ubuntu@EAC-5000:~/workspaces/deep_stream_view/DeepStream-gi/scripts$ sudo ./lock_jetson_clock_to_max.sh --max
[sudo] password for ubuntu:
Storing system configuration in /tmp/defclocks.conf
Set MAXN Power and Clock : sudo jetson_clocks --show
Yes,The dewarper tear is fix,
I use yolov8n.onnx model,
But why person detetcted osd not on correct places.
And run after a while,
The pipeline be crash,
Some times have cuda runtime error
Have theese error:
bash '/home/nvidia/workspaces/yolov8-for-jetson/DeepStream-gi/scripts/GS_4Screen_yolov8n_Detect.sh'
Setting pipeline to PAUSED ...
gstnvtracker: Loading low-level lib at /opt/nvidia/deepstream/deepstream/lib/libnvds_nvmultiobjecttracker.so
[NvMultiObjectTracker] Initialized
Setting min object dimensions as 16x16 instead of 1x1 to support VIC compute mode.
0:00:00.315054528 17963 0xaaaafcb9e200 INFO nvinfer gstnvinfer.cpp:684:gst_nvinfer_logger:<nvinfer0> NvDsInferContext[UID 1]: Info from NvDsInferContextImpl::deserializeEngineAndBackend() <nvdsinfer_context_impl.cpp:2092> [UID = 1]: deserialized trt engine from :/home/nvidia/workspaces/yolov8-for-jetson/DeepStream-gi/configs/engines/JP_6.1/model_b1_gpu0_fp32.engine
Implicit layer support has been deprecated
INFO: [Implicit Engine Info]: layers num: 0
0:00:00.315144352 17963 0xaaaafcb9e200 INFO nvinfer gstnvinfer.cpp:684:gst_nvinfer_logger:<nvinfer0> NvDsInferContext[UID 1]: Info from NvDsInferContextImpl::generateBackendContext() <nvdsinfer_context_impl.cpp:2195> [UID = 1]: Use deserialized engine model: /home/nvidia/workspaces/yolov8-for-jetson/DeepStream-gi/configs/engines/JP_6.1/model_b1_gpu0_fp32.engine
0:00:00.320719616 17963 0xaaaafcb9e200 INFO nvinfer gstnvinfer_impl.cpp:343:notifyLoadModelStatus:<nvinfer0> [UID 1]: Load new model:config_infer_primary_yoloV8.txt sucessfully
Pipeline is live and does not need PREROLL ...
Pipeline is PREROLLED ...
Setting pipeline to PLAYING ...
New clock: GstSystemClock
Redistribute latency...
/dvs/git/dirty/git-master_linux/nvutils/nvbufsurftransform/nvbufsurftransform_copy.cpp:341: => Failed in mem copy
GPUassert: an illegal memory access was encountered /dvs/git/dirty/git-master_linux/deepstream/sdk/src/utils/nvmultiobjecttracker/src/modules/VisualTracker/VisualTracker.cpp 960
!![Exception] GPUassert failed
An exception occurred. GPUassert failed
gstnvtracker: Low-level tracker lib returned error 1
cuGraphicsEGLRegisterImage failed: 700, cuda process stop
/dvs/git/dirty/git-master_linux/nvutils/nvbufsurftransform/nvbufsurftransform_copy.cpp:341: => Failed in mem copy
cuGraphicsEGLRegisterImage failed: 700, cuda process stop
[WARN ] 2024-11-14 06:23:47 (cudaErrorIllegalAddress)
cuGraphicsEGLRegisterImage failed: 700, cuda process stop
ERROR: from element /GstPipeline:pipeline0/GstNvDsOsd:nvdsosd0: Unable to set device
Additional debug info:
/dvs/git/dirty/git-master_linux/deepstream/sdk/src/gst-plugins/gst-nvdsosd/gstnvdsosd.c(340): gst_nvds_osd_transform_ip (): /GstPipeline:pipeline0/GstNvDsOsd:nvdsosd0
Execution ended after 0:02:39.990863584
Setting pipeline to NULL ...
Unable to set device in gst_nvstreammux_change_state
Freeing pipeline ...
(gst-launch-1.0:17963): GStreamer-CRITICAL **: 06:23:47.863:
Trying to dispose element nvdewarper3, but it is in PLAYING instead of the NULL state.
You need to explicitly set elements to the NULL state before
dropping the final reference, to allow them to clean up.
This problem may also be caused by a refcounting bug in the
application or some element.
CUDA runtime error 4 at line 1306 in file /dvs/git/dirty/git-master_linux/deepstream/sdk/src/gst-plugins/gst-nvdewarper/gstnvdewarper.cpp
(gst-launch-1.0:17963): GStreamer-CRITICAL **: 06:23:47.864:
Trying to dispose element nv3dsink0, but it is in PLAYING instead of the NULL state.
You need to explicitly set elements to the NULL state before
dropping the final reference, to allow them to clean up.
This problem may also be caused by a refcounting bug in the
application or some element.
(gst-launch-1.0:17963): GStreamer-CRITICAL **: 06:23:47.864:
Trying to dispose element mux, but it is in PLAYING instead of the NULL state.
You need to explicitly set elements to the NULL state before
dropping the final reference, to allow them to clean up.
This problem may also be caused by a refcounting bug in the
application or some element.
(gst-launch-1.0:17963): GStreamer-CRITICAL **: 06:23:47.864:
Trying to dispose element pipeline0, but it is in PLAYING instead of the NULL state.
You need to explicitly set elements to the NULL state before
dropping the final reference, to allow them to clean up.
This problem may also be caused by a refcounting bug in the
application or some element.
(gst-launch-1.0:17963): GLib-GObject-WARNING **: 06:23:47.864: invalid unclassed pointer in cast to 'GstElement'
Unable to set device in gst_nvstreammux_src_collect_buffers
(gst-launch-1.0:17963): GStreamer-CRITICAL **: 06:23:47.868:
Trying to dispose element nvvideoconvert4, but it is in PLAYING instead of the NULL state.
You need to explicitly set elements to the NULL state before
dropping the final reference, to allow them to clean up.
This problem may also be caused by a refcounting bug in the
application or some element.
Seems the error happens with nvtracker. Have you tried the “deepstream-app” sample /opt/nvidia/deepstream/deepstream/samples/configs/deepstream-app/source4_1080p_dec_infer-resnet_tracker_sgie_tiled_display_int8.txt ?
