Dear my friend, I am running this deepstream-pose project in the GPU docker “nvcr.io/nvidia/deepstream:5.0-dp-20.04-devel”, and the binary file works not good.
The CUDA nvcc -V in docker is 10.2
I copy the libnvds_osd.so file to replace the old one
The error information is :
(deepstream-pose-estimation-app:106): GStreamer-WARNING **: 08:38:22.660: Failed to load plugin ‘/usr/lib/x86_64-linux-gnu/gstreamer-1.0/deepstream/libnvdsgst_osd.so’: ///opt/nvidia/deepstream/deepstream-5.0/lib/libnvds_osd.so: undefined symbol: nvds_mask_utils_resize_to_binary_argb32
One element could not be created. Exiting.
When I use the old libnvds_osd.so file , there would is a error “libnvosd (504):(ERROR) : Out of bound radius”
• Hardware Platform (Jetson / GPU): GPU, 2060
• DeepStream Version: 5.0
• JetPack Version (valid for Jetson only)
• TensorRT Version
• NVIDIA GPU Driver Version (valid for GPU only) 440.82
• 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)
I have change the docker to nvcr.io/nvidia/deepstream 5.0.1-20.09-devel , the problem is solved .
But I still have the “out of bound radius” problem :
libnvosd (603):(ERROR) : Out of bound radius
0:02:16.106130660 128 0x5614e09ea630 WARN nvinfer gstnvinfer.cpp:1975:gst_nvinfer_output_loop: error: Internal data stream error.
0:02:16.106140016 128 0x5614e09ea630 WARN nvinfer gstnvinfer.cpp:1975:gst_nvinfer_output_loop: error: streaming stopped, reason error (-5)
ERROR from element nv-onscreendisplay: Unable to draw circles
Error details: gstnvdsosd.c(558): gst_nvds_osd_transform_ip (): /GstPipeline:deepstream-tensorrt-openpose-pipeline/GstNvDsOsd:nv-onscreendisplay
Returned, stopping playback
Are you using GitHub - NVIDIA-AI-IOT/deepstream_pose_estimation: This is a sample DeepStream application to demonstrate a human pose estimation pipeline.? This is just a sample code, the “Out of bound radius” may be caused by the display circle parameters. You can add boundary check in create_display_meta() function. Current deepstream does not support the circle out of the image.
I also have the same problem, but how to write boundary check in create_display_meta() function. Q.Q
Please help to open a new topic if it’s still an issue.
I already solve that, I set the resolution of streammux aboout pose estimation as same as the resolution of osd and tiled-display. Thx!