gstnvtracker: Loading low-level lib at /opt/nvidia/deepstream/deepstream-7.1/lib/libnvds_nvmultiobjecttracker.so
[NvTrackerParams::getConfigRoot()] !!![WARNING] File doesn’t exist. Will go ahead with default values
[NvMultiObjectTracker] Initialized
Got this error when running trackers like NvDCF_accuracy and NvDeepSORT even though I have the reid model .etlt file and every file path is specicified correctly.
Other trackers work fine
Please provide complete information as applicable to your setup.
• Hardware Platform (Jetson / GPU)
• DeepStream Version
• JetPack Version (valid for Jetson only)
• TensorRT Version
• 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)
• Requirement details( This is for new requirement. Including the module name-for which plugin or for which sample application, the function description)
Are you follow this guide to setup ReID model: Gst-nvtracker — DeepStream documentation . Please share the full log when you got the fail during starting the deepstream application.
• Hardware Platform - GPU
• DeepStream Version -7.1
• TensorRT Version -10.3
• NVIDIA GPU Driver Version - 580.88
I Followed the tutorial to set up reID exactly
shengyu@HC-HW-88100100:/opt/nvidia/deepstream/deepstream-7.1$ deepstream-app -c pipeline.txt
Failed to query video capabilities: Inappropriate ioctl for device
gstnvtracker: Loading low-level lib at /opt/nvidia/deepstream/deepstream-7.1/lib/libnvds_nvmultiobjecttracker.so
[NvTrackerParams::getConfigRoot()] !!![WARNING] File doesn’t exist. Will go ahead with default values
[NvMultiObjectTracker] Initialized
0:00:01.290711422 1044 0x5b98642ed4d0 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 :/opt/nvidia/deepstream/deepstream-7.1/samples/models/Primary_Detector/resnet18_trafficcamnet_pruned.onnx_b4_gpu0_fp16.engine
INFO: ../nvdsinfer/nvdsinfer_model_builder.cpp:327 [FullDims Engine Info]: layers num: 3
0 INPUT kFLOAT input_1:0 3x544x960 min: 1x3x544x960 opt: 4x3x544x960 Max: 4x3x544x960
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: 0
0:00:01.290823444 1044 0x5b98642ed4d0 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: /opt/nvidia/deepstream/deepstream-7.1/samples/models/Primary_Detector/resnet18_trafficcamnet_pruned.onnx_b4_gpu0_fp16.engine
0:00:01.297178833 1044 0x5b98642ed4d0 INFO nvinfer gstnvinfer_impl.cpp:343:notifyLoadModelStatus:<primary_gie> [UID 1]: Load new model:/opt/nvidia/deepstream/deepstream-7.1/config_infer_primary.txt sucessfully
Runtime commands:
h: Print this help
q: Quit
p: Pause
r: Resume
NOTE: To expand a source in the 2D tiled display and view object details, left-click on the source.
To go back to the tiled display, right-click anywhere on the window.
** INFO: <bus_callback:291>: Pipeline ready
Failed to query video capabilities: Inappropriate ioctl for device
Failed to query video capabilities: Inappropriate ioctl for device
Failed to query video capabilities: Inappropriate ioctl for device
Failed to query video capabilities: Inappropriate ioctl for device
** INFO: <bus_callback:277>: Pipeline running
**PERF: FPS 0 (Avg) FPS 1 (Avg) FPS 2 (Avg) FPS 3 (Avg)
**PERF: 94.62 (94.57) 94.62 (94.57) 94.62 (94.57) 94.51 (94.45)
**PERF: 72.38 (79.49) 72.38 (79.49) 72.38 (79.49) 72.53 (79.53)
**PERF: 90.62 (83.14) 90.62 (83.14) 90.62 (83.14) 90.62 (83.17)
**PERF: 68.17 (79.44) 67.97 (79.39) 68.17 (79.44) 68.17 (79.46)
**PERF: 81.35 (79.83) 81.35 (79.79) 81.35 (79.83) 81.35 (79.84)
**PERF: 96.68 (82.60) 96.68 (82.57) 96.68 (82.60) 96.68 (82.62)
**PERF: 94.70 (84.33) 94.90 (84.33) 94.70 (84.33) 94.90 (84.37)
**PERF: 95.16 (85.66) 95.16 (85.66) 95.16 (85.66) 95.16 (85.69)
**PERF: 67.41 (82.98) 67.41 (82.98) 67.41 (82.98) 67.41 (83.01)
**PERF: 96.69 (84.30) 96.69 (84.30) 96.69 (84.30) 96.69 (84.33)
**PERF: 100.29 (85.69) 100.29 (85.69) 100.29 (85.69) 100.29 (85.71)
**PERF: 102.69 (87.06) 102.69 (87.06) 102.69 (87.06) 102.69 (87.09)
**PERF: 99.99 (88.03) 99.99 (88.03) 99.99 (88.03) 99.99 (88.05)
nvstreammux: Successfully handled EOS for source_id=0
nvstreammux: Successfully handled EOS for source_id=1
nvstreammux: Successfully handled EOS for source_id=2
nvstreammux: Successfully handled EOS for source_id=3
** INFO: <bus_callback:334>: Received EOS. Exiting …
Quitting
[NvMultiObjectTracker] De-initialized
App run successful
shengyu@HC-HW-88100100:/opt/nvidia/deepstream/deepstream-7.1$
Above already show the “PERF” log, so the deepstream-app is running. What is the issue now? Can you share your pipeline.txt file or can you test with DeepStream release configure file?
[NvTrackerParams::getConfigRoot()] !!![WARNING] File doesn’t exist. Will go ahead with default values
The problem is with this, I dont understand what they mean by using default values. This warning only appear when i run NvDeepSORT and NVdcf_accuracy.
And is the engine file suppose to built upon runing the pipeline/app? cause I dont see any engine files being built
Can you have a test with DeepStream default release? I don’t see the log with below command line.
root@kevin-System-Product-Name:/opt/nvidia/deepstream/deepstream-7.1/samples/configs/deepstream-app# deepstream-app -c source4_1080p_dec_infer-resnet_tracker_sgie_tiled_display_int8.txt