search

NVIDIA-AI-IOT / deepstream-occupancy-analytics

This is a sample application for counting people entering/leaving in a building using NVIDIA Deepstream SDK, Transfer Learning Toolkit (TLT), and pre-trained models. This application can be used to build real-time occupancy analytics applications for smart buildings, hospitals, retail, etc. The application is based on deepstream-test5 sample application.
MIT License
221 stars 73 forks source link

Issue running this app with Deepstream 6.0 #42

Open JanetSe opened 2 years ago

JanetSe commented 2 years ago

• Hardware Platform (Jetson / GPU): Jetson Nano • DeepStream Version: 6.0 When running: sudo apt-cache show nvidia-jetpack, I get the following message:

Package: nvidia-jetpack Version: 4.5.1-b17 Architecture: arm64 Maintainer: NVIDIA Corporation Installed-Size: 194 Depends: nvidia-cuda (= 4.5.1-b17), nvidia-opencv (= 4.5.1-b17), nvidia-cudnn8 (= 4.5.1-b17), nvidia-tensorrt (= 4.5.1-b17), nvidia-visionworks (= 4.5.1-b17), nvidia-container (= 4.5.1-b17), nvidia-vpi (= 4.5.1-b17), nvidia-l4t-jetson-multimedia-api (>> 32.5-0), nvidia-l4t-jetson-multimedia-api (<< 32.6-0) Homepage: http://developer.nvidia.com/jetson Priority: standard Section: metapackages Filename: pool/main/n/nvidia-jetpack/nvidia-jetpack_4.5.1-b17_arm64.deb Size: 29390 SHA256: 13c10e9a53ec51c261ce188d626966dfca27f26b2ed94ba700147c1ba3e35399 SHA1: 81047a7779241bbf16763dbd1c4c12cf8c9d0496 MD5sum: 54916439514f39af5234b3a43e329910 Description: NVIDIA Jetpack Meta Package Description-md5: ad1462289bdbc54909ae109d1d32c0a8

Package: nvidia-jetpack Version: 4.5-b129 Architecture: arm64 Maintainer: NVIDIA Corporation Installed-Size: 194 Depends: nvidia-cuda (= 4.5-b129), nvidia-opencv (= 4.5-b129), nvidia-cudnn8 (= 4.5-b129), nvidia-tensorrt (= 4.5-b129), nvidia-visionworks (= 4.5-b129), nvidia-container (= 4.5-b129), nvidia-vpi (= 4.5-b129), nvidia-l4t-jetson-multimedia-api (>> 32.5-0), nvidia-l4t-jetson-multimedia-api (<< 32.6-0) Homepage: http://developer.nvidia.com/jetson Priority: standard Section: metapackages Filename: pool/main/n/nvidia-jetpack/nvidia-jetpack_4.5-b129_arm64.deb Size: 29358 SHA256: 9ee354a66d932a3fbb244c926f333143a845c627c6981d108e01df2958ac462c SHA1: 0e07f27c6fb9e34a70c69ae1150d1e578e938089 MD5sum: a551bbc8ff653c8983ce1804082bbcab Description: NVIDIA Jetpack Meta Package Description-md5: ad1462289bdbc54909ae109d1d32c0a8

I have already made the deepstream-occupancy-analytics on deepstream 5.1 and it worked fine, I cloned the same application on a different jetson with deepstream 6.0, but I get the following error:

ERROR: : Failed to create ‘nvosd0’ ERROR: : create_osd_bin failed ERROR: : create_processing_instance failed ERROR: : create_pipeline failed ** ERROR: main:1041: Failed to create pipeline Quitting App run failed

Any idea what this issue is referring to?

Thanks

monjha commented 2 years ago

Are you using ds6.0 branch?

niyazFattahov commented 2 years ago

Are you using ds6.0 branch?

Hello, should this work in ds6.0? I cannot run example: niyaz@niyaz:/opt/nvidia/deepstream/deepstream-6.0/sources/apps/sample_apps/deepstream-occupancy-analytics$ ./deepstream-test5-analytics -c config/test5_config_file_src_infer_tlt.txt ** WARN: : Deprecated config 'smart-rec-video-cache' used in group [source1]. Use 'smart-rec-cache' instead

(deepstream-test5-analytics:11522): GLib-CRITICAL **: 14:43:46.449: g_strchug: assertion 'string != NULL' failed

(deepstream-test5-analytics:11522): GLib-CRITICAL : 14:43:46.449: g_strchomp: assertion 'string != NULL' failed WARN: : Num of Tiles less than number of sources, readjusting to 2 rows, 1 columns Warning: 'input-dims' parameter has been deprecated. Use 'infer-dims' instead. ** ERROR: : Failed to set pipeline to PAUSED Quitting ERROR from sink_sub_bin_sink2: Could not configure supporting library. Debug info: /dvs/git/dirty/git-master_linux/deepstream/sdk/src/gst-plugins/gst-nvmsgbroker/gstnvmsgbroker.cpp(402): legacy_gst_nvmsgbroker_start (): /GstPipeline:pipeline/GstBin:sink_sub_bin2/GstNvMsgBroker:sink_sub_bin_sink2: unable to connect to broker library ERROR from sink_sub_bin_sink2: GStreamer error: state change failed and some element failed to post a proper error message with the reason for the failure. Debug info: gstbasesink.c(5265): gst_base_sink_change_state (): /GstPipeline:pipeline/GstBin:sink_sub_bin2/GstNvMsgBroker:sink_sub_bin_sink2: Failed to start App run failed

niyazFattahov commented 2 years ago

can this work from csi camera? I dont see option for csi

monjha commented 2 years ago

For ds6.0, please check the ds_6.0 branch. For csi camera, check this https://docs.nvidia.com/metropolis/deepstream/dev-guide/text/DS_ref_app_deepstream.html?highlight=csi#id4 and change the type of source group for csi.

niyazFattahov commented 2 years ago

For ds6.0, please check the ds_6.0 branch. For csi camera, check this https://docs.nvidia.com/metropolis/deepstream/dev-guide/text/DS_ref_app_deepstream.html?highlight=csi#id4 and change the type of source group for csi.

I get segfault with csi source and rtsp sink

monjha commented 2 years ago

What platform are you using? Also, any other ds sample application is running with CSI camera and rtsp sink?

niyazFattahov commented 2 years ago

What platform are you using? Also, any other ds sample application is running with CSI camera and rtsp sink?

Jetson Nanno, https://docs.nvidia.com/metropolis/deepstream/dev-guide/text/DS_Quickstart.html I have tested with this config and it working(detecting people): deepstream-app -c source1_csi_dec_infer_resnet_int8.txt

liaoweiguo commented 2 years ago

seems not working in DS 6.1

XinyueZ commented 1 year ago

The same issue to me with a sample program. I installed the docker version via docker pull nvcr.io/nvidia/deepstream-l4t:6.2-triton on the Orin (A sample program works well on PC GPU).

Any help?