Issue with Deepstream Pose Estimation App: the "Decodebin did not pick nvidia decoder plugin" error in GStreamer

minshan1 · March 26, 2023, 11:31pm

I’m encountering an issue while running the deepstream-pose-estimation-app on my docker container.

My environment set up
GPU platforms: V100
DeepStreamSDK 6.1.0
TensorRT Version: 8.5.2-1+cuda11.8
NVIDIA GPU Driver Version: 510.108.03
CUDA Version: 11.8
gcc (Ubuntu 9.4.0-1ubuntu1~20.04.1) 9.4.0
GStreamer1.16.3

The model I am using:
bodypose3dnet_vdeployable_accuracy_v1.0
peoplenet_vdeployable_quantized_v2.5

The command :
./deepstream-pose-estimation-app --input file:///opt/nvidia/deepstream/deepstream/sources/apps/sample_apps/deepstream_reference_apps/deepstream-bodypose-3d/streams/9-12-53_57sec.mp4 --output /opt/nvidia/deepstream/deepstream/sources/apps/sample_apps/deepstream_reference_apps/deepstream-bodypose-3d/streams/3_24_output.mp4 --focal 800.0 --width 1280 --height 720 --fps --save-pose /opt/nvidia/deepstream/deepstream/sources/apps/sample_apps/deepstream_reference_apps/deepstream-bodypose-3d/streams/3_24.json

The console output is as follows:
Now playing: file:///opt/nvidia/deepstream/deepstream/sources/apps/sample_apps/deepstream_reference_apps/deepstream-bodypose-3d/streams/9-12-53_57sec.mp4
0:00:38.570974092 7 0x55834d9f00c0 INFO nvinfer gstnvinfer.cpp:646: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-6.1/sources/apps/sample_apps/deepstream_reference_apps/deepstream-bodypose-3d/models/bodypose3dnet_vdeployable_accuracy_v1.0/bodypose3dnet_accuracy.etlt_b8_gpu0_fp16.engine
0:00:38.635867529 7 0x55834d9f00c0 INFO nvinfer gstnvinfer.cpp:646:gst_nvinfer_logger: NvDsInferContext[UID 1]: Info from NvDsInferContextImpl::generateBackendContext() <nvdsinfer_context_impl.cpp:2003> [UID = 1]: Use deserialized engine model: /opt/nvidia/deepstream/deepstream-6.1/sources/apps/sample_apps/deepstream_reference_apps/deepstream-bodypose-3d/models/bodypose3dnet_vdeployable_accuracy_v1.0/bodypose3dnet_accuracy.etlt_b8_gpu0_fp16.engine
0:00:38.687749401 7 0x55834d9f00c0 INFO nvinfer gstnvinfer_impl.cpp:328:notifyLoadModelStatus: [UID 1]: Load new model:…/configs/config_infer_secondary_bodypose3dnet.txt sucessfully
WARNING: [TRT]: CUDA lazy loading is not enabled. Enabling it can significantly reduce device memory usage. See CUDA_MODULE_LOADING in CUDA C++ Programming Guide
WARNING: [TRT]: (foreignNode) cuBLASLt subversions: compiled against 11.8.1.0 but running against 11.11.3.0.
WARNING: [TRT]: (foreignNode) cuBLASLt subversions: compiled against 11.8.1.0 but running against 11.11.3.0.
WARNING: [TRT]: (foreignNode) cuBLASLt subversions: compiled against 11.8.1.0 but running against 11.11.3.0.
WARNING: [TRT]: (foreignNode) cuBLASLt subversions: compiled against 11.8.1.0 but running against 11.11.3.0.
WARNING: [TRT]: (foreignNode) cuBLASLt subversions: compiled against 11.8.1.0 but running against 11.11.3.0.
WARNING: [TRT]: CUDA lazy loading is not enabled. Enabling it can significantly reduce device memory usage. See CUDA_MODULE_LOADING in CUDA C++ Programming Guide
INFO: …/nvdsinfer/nvdsinfer_model_builder.cpp:610 [FullDims Engine Info]: layers num: 9
0 INPUT kFLOAT input0 3x256x192 min: 1x3x256x192 opt: 8x3x256x192 Max: 8x3x256x192
1 INPUT kFLOAT k_inv 3x3 min: 1x3x3 opt: 8x3x3 Max: 8x3x3
2 INPUT kFLOAT t_form_inv 3x3 min: 1x3x3 opt: 8x3x3 Max: 8x3x3
3 INPUT kFLOAT scale_normalized_mean_limb_lengths 36 min: 1x36 opt: 8x36 Max: 8x36
4 INPUT kFLOAT mean_limb_lengths 36 min: 1x36 opt: 8x36 Max: 8x36
5 OUTPUT kFLOAT pose25d 34x4 min: 0 opt: 0 Max: 0
6 OUTPUT kFLOAT pose2d 34x3 min: 0 opt: 0 Max: 0
7 OUTPUT kFLOAT pose3d 34x3 min: 0 opt: 0 Max: 0
8 OUTPUT kFLOAT pose2d_org_img 34x3 min: 0 opt: 0 Max: 0

gstnvtracker: Loading low-level lib at /opt/nvidia/deepstream/deepstream/lib/libnvds_nvmultiobjecttracker.so
gstnvtracker: Batch processing is ON
gstnvtracker: Past frame output is OFF
[NvMultiObjectTracker] Initialized
0:00:49.859881703 7 0x55834d9f00c0 INFO nvinfer gstnvinfer.cpp:646: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-6.1/sources/apps/sample_apps/deepstream_reference_apps/deepstream-bodypose-3d/models/peoplenet_vdeployable_quantized_v2.5/resnet34_peoplenet_int8.etlt_b1_gpu0_int8.engine
0:00:49.909775424 7 0x55834d9f00c0 INFO nvinfer gstnvinfer.cpp:646:gst_nvinfer_logger: NvDsInferContext[UID 1]: Info from NvDsInferContextImpl::generateBackendContext() <nvdsinfer_context_impl.cpp:2003> [UID = 1]: Use deserialized engine model: /opt/nvidia/deepstream/deepstream-6.1/sources/apps/sample_apps/deepstream_reference_apps/deepstream-bodypose-3d/models/peoplenet_vdeployable_quantized_v2.5/resnet34_peoplenet_int8.etlt_b1_gpu0_int8.engine
0:00:49.922038507 7 0x55834d9f00c0 INFO nvinfer gstnvinfer_impl.cpp:328:notifyLoadModelStatus: [UID 1]: Load new model:…/configs/config_infer_primary_peoplenet.txt sucessfully
WARNING: [TRT]: CUDA lazy loading is not enabled. Enabling it can significantly reduce device memory usage. See CUDA_MODULE_LOADING in CUDA C++ Programming Guide
WARNING: [TRT]: CUDA lazy loading is not enabled. Enabling it can significantly reduce device memory usage. See CUDA_MODULE_LOADING in CUDA C++ Programming Guide
INFO: …/nvdsinfer/nvdsinfer_model_builder.cpp:610 [Implicit Engine Info]: layers num: 3
0 INPUT kFLOAT input_1 3x544x960
1 OUTPUT kFLOAT output_bbox/BiasAdd 12x34x60
2 OUTPUT kFLOAT output_cov/Sigmoid 3x34x60

Decodebin child added: source
Decodebin child added: decodebin0
Running…
Error: Decodebin did not pick nvidia decoder plugin.
In cb_newpad
Returned, stopping playback
ERROR from element qtdemux0: Internal data stream error.
Error details: qtdemux.c(6619): gst_qtdemux_loop (): /GstPipeline:deepstream-bodypose3dnet/GstBin:source-bin-00/GstURIDecodeBin:uri-decode-bin/GstDecodeBin:decodebin0/GstQTDemux:qtdemux0:
streaming stopped, reason not-linked (-1)
[NvMultiObjectTracker] De-initialized
Deleting pipeline

fanzh · March 27, 2023, 3:29am

can the application run fine with the native sample video streams/bodypose.mp4?
could you share the result of “gst-inspect-1.0 |grep nvv4l2decoder”?

minshan1 · March 27, 2023, 7:39am

It is the same error when running with the native sample video streams/bodypose.mp4.
Output for “gst-inspect-1.0 |grep nvv4l2decoder":
nvvideo4linux2: nvv4l2decoder: NVIDIA v4l2 video decoder

fanzh · March 27, 2023, 2:55pm

please refer to https://docs.nvidia.com/metropolis/deepstream/dev-guide/text/DS_Quickstart.html#id6, the libs version is not compatible in your environment.

minshan1 · March 27, 2023, 11:51pm

Do you know which lib is not compapatible?
I installed the deepstream 6.2 instdead, but getting this error when running deepstream-pose-estimation-app

The console output:
Now playing: file:///opt/nvidia/deepstream/deepstream/sources/apps/sample_apps/deepstream_reference_apps/deepstream-bodypose-3d/streams/bodypose.mp4
0:00:27.053489361 7 0x561bc386a930 INFO nvinfer gstnvinfer.cpp:680:gst_nvinfer_logger: NvDsInferContext[UID 1]: Info from NvDsInferContextImpl::deserializeEngineAndBackend() <nvdsinfer_context_impl.cpp:1909> [UID = 1]: deserialized trt engine from :/opt/nvidia/deepstream/deepstream-6.2/sources/apps/sample_apps/deepstream_reference_apps/deepstream-bodypose-3d/models/bodypose3dnet_vdeployable_accuracy_v1.0/bodypose3dnet_accuracy.etlt_b8_gpu0_fp16.engine
0:00:27.093533542 7 0x561bc386a930 INFO nvinfer gstnvinfer.cpp:680:gst_nvinfer_logger: NvDsInferContext[UID 1]: Info from NvDsInferContextImpl::generateBackendContext() <nvdsinfer_context_impl.cpp:2012> [UID = 1]: Use deserialized engine model: /opt/nvidia/deepstream/deepstream-6.2/sources/apps/sample_apps/deepstream_reference_apps/deepstream-bodypose-3d/models/bodypose3dnet_vdeployable_accuracy_v1.0/bodypose3dnet_accuracy.etlt_b8_gpu0_fp16.engine
0:00:27.109664167 7 0x561bc386a930 INFO nvinfer gstnvinfer_impl.cpp:328:notifyLoadModelStatus: [UID 1]: Load new model:…/configs/config_infer_secondary_bodypose3dnet.txt sucessfully
WARNING: [TRT]: CUDA lazy loading is not enabled. Enabling it can significantly reduce device memory usage. See CUDA_MODULE_LOADING in CUDA C++ Programming Guide
WARNING: [TRT]: (foreignNode) cuBLASLt subversions: compiled against 11.8.1.0 but running against 11.11.3.0.
WARNING: [TRT]: (foreignNode) cuBLASLt subversions: compiled against 11.8.1.0 but running against 11.11.3.0.
WARNING: [TRT]: (foreignNode) cuBLASLt subversions: compiled against 11.8.1.0 but running against 11.11.3.0.
WARNING: [TRT]: (foreignNode) cuBLASLt subversions: compiled against 11.8.1.0 but running against 11.11.3.0.
WARNING: [TRT]: (foreignNode) cuBLASLt subversions: compiled against 11.8.1.0 but running against 11.11.3.0.
WARNING: [TRT]: CUDA lazy loading is not enabled. Enabling it can significantly reduce device memory usage. See CUDA_MODULE_LOADING in CUDA C++ Programming Guide
INFO: …/nvdsinfer/nvdsinfer_model_builder.cpp:610 [FullDims Engine Info]: layers num: 9
0 INPUT kFLOAT input0 3x256x192 min: 1x3x256x192 opt: 8x3x256x192 Max: 8x3x256x192
1 INPUT kFLOAT k_inv 3x3 min: 1x3x3 opt: 8x3x3 Max: 8x3x3
2 INPUT kFLOAT t_form_inv 3x3 min: 1x3x3 opt: 8x3x3 Max: 8x3x3
3 INPUT kFLOAT scale_normalized_mean_limb_lengths 36 min: 1x36 opt: 8x36 Max: 8x36
4 INPUT kFLOAT mean_limb_lengths 36 min: 1x36 opt: 8x36 Max: 8x36
5 OUTPUT kFLOAT pose25d 34x4 min: 0 opt: 0 Max: 0
6 OUTPUT kFLOAT pose2d 34x3 min: 0 opt: 0 Max: 0
7 OUTPUT kFLOAT pose3d 34x3 min: 0 opt: 0 Max: 0
8 OUTPUT kFLOAT pose2d_org_img 34x3 min: 0 opt: 0 Max: 0

gstnvtracker: Loading low-level lib at /opt/nvidia/deepstream/deepstream/lib/libnvds_nvmultiobjecttracker.so
gstnvtracker: Batch processing is ON
gstnvtracker: Past frame output is OFF
~~ CLOG[src/modules/ReID/ReID.cpp, loadTRTEngine() @line 418]: Engine file does not exist
[NvMultiObjectTracker] Load engine failed. Create engine again.

!![ERROR] UFF file does not exist
[NvMultiObjectTracker] De-initialized
An exception occurred. UFF file does not exist
gstnvtracker: Failed to initialize tracker context!
gstnvtracker:: Failed to create batch context. Shutting down processing.
Running…

fanzh · March 28, 2023, 2:09am

from the question description, DeepStreamSDK 6.1.0 is not compatible with TRT 8.5.2.2.
could you share the result of “dpkg -l |grep TensorRT” and dpkg -l | grep gstreamer? if not using docker, please intall the libs according to this docdgpu-setup-for-ubuntu, and make sure all libs version meet this table 's requirement mentioned above.

from the error, you enabled " --tracker accuracy" mode, which will need a tracker model, for simplicity, you can try “eepstream/deepstream/sources/apps/sample_apps/deepstream_reference_apps/deepstream-bodypose-3d/streams/bodypose.mp4 --output fakesink”

minshan1 · March 28, 2023, 4:57am

Result for “dpkg -l |grep TensorRT” :
ii libnvinfer-bin 8.5.2-1+cuda11.8 amd64 TensorRT binaries
ii libnvinfer-dev 8.5.2-1+cuda11.8 amd64 TensorRT development libraries and headers
ii libnvinfer-plugin-dev 8.5.2-1+cuda11.8 amd64 TensorRT plugin libraries
ii libnvinfer-plugin8 8.5.2-1+cuda11.8 amd64 TensorRT plugin libraries
ii libnvinfer-samples 8.5.2-1+cuda11.8 all TensorRT samples
ii libnvinfer8 8.5.2-1+cuda11.8 amd64 TensorRT runtime libraries
ii libnvonnxparsers-dev 8.5.2-1+cuda11.8 amd64 TensorRT ONNX libraries
ii libnvonnxparsers8 8.5.2-1+cuda11.8 amd64 TensorRT ONNX libraries
ii libnvparsers-dev 8.5.2-1+cuda11.8 amd64 TensorRT parsers libraries
ii libnvparsers8 8.5.2-1+cuda11.8 amd64 TensorRT parsers libraries
ii python3-libnvinfer 8.5.2-1+cuda11.8 amd64 Python 3 bindings for TensorRT
ii python3-libnvinfer-dev 8.5.2-1+cuda11.8 amd64 Python 3 development package for TensorRT

Result for “dpkg -l | grep gstreamer”:
ii gir1.2-gstreamer-1.0:amd64 1.16.3-0ubuntu1.1 amd64 GObject introspection data for the GStreamer library
ii gstreamer1.0-gl:amd64 1.16.3-0ubuntu1.1 amd64 GStreamer plugins for GL
ii gstreamer1.0-libav:amd64 1.16.2-2 amd64 ffmpeg plugin for GStreamer
ii gstreamer1.0-plugins-bad:amd64 1.16.3-0ubuntu1 amd64 GStreamer plugins from the “bad” set
ii gstreamer1.0-plugins-base:amd64 1.16.3-0ubuntu1.1 amd64 GStreamer plugins from the “base” set
ii gstreamer1.0-plugins-good:amd64 1.16.3-0ubuntu1.1 amd64 GStreamer plugins from the “good” set
ii gstreamer1.0-plugins-ugly:amd64 1.16.2-2build1 amd64 GStreamer plugins from the “ugly” set
ii gstreamer1.0-tools 1.16.3-0ubuntu1.1 amd64 Tools for use with GStreamer
ii gstreamer1.0-x:amd64 1.16.3-0ubuntu1.1 amd64 GStreamer plugins for X11 and Pango
ii libgstreamer-gl1.0-0:amd64 1.16.3-0ubuntu1.1 amd64 GStreamer GL libraries
ii libgstreamer-plugins-bad1.0-0:amd64 1.16.3-0ubuntu1 amd64 GStreamer libraries from the “bad” set
ii libgstreamer-plugins-base1.0-0:amd64 1.16.3-0ubuntu1.1 amd64 GStreamer libraries from the “base” set
ii libgstreamer-plugins-base1.0-dev:amd64 1.16.3-0ubuntu1.1 amd64 GStreamer development files for libraries from the “base” set
ii libgstreamer-plugins-good1.0-0:amd64 1.16.3-0ubuntu1.1 amd64 GStreamer development files for libraries from the “good” set
ii libgstreamer1.0-0:amd64 1.16.3-0ubuntu1.1 amd64 Core GStreamer libraries and elements
ii libgstreamer1.0-dev:amd64 1.16.3-0ubuntu1.1 amd64 GStreamer core development files

minshan1 · March 28, 2023, 11:42am

Is it the command that you mean?
./deepstream-pose-estimation-app --input file:///opt/nvidia/deepstream/deepstream/sources/apps/sample_apps/deepstream_reference_apps/deepstream-bodypose-3d/streams/bodypose.mp4 --output fakesink --focal 800.0 --width 1280 --height 720 --fps --save-pose /opt/nvidia/deepstream/deepstream/sources/apps/sample_apps/deepstream_reference_apps/deepstream-bodypose-3d/streams/3_16.json

I ran the above command but still get this error:
Now playing: file:///opt/nvidia/deepstream/deepstream/sources/apps/sample_apps/deepstream_reference_apps/deepstream-bodypose-3d/streams/bodypose.mp4
0:00:04.887265148 6 0x558b65d6cc30 INFO nvinfer gstnvinfer.cpp:680:gst_nvinfer_logger: NvDsInferContext[UID 1]: Info from NvDsInferContextImpl::deserializeEngineAndBackend() <nvdsinfer_context_impl.cpp:1909> [UID = 1]: deserialized trt engine from :/opt/nvidia/deepstream/deepstream-6.2/sources/apps/sample_apps/deepstream_reference_apps/deepstream-bodypose-3d/models/bodypose3dnet_vdeployable_accuracy_v1.0/bodypose3dnet_accuracy.etlt_b8_gpu0_fp16.engine
0:00:04.925189311 6 0x558b65d6cc30 INFO nvinfer gstnvinfer.cpp:680:gst_nvinfer_logger: NvDsInferContext[UID 1]: Info from NvDsInferContextImpl::generateBackendContext() <nvdsinfer_context_impl.cpp:2012> [UID = 1]: Use deserialized engine model: /opt/nvidia/deepstream/deepstream-6.2/sources/apps/sample_apps/deepstream_reference_apps/deepstream-bodypose-3d/models/bodypose3dnet_vdeployable_accuracy_v1.0/bodypose3dnet_accuracy.etlt_b8_gpu0_fp16.engine
0:00:04.931130069 6 0x558b65d6cc30 INFO nvinfer gstnvinfer_impl.cpp:328:notifyLoadModelStatus: [UID 1]: Load new model:…/configs/config_infer_secondary_bodypose3dnet.txt sucessfully
WARNING: [TRT]: CUDA lazy loading is not enabled. Enabling it can significantly reduce device memory usage. See CUDA_MODULE_LOADING in CUDA C++ Programming Guide
WARNING: [TRT]: (foreignNode) cuBLASLt subversions: compiled against 11.8.1.0 but running against 11.11.3.0.
WARNING: [TRT]: (foreignNode) cuBLASLt subversions: compiled against 11.8.1.0 but running against 11.11.3.0.
WARNING: [TRT]: (foreignNode) cuBLASLt subversions: compiled against 11.8.1.0 but running against 11.11.3.0.
WARNING: [TRT]: (foreignNode) cuBLASLt subversions: compiled against 11.8.1.0 but running against 11.11.3.0.
WARNING: [TRT]: (foreignNode) cuBLASLt subversions: compiled against 11.8.1.0 but running against 11.11.3.0.
WARNING: [TRT]: CUDA lazy loading is not enabled. Enabling it can significantly reduce device memory usage. See CUDA_MODULE_LOADING in CUDA C++ Programming Guide
INFO: …/nvdsinfer/nvdsinfer_model_builder.cpp:610 [FullDims Engine Info]: layers num: 9
0 INPUT kFLOAT input0 3x256x192 min: 1x3x256x192 opt: 8x3x256x192 Max: 8x3x256x192
1 INPUT kFLOAT k_inv 3x3 min: 1x3x3 opt: 8x3x3 Max: 8x3x3
2 INPUT kFLOAT t_form_inv 3x3 min: 1x3x3 opt: 8x3x3 Max: 8x3x3
3 INPUT kFLOAT scale_normalized_mean_limb_lengths 36 min: 1x36 opt: 8x36 Max: 8x36
4 INPUT kFLOAT mean_limb_lengths 36 min: 1x36 opt: 8x36 Max: 8x36
5 OUTPUT kFLOAT pose25d 34x4 min: 0 opt: 0 Max: 0
6 OUTPUT kFLOAT pose2d 34x3 min: 0 opt: 0 Max: 0
7 OUTPUT kFLOAT pose3d 34x3 min: 0 opt: 0 Max: 0
8 OUTPUT kFLOAT pose2d_org_img 34x3 min: 0 opt: 0 Max: 0

gstnvtracker: Loading low-level lib at /opt/nvidia/deepstream/deepstream/lib/libnvds_nvmultiobjecttracker.so
gstnvtracker: Batch processing is ON
gstnvtracker: Past frame output is OFF
~~ CLOG[src/modules/ReID/ReID.cpp, loadTRTEngine() @line 418]: Engine file does not exist
[NvMultiObjectTracker] Load engine failed. Create engine again.

!![ERROR] UFF file does not exist
[NvMultiObjectTracker] De-initialized
An exception occurred. UFF file does not exist
gstnvtracker: Failed to initialize tracker context!
gstnvtracker:: Failed to create batch context. Shutting down processing.
Running…

The current environment is:
GPU platforms: V100
DeepStreamSDK 6.2.0
TensorRT Version: 8.5.2-1+cuda11.8
NVIDIA GPU Driver Version: 510.108.03
CUDA Version: 11.8
gcc (Ubuntu 9.4.0-1ubuntu1~20.04.1) 9.4.0
GStreamer1.16.3

fanzh · March 28, 2023, 3:07pm

please try the following command first, the difference is using “using track perf”, which will not need that model.
./deepstream-pose-estimation-app --input file:///opt/nvidia/deepstream/deepstream/sources/apps/sample_apps/deepstream_reference_apps/deepstream-bodypose-3d/streams/bodypose.mp4 --tracker perf --output fakesink --focal 800.0 --width 1280 --height 720 --fps --save-pose /opt/nvidia/deepstream/deepstream/sources/apps/sample_apps/deepstream_reference_apps/deepstream-bodypose-3d/streams/3_16.json

minshan1 · March 28, 2023, 4:07pm

Using this command, it is getting the internal data stream error as before.

Now playing: file:///opt/nvidia/deepstream/deepstream/sources/apps/sample_apps/deepstream_reference_apps/deepstream-bodypose-3d/streams/bodypose.mp4
0:00:05.821074964 7 0x55ac7a1eea30 INFO nvinfer gstnvinfer.cpp:680:gst_nvinfer_logger: NvDsInferContext[UID 1]: Info from NvDsInferContextImpl::deserializeEngineAndBackend() <nvdsinfer_context_impl.cpp:1909> [UID = 1]: deserialized trt engine from :/opt/nvidia/deepstream/deepstream-6.2/sources/apps/sample_apps/deepstream_reference_apps/deepstream-bodypose-3d/models/bodypose3dnet_vdeployable_accuracy_v1.0/bodypose3dnet_accuracy.etlt_b8_gpu0_fp16.engine
0:00:05.855795688 7 0x55ac7a1eea30 INFO nvinfer gstnvinfer.cpp:680:gst_nvinfer_logger: NvDsInferContext[UID 1]: Info from NvDsInferContextImpl::generateBackendContext() <nvdsinfer_context_impl.cpp:2012> [UID = 1]: Use deserialized engine model: /opt/nvidia/deepstream/deepstream-6.2/sources/apps/sample_apps/deepstream_reference_apps/deepstream-bodypose-3d/models/bodypose3dnet_vdeployable_accuracy_v1.0/bodypose3dnet_accuracy.etlt_b8_gpu0_fp16.engine
0:00:05.860522369 7 0x55ac7a1eea30 INFO nvinfer gstnvinfer_impl.cpp:328:notifyLoadModelStatus: [UID 1]: Load new model:…/configs/config_infer_secondary_bodypose3dnet.txt sucessfully
WARNING: [TRT]: CUDA lazy loading is not enabled. Enabling it can significantly reduce device memory usage. See CUDA_MODULE_LOADING in CUDA C++ Programming Guide
WARNING: [TRT]: (foreignNode) cuBLASLt subversions: compiled against 11.8.1.0 but running against 11.11.3.0.
WARNING: [TRT]: (foreignNode) cuBLASLt subversions: compiled against 11.8.1.0 but running against 11.11.3.0.
WARNING: [TRT]: (foreignNode) cuBLASLt subversions: compiled against 11.8.1.0 but running against 11.11.3.0.
WARNING: [TRT]: (foreignNode) cuBLASLt subversions: compiled against 11.8.1.0 but running against 11.11.3.0.
WARNING: [TRT]: (foreignNode) cuBLASLt subversions: compiled against 11.8.1.0 but running against 11.11.3.0.
WARNING: [TRT]: CUDA lazy loading is not enabled. Enabling it can significantly reduce device memory usage. See CUDA_MODULE_LOADING in CUDA C++ Programming Guide
INFO: …/nvdsinfer/nvdsinfer_model_builder.cpp:610 [FullDims Engine Info]: layers num: 9
0 INPUT kFLOAT input0 3x256x192 min: 1x3x256x192 opt: 8x3x256x192 Max: 8x3x256x192
1 INPUT kFLOAT k_inv 3x3 min: 1x3x3 opt: 8x3x3 Max: 8x3x3
2 INPUT kFLOAT t_form_inv 3x3 min: 1x3x3 opt: 8x3x3 Max: 8x3x3
3 INPUT kFLOAT scale_normalized_mean_limb_lengths 36 min: 1x36 opt: 8x36 Max: 8x36
4 INPUT kFLOAT mean_limb_lengths 36 min: 1x36 opt: 8x36 Max: 8x36
5 OUTPUT kFLOAT pose25d 34x4 min: 0 opt: 0 Max: 0
6 OUTPUT kFLOAT pose2d 34x3 min: 0 opt: 0 Max: 0
7 OUTPUT kFLOAT pose3d 34x3 min: 0 opt: 0 Max: 0
8 OUTPUT kFLOAT pose2d_org_img 34x3 min: 0 opt: 0 Max: 0

gstnvtracker: Loading low-level lib at /opt/nvidia/deepstream/deepstream/lib/libnvds_nvmultiobjecttracker.so
gstnvtracker: Batch processing is ON
gstnvtracker: Past frame output is OFF
[NvMultiObjectTracker] Initialized
0:00:12.451065263 7 0x55ac7a1eea30 INFO nvinfer gstnvinfer.cpp:680:gst_nvinfer_logger: NvDsInferContext[UID 1]: Info from NvDsInferContextImpl::deserializeEngineAndBackend() <nvdsinfer_context_impl.cpp:1909> [UID = 1]: deserialized trt engine from :/opt/nvidia/deepstream/deepstream-6.2/sources/apps/sample_apps/deepstream_reference_apps/deepstream-bodypose-3d/models/peoplenet_vdeployable_quantized_v2.5/resnet34_peoplenet_int8.etlt_b1_gpu0_int8.engine
0:00:12.494219389 7 0x55ac7a1eea30 INFO nvinfer gstnvinfer.cpp:680:gst_nvinfer_logger: NvDsInferContext[UID 1]: Info from NvDsInferContextImpl::generateBackendContext() <nvdsinfer_context_impl.cpp:2012> [UID = 1]: Use deserialized engine model: /opt/nvidia/deepstream/deepstream-6.2/sources/apps/sample_apps/deepstream_reference_apps/deepstream-bodypose-3d/models/peoplenet_vdeployable_quantized_v2.5/resnet34_peoplenet_int8.etlt_b1_gpu0_int8.engine
0:00:12.515754291 7 0x55ac7a1eea30 INFO nvinfer gstnvinfer_impl.cpp:328:notifyLoadModelStatus: [UID 1]: Load new model:…/configs/config_infer_primary_peoplenet.txt sucessfully
WARNING: [TRT]: CUDA lazy loading is not enabled. Enabling it can significantly reduce device memory usage. See CUDA_MODULE_LOADING in CUDA C++ Programming Guide
WARNING: [TRT]: CUDA lazy loading is not enabled. Enabling it can significantly reduce device memory usage. See CUDA_MODULE_LOADING in CUDA C++ Programming Guide
INFO: …/nvdsinfer/nvdsinfer_model_builder.cpp:610 [Implicit Engine Info]: layers num: 3
0 INPUT kFLOAT input_1 3x544x960
1 OUTPUT kFLOAT output_bbox/BiasAdd 12x34x60
2 OUTPUT kFLOAT output_cov/Sigmoid 3x34x60

Decodebin child added: source
Decodebin child added: decodebin0
Running…
In cb_newpad
Error: Decodebin did not pick nvidia decoder plugin.
ERROR from element qtdemux0: Internal data stream error.
Error details: qtdemux.c(6619): gst_qtdemux_loop (): /GstPipeline:deepstream-bodypose3dnet/GstBin:source-bin-00/GstURIDecodeBin:uri-decode-bin/GstDecodeBin:decodebin0/GstQTDemux:qtdemux0:
streaming stopped, reason not-linked (-1)
Returned, stopping playback
[NvMultiObjectTracker] De-initialized
Deleting pipeline

minshan1 · March 28, 2023, 11:43pm

Is it still because the incompatible libs?

fanzh · March 29, 2023, 2:02am

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

if using deepstream6.2, driver version should be R525.85.12, please refer the compatibility table mentioned above.

system · April 25, 2023, 2:56am

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

Topic		Replies	Views
Error when running deepstream-pose-estimation-app DeepStream SDK	8	863	March 27, 2023
"reason not-negotiated (-4)" python deepstream-app1 is stopped DeepStream SDK	2	612	December 26, 2022
Runtime errors when running the human pose estimation application DeepStream SDK tensorrt , cuda , ubuntu	25	4803	October 12, 2021
DeepStream6.3 Error while setting IOCTL DeepStream SDK	8	983	September 4, 2023
Deepstream 6.2 nvdcf tracker DeepStream SDK	29	1092	April 29, 2024
Deepstream pipeline waits for input indefinitely DeepStream SDK deepstream61	19	676	June 16, 2022
Deepstream_pose_estimation - fatal error: gstnvdsmeta.h: No such file or directory DeepStream SDK	12	2572	February 22, 2022
GStreamer-CRITICAL **: 16:10:55.658: gst_meta_api_type_has_tag: assertion 'tag != 0' failed DeepStream SDK ubuntu , gstreamer , python , deepstream	18	53	February 21, 2025
Cuda failure: status=801 Error(-1) in buffer allocation DeepStream SDK	36	1470	September 18, 2023
Can't run deepstream-app-5.1 example using deepstream docker 5.1, but can do it with deepstream docker 5.0.1 DeepStream SDK	4	1986	October 12, 2021

Issue with Deepstream Pose Estimation App: the "Decodebin did not pick nvidia decoder plugin" error in GStreamer

Related topics