'nvinfer' errors while running python demo apps on DS SDK5 Jetson Nano

I have installed DeepStream SDK 5.0 with JetPack 4.4 for developing applications in Python. I am trying to run sample application deepstream-test1 with a .h264 video file as input. Getting the following error
python3 deepstream_test_1.py /opt/nvidia/deepstream/deepstream-5.0/samples/streams/sample_720p.h264
2020-07-13 15:20:18.461930: I tensorflow/stream_executor/platform/default/dso_loader.cc:48] Successfully opened dynamic library libcudart.so.10.2
Creating Pipeline

Creating Source

Creating H264Parser

Creating Decoder

Creating EGLSink

Playing file /opt/nvidia/deepstream/deepstream-5.0/samples/streams/sample_720p.h264
Warn: ‘threshold’ parameter has been deprecated. Use ‘pre-cluster-threshold’ instead.
Adding elements to Pipeline

Linking elements in the Pipeline

Starting pipeline

Using winsys: x11
Opening in BLOCKING MODE
ERROR: Deserialize engine failed because file path: /opt/nvidia/deepstream/deepstream-5.0/sources/python/apps/deepstream-test1/…/…/…/…/samples/models/Primary_Detector/resnet10.caffemodel_b1_gpu0_int8.engine open error
0:00:03.830314844 18521 0xb4f2980 WARN nvinfer gstnvinfer.cpp:599:gst_nvinfer_logger: NvDsInferContext[UID 1]: Warning from NvDsInferContextImpl::deserializeEngineAndBackend() <nvdsinfer_context_impl.cpp:1566> [UID = 1]: deserialize engine from file :/opt/nvidia/deepstream/deepstream-5.0/sources/python/apps/deepstream-test1/…/…/…/…/samples/models/Primary_Detector/resnet10.caffemodel_b1_gpu0_int8.engine failed
0:00:03.830382919 18521 0xb4f2980 WARN nvinfer gstnvinfer.cpp:599:gst_nvinfer_logger: NvDsInferContext[UID 1]: Warning from NvDsInferContextImpl::generateBackendContext() <nvdsinfer_context_impl.cpp:1673> [UID = 1]: deserialize backend context from engine from file :/opt/nvidia/deepstream/deepstream-5.0/sources/python/apps/deepstream-test1/…/…/…/…/samples/models/Primary_Detector/resnet10.caffemodel_b1_gpu0_int8.engine failed, try rebuild
0:00:03.830413232 18521 0xb4f2980 INFO nvinfer gstnvinfer.cpp:602:gst_nvinfer_logger: NvDsInferContext[UID 1]: Info from NvDsInferContextImpl::buildModel() <nvdsinfer_context_impl.cpp:1591> [UID = 1]: Trying to create engine from model files
Warning, setting batch size to 1. Update the dimension after parsing due to using explicit batch size.
WARNING: INT8 not supported by platform. Trying FP16 mode.
ERROR: [TRT]: Network has dynamic or shape inputs, but no optimization profile has been defined.
ERROR: [TRT]: Network validation failed.
ERROR: Build engine failed from config file
ERROR: failed to build trt engine.
0:00:03.860735562 18521 0xb4f2980 ERROR nvinfer gstnvinfer.cpp:596:gst_nvinfer_logger: NvDsInferContext[UID 1]: Error in NvDsInferContextImpl::buildModel() <nvdsinfer_context_impl.cpp:1611> [UID = 1]: build engine file failed
0:00:03.861199950 18521 0xb4f2980 ERROR nvinfer gstnvinfer.cpp:596:gst_nvinfer_logger: NvDsInferContext[UID 1]: Error in NvDsInferContextImpl::generateBackendContext() <nvdsinfer_context_impl.cpp:1697> [UID = 1]: build backend context failed
0:00:03.861239274 18521 0xb4f2980 ERROR nvinfer gstnvinfer.cpp:596:gst_nvinfer_logger: NvDsInferContext[UID 1]: Error in NvDsInferContextImpl::initialize() <nvdsinfer_context_impl.cpp:1024> [UID = 1]: generate backend failed, check config file settings
0:00:03.861298442 18521 0xb4f2980 WARN nvinfer gstnvinfer.cpp:781:gst_nvinfer_start: error: Failed to create NvDsInferContext instance
0:00:03.861327088 18521 0xb4f2980 WARN nvinfer gstnvinfer.cpp:781:gst_nvinfer_start: error: Config file path: dstest1_pgie_config.txt, NvDsInfer Error: NVDSINFER_CONFIG_FAILED
Error: gst-resource-error-quark: Failed to create NvDsInferContext instance (1): /dvs/git/dirty/git-master_linux/deepstream/sdk/src/gst-plugins/gst-nvinfer/gstnvinfer.cpp(781): gst_nvinfer_start (): /GstPipeline:pipeline0/GstNvInfer:primary-inference:
Config file path: dstest1_pgie_config.txt, NvDsInfer Error: NVDSINFER_CONFIG_FAILED

I have installed gst python v1.14.5 successfully.

I am facing the same issue, can anyone provide any help in this?

I have also tried moving the “Primary-Detector” files to “deepstream-test1” directory and changed the paths in config file accordingly. But the “open error” remains same.

I was able to solve the issue by using JetPack4.4 - developer preview version instead of the production version which is available at https://developer.nvidia.com/jetpack-sdk-44-dp-archive . I got a tip off after looking at other issues related to the DeepStream 5.5 SDK. Hope this helps.

2 Likes

Is there any way to downgrade to jetpack 4.4 preview (L4T 32.4.2) ?
Or we need to use the sd card image only in the jetpack archive section?

Hi @sujataapatil
You can use SDKManager to install the Jetson system, including flashing image, installing the AI, MM components.

1 Like