Deepstream-image-meta-test app gave segmentation fault in Deepstream 6.1

Please provide complete information as applicable to your setup.

• Hardware Platform (Jetson / GPU): GeForce RTX 3090
• DeepStream Version: 6.1
• TensorRT Version: 8.2.5.1
• NVIDIA GPU Driver Version (valid for GPU only): 510.73.05
• Issue Type( questions, new requirements, bugs): bug
• 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)

The sample app is deepstream-image-meta-test, after installing dependencies and running make, I ran the app as follow:

./deepstream-image-meta-test file:///home/ds61/ds6.1-apps/samples/streams/sample_720p.mp4

The output:

WARNING: Overriding infer-config batch-size (2) with number of sources (1)
Failed to open lib libjpeg.so 
Now playing: file:///home/ds61/ds6.1-apps/samples/streams/sample_720p.mp4,
0:00:00.228603087 12975 0x55966316fd00 WARN                 nvinfer gstnvinfer.cpp:643:gst_nvinfer_logger:<primary-nvinference-engine> NvDsInferContext[UID 1]: Warning from NvDsInferContextImpl::initialize() <nvdsinfer_context_impl.cpp:1161> [UID = 1]: Warning, OpenCV has been deprecated. Using NMS for clustering instead of cv::groupRectangles with topK = 20 and NMS Threshold = 0.5
0:00:00.228740426 12975 0x55966316fd00 INFO                 nvinfer gstnvinfer.cpp:646:gst_nvinfer_logger:<primary-nvinference-engine> NvDsInferContext[UID 1]: Info from NvDsInferContextImpl::buildModel() <nvdsinfer_context_impl.cpp:1914> [UID = 1]: Trying to create engine from model files
0:00:25.587422249 12975 0x55966316fd00 INFO                 nvinfer gstnvinfer.cpp:646:gst_nvinfer_logger:<primary-nvinference-engine> NvDsInferContext[UID 1]: Info from NvDsInferContextImpl::buildModel() <nvdsinfer_context_impl.cpp:1946> [UID = 1]: serialize cuda engine to file: /home/ds61/ds6.1-apps/samples/models/Primary_Detector/resnet10.caffemodel_b1_gpu0_int8.engine successfully
INFO: ../nvdsinfer/nvdsinfer_model_builder.cpp:610 [Implicit Engine Info]: layers num: 3
0   INPUT  kFLOAT input_1         3x368x640       
1   OUTPUT kFLOAT conv2d_bbox     16x23x40        
2   OUTPUT kFLOAT conv2d_cov/Sigmoid 4x23x40         

0:00:25.609331189 12975 0x55966316fd00 INFO                 nvinfer gstnvinfer_impl.cpp:328:notifyLoadModelStatus:<primary-nvinference-engine> [UID 1]: Load new model:ds_image_meta_pgie_config.txt sucessfully
Running...
Segmentation fault (core dumped)

It complained about “Failed to open lib libjpeg.so”, I’m on Ubuntu 20.04, and installed all the dependencies mentioned in the README. I skip the libjpeg.so.8 part because it’s for RHEL Systems only. I’m not sure if this is the reason why the app segfault.

How do I fix this?

Missing dependencies not mentioned in the README file: libjpeg-dev. After install libjpeg-dev, the app run as normal.

Glad to know the issue is solved!

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