NvDsInferContext instance
0:00:09.611167475 15559 0x55afaf4160 WARN nvinfer gstnvinfer.cpp:841:gst_nvinfer_start: error: Config file path: dstest_pgie_config.txt, NvDsInfer Error: NVDSINFER_CONFIG_FAILED
[NvMultiObjectTracker] De-initialized
Failed to set pipeline to playing. Exiting.```

3

What do you mean is to use the same model and same config file，where one works normally and the other fails?

4

Yes, I guess that when I run the script ‘LD_PRELOAD=./libmyplugins. so./deepstream test rt src add del’, ‘LD_PRELOAD=./libmyplugins. so’ does not work.

5

No. Just from the log Yolo type is not defined from config file name. There may be differences in the configuration between these two uses. You can check that first. This part is open source:opt\nvidia\deepstream\deepstream\sources\objectDetector_Yolo\nvdsinfer_custom_impl_Yolo\nvdsinfer_yolo_engine.cpp.

6

Thank you very much for helping me find the direction to solve the problem. It has already been running。

7

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