Config file path: dstest2_sgie3_config.txt, NvDsInfer Error: NVDSINFER_CONFIG_FAILED

I am trying to run a deepstream python application. deepstream_python_apps/apps/deepstream-test2 at master · NVIDIA-AI-IOT/deepstream_python_apps (github.com)

The python file is running in a docker provide here. Docker Containers — DeepStream 6.1 Release documentation (nvidia.com)

Command:

python3 deepstream_test_2.py dronewedding.mp4 1

Output:

Creating Pipeline

Creating Source

Creating H264Parser

Creating Decoder

Creating EGLSink

Playing file dronewedding.mp4
Adding elements to Pipeline

Linking elements in the Pipeline

Starting pipeline

WARNING: ../nvdsinfer/nvdsinfer_model_builder.cpp:1482 Deserialize engine failed because file path: /home/saiteja/deepstream/deepstream_python_apps/apps/deepstream-test2/../../../../samples/models/Secondary_VehicleTypes/resnet18.caffemodel_b16_gpu0_int8.engine open error
0:00:03.253217640   297      0x36bee30 WARN                 nvinfer gstnvinfer.cpp:643:gst_nvinfer_logger:<secondary3-nvinference-engine> NvDsInferContext[UID 4]: Warning from NvDsInferContextImpl::deserializeEngineAndBackend() <nvdsinfer_context_impl.cpp:1888> [UID = 4]: deserialize engine from file :/home/saiteja/deepstream/deepstream_python_apps/apps/deepstream-test2/../../../../samples/models/Secondary_VehicleTypes/resnet18.caffemodel_b16_gpu0_int8.engine failed
0:00:03.280753699   297      0x36bee30 WARN                 nvinfer gstnvinfer.cpp:643:gst_nvinfer_logger:<secondary3-nvinference-engine> NvDsInferContext[UID 4]: Warning from NvDsInferContextImpl::generateBackendContext() <nvdsinfer_context_impl.cpp:1993> [UID = 4]: deserialize backend context from engine from file :/home/saiteja/deepstream/deepstream_python_apps/apps/deepstream-test2/../../../../samples/models/Secondary_VehicleTypes/resnet18.caffemodel_b16_gpu0_int8.engine failed, try rebuild
0:00:03.280790635   297      0x36bee30 INFO                 nvinfer gstnvinfer.cpp:646:gst_nvinfer_logger:<secondary3-nvinference-engine> NvDsInferContext[UID 4]: Info from NvDsInferContextImpl::buildModel() <nvdsinfer_context_impl.cpp:1914> [UID = 4]: Trying to create engine from model files
ERROR: ../nvdsinfer/nvdsinfer_model_builder.cpp:130 Cannot access prototxt file '/home/saiteja/deepstream/deepstream_python_apps/apps/deepstream-test2/../../../../samples/models/Secondary_VehicleTypes/resnet18.prototxt'
ERROR: ../nvdsinfer/nvdsinfer_model_builder.cpp:966 failed to build network since parsing model errors.
ERROR: ../nvdsinfer/nvdsinfer_model_builder.cpp:799 failed to build network.
0:00:03.811724437   297      0x36bee30 ERROR                nvinfer gstnvinfer.cpp:640:gst_nvinfer_logger:<secondary3-nvinference-engine> NvDsInferContext[UID 4]: Error in NvDsInferContextImpl::buildModel() <nvdsinfer_context_impl.cpp:1934> [UID = 4]: build engine file failed
0:00:03.834506632   297      0x36bee30 ERROR                nvinfer gstnvinfer.cpp:640:gst_nvinfer_logger:<secondary3-nvinference-engine> NvDsInferContext[UID 4]: Error in NvDsInferContextImpl::generateBackendContext() <nvdsinfer_context_impl.cpp:2020> [UID = 4]: build backend context failed
0:00:03.834579164   297      0x36bee30 ERROR                nvinfer gstnvinfer.cpp:640:gst_nvinfer_logger:<secondary3-nvinference-engine> NvDsInferContext[UID 4]: Error in NvDsInferContextImpl::initialize() <nvdsinfer_context_impl.cpp:1257> [UID = 4]: generate backend failed, check config file settings
0:00:03.834698012   297      0x36bee30 WARN                 nvinfer gstnvinfer.cpp:846:gst_nvinfer_start:<secondary3-nvinference-engine> error: Failed to create NvDsInferContext instance
0:00:03.834708136   297      0x36bee30 WARN                 nvinfer gstnvinfer.cpp:846:gst_nvinfer_start:<secondary3-nvinference-engine> error: Config file path: dstest2_sgie3_config.txt, NvDsInfer Error: NVDSINFER_CONFIG_FAILED
Error: gst-resource-error-quark: Failed to create NvDsInferContext instance (1): gstnvinfer.cpp(846): gst_nvinfer_start (): /GstPipeline:pipeline0/GstNvInfer:secondary3-nvinference-engine:
Config file path: dstest2_sgie3_config.txt, NvDsInfer Error: NVDSINFER_CONFIG_FAILED

Nvidia-smi:

+-----------------------------------------------------------------------------+
| NVIDIA-SMI 510.47.03    Driver Version: 510.47.03    CUDA Version: 11.6     |
|-------------------------------+----------------------+----------------------+
| GPU  Name        Persistence-M| Bus-Id        Disp.A | Volatile Uncorr. ECC |
| Fan  Temp  Perf  Pwr:Usage/Cap|         Memory-Usage | GPU-Util  Compute M. |
|                               |                      |               MIG M. |
|===============================+======================+======================|
|   0  Tesla T4            Off  | 00000000:06:00.0 Off |                    0 |
| N/A   44C    P0    28W /  70W |      0MiB / 15360MiB |     10%      Default |
|                               |                      |                  N/A |
+-------------------------------+----------------------+----------------------+

+-----------------------------------------------------------------------------+
| Processes:                                                                  |
|  GPU   GI   CI        PID   Type   Process name                  GPU Memory |
|        ID   ID                                                   Usage      |
|=============================================================================|
|  No running processes found                                                 |
+-----------------------------------------------------------------------------+

Please use H264 elementary stream.

ERROR: …/nvdsinfer/nvdsinfer_model_builder.cpp:130 Cannot access prototxt file ‘/home/saiteja/deepstream/deepstream_python_apps/apps/deepstream-test2/…/…/…/…/samples/models/Secondary_VehicleTypes/resnet18.prototxt’
and make sure you provide the correct model path.

I am using a docker container to run the command, how do I set the proper path to run the command, rather than changing the path in every sgie.txt file.

root@066b82106484:/opt/nvidia/deepstream/deepstream-6.1/deepstream_python_apps/apps/deepstream-test1# python3 deepstream_test_2.py /opt/nvidia/deepstream/deepstream-6.0/samples/streams/sample_720p.h264

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