AGX Xavier - segmenation fault on DeepStream People detection + Flowtron

Hi
I’m using Jetpack 4.4 DP L4T 32.4.2
AGX Xavier
CUDA 10.2.89
TensorRT 7.1.0.16
I’ve run DeepStream demos succesfully.
Unfortunately running people detection demo crashes 3 seconds after start showing video stream from /dev/video0
with segmentation fault.
I’ve tried on 2 different usb cameras - the same effect
I’m runing this with
sudo docker run -it --net=host --runtime nvidia --device=/dev/video0:/dev/video0 -e DISPLAY=$DISPLAY -v /tmp/.X11-unix/:/tmp/.X11-unix nvcr.io/nvidia/deepstream-peopledetection:r32.4.2 deepstream-test5-app -c deepstream-5.0/samples/configs/deepstream-app/source1_usb_dec_infer_resnet_int8.txt
Runtime log looks as follow

ERROR: Deserialize engine failed because file path: /opt/nvidia/deepstream/deepstream-5.0/samples/configs/deepstream-app/…/…/models/Primary_Detector/resnet10.caffemodel_b30_gpu0_int8.engine open error
0:00:04.271570441 1 0x5594840ca0 WARN nvinfer gstnvinfer.cpp:599:gst_nvinfer_logger:<primary_gie> NvDsInferContext[UID 1]: Warning from NvDsInferContextImpl::deserializeEngineAndBackend() <nvdsinfer_context_impl.cpp:1563> [UID = 1]: deserialize engine from file :/opt/nvidia/deepstream/deepstream-5.0/samples/configs/deepstream-app/…/…/models/Primary_Detector/resnet10.caffemodel_b30_gpu0_int8.engine failed
0:00:04.271874578 1 0x5594840ca0 WARN nvinfer gstnvinfer.cpp:599:gst_nvinfer_logger:<primary_gie> NvDsInferContext[UID 1]: Warning from NvDsInferContextImpl::generateBackendContext() <nvdsinfer_context_impl.cpp:1670> [UID = 1]: deserialize backend context from engine from file :/opt/nvidia/deepstream/deepstream-5.0/samples/configs/deepstream-app/…/…/models/Primary_Detector/resnet10.caffemodel_b30_gpu0_int8.engine failed, try rebuild
0:00:04.271971382 1 0x5594840ca0 INFO nvinfer gstnvinfer.cpp:602:gst_nvinfer_logger:<primary_gie> NvDsInferContext[UID 1]: Info from NvDsInferContextImpl::buildModel() <nvdsinfer_context_impl.cpp:1588> [UID = 1]: Trying to create engine from model files
INFO: [TRT]: Reading Calibration Cache for calibrator: EntropyCalibration2
INFO: [TRT]: Generated calibration scales using calibration cache. Make sure that calibration cache has latest scales.
INFO: [TRT]: To regenerate calibration cache, please delete the existing one. TensorRT will generate a new calibration cache.
INFO: [TRT]:
INFO: [TRT]: --------------- Layers running on DLA:
INFO: [TRT]:
INFO: [TRT]: --------------- Layers running on GPU:
INFO: [TRT]: conv1 + activation_1/Relu, block_1a_conv_1 + activation_2/Relu, block_1a_conv_2, block_1a_conv_shortcut + add_1 + activation_3/Relu, block_2a_conv_1 + activation_4/Relu, block_2a_conv_2, block_2a_conv_shortcut + add_2 + activation_5/Relu, block_3a_conv_1 + activation_6/Relu, block_3a_conv_2, block_3a_conv_shortcut + add_3 + activation_7/Relu, block_4a_conv_1 + activation_8/Relu, block_4a_conv_2, block_4a_conv_shortcut + add_4 + activation_9/Relu, conv2d_cov, conv2d_cov/Sigmoid, conv2d_bbox,
INFO: [TRT]: Some tactics do not have sufficient workspace memory to run. Increasing workspace size may increase performance, please check verbose output.
INFO: [TRT]: Detected 1 inputs and 2 output network tensors.
0:00:26.165588523 1 0x5594840ca0 INFO nvinfer gstnvinfer.cpp:602:gst_nvinfer_logger:<primary_gie> NvDsInferContext[UID 1]: Info from NvDsInferContextImpl::buildModel() <nvdsinfer_context_impl.cpp:1621> [UID = 1]: serialize cuda engine to file: /opt/nvidia/deepstream/deepstream-5.0/samples/models/Primary_Detector/resnet10.caffemodel_b1_gpu0_int8.engine successfully
INFO: [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

0:00:26.182550680 1 0x5594840ca0 INFO nvinfer gstnvinfer_impl.cpp:311:notifyLoadModelStatus:<primary_gie> [UID 1]: Load new model:/opt/nvidia/deepstream/deepstream-5.0/samples/configs/deepstream-app/config_infer_primary.txt sucessfully

Runtime commands:
h: Print this help
q: Quit

p: Pause
r: Resume

NOTE: To expand a source in the 2D tiled display and view object details, left-click on the source.
To go back to the tiled display, right-click anywhere on the window.

**PERF: FPS 0 (Avg)
Wed May 27 16:41:35 2020
**PERF: 0.00 (0.00)
** INFO: <bus_callback:172>: Pipeline ready

** INFO: <bus_callback:158>: Pipeline running

Dmesg error
[ 1644.645230] nvmap_alloc_handle: PID 13264: deepstream-test: WARNING: All NvMap Allocations must have a tag to identify the subsystem allocating memory.Please pass the tag to the API call NvRmMemHanldeAllocAttr() or relevant.
Running manually in the container gives additionally:
**PERF: FPS 0 (Avg)
Wed May 27 16:43:59 2020
**PERF: 0.00 (0.00)
** INFO: <bus_callback:172>: Pipeline ready

** INFO: <bus_callback:158>: Pipeline running

Wed May 27 16:44:04 2020
**PERF: 15.11 (15.08)
Segmentation fault (core dumped)

Observation - this not crashes when i’m not moving object (me) or moving very slow on the camera.

My flowtron project inference run test (audio) after compiling torch without docker etc with Magma crashes also but there is a
Segmentation fault on /usr/lib/aarch64-linux-gnu/libcudnn_ops_infer.so.8.0.0 - checked on GDB
(https://github.com/NVIDIA/flowtron)

Any suggestions appreciated.

Hi,

Thanks for your report.
We are going to reproduce this. Will update more information with you later.

Hi,

Thanks for your patience.

We can reproduce this issue in our environment.
This issue is passed to our internally.
Will update more information with you once we got a feedback.

Thanks.

Hi,

May I know your environment setting?
We found this issue won’t occur if the device with enough memory and space.

Thanks.

Hi
Yes of course my current configuration details are as follows:

/dev/mmcblk0p1 28G 24G 2,3G 92% /
none 7,4G 0 7,4G 0% /dev
tmpfs 7,8G 4,0K 7,8G 1% /dev/shm
tmpfs 7,8G 30M 7,7G 1% /run
tmpfs 5,0M 4,0K 5,0M 1% /run/lock
tmpfs 7,8G 0 7,8G 0% /sys/fs/cgroup
/dev/nvme0n1p1 251G 161G 78G 68% /home/mirek
tmpfs 1,6G 112K 1,6G 1% /run/user/1000

Amount of space on disk shouldn’t be a problem - I’m running with share with 161G free space

Amount of memory too - vmstat says it’s 13GB
procs -----------memory---------- —swap-- -----io---- -system-- ------cpu-----
r b swpd free inact active si so bi bo in cs us sy id wa st
0 0 0 13549308 436724 1138416 0 0 11 6 50 79 0 0 99 0 0

How the memory size can relate to segmentation fault ? Lack of memory or address space is usually expressed by OOM.
Segmentation fault is happening when instruction writes to memory area used by kernel or other program.
Below screenshot if needed from libraries used.
Please share what type of settings you need - I will be happy to share

image.png

Best regards Mirek Bartecki

Hi,

Would you mind to share the system information from tegrastats with us?

$ sudo tegrastats

More, may I know your camera config also?
We don’t meet any error with a USB camera with camera-fps-n=30.

Thanks.

Hello

My tegrastats are like below - measured while running deepstream-test5
RAM 4200/15823MB (lfb 2146x4MB) SWAP 0/40679MB (cached 0MB) CPU [11%AT1142,8%AT1142,16%AT1143,71%AT1143,10%AT1142,10%AT1143,6%AT1144,10%AT1143] EMC_FREQ 2%AT1600 GR3D_FREQ 0%AT420 APE 150 MTS fg 0% bg 16% AOAT32C GPUAT32.5C TdiodeAT38C PMICAT100C AUXAT33C CPUAT34C thermalAT33.3C TboardAT34C GPU 464/464 CPU 774/666 SOC 1394/1146 CV 0/0 VDDRQ 154/61 SYS5V 3004/2852
RAM 4376/15823MB (lfb 2146x4MB) SWAP 0/40679MB (cached 0MB) CPU [21%AT1142,6%AT1142,11%AT1143,81%AT1143,10%AT1142,11%AT1142,8%AT1143,9%AT1143] EMC_FREQ 4%AT1065 GR3D_FREQ 9%AT420 APE 150 MTS fg 1% bg 15% AOAT32C GPUAT32.5C TdiodeAT38C PMICAT100C AUXAT33C CPUAT34C thermalAT33.15C TboardAT34C GPU 464/464 CPU 930/690 SOC 1239/1155 CV 0/0 VDDRQ 155/70 SYS5V 2964/2862
RAM 4552/15823MB (lfb 2146x4MB) SWAP 0/40679MB (cached 0MB) CPU [16%AT1142,10%AT1142,45%AT1141,50%AT1142,6%AT1141,6%AT1142,20%AT1143,8%AT1141] EMC_FREQ 3%AT1065 GR3D_FREQ 3%AT420 APE 150 MTS fg 0% bg 14% AOAT32C GPUAT33C TdiodeAT38C PMICAT100C AUXAT33C CPUAT34C thermalAT33.15C TboardAT34C GPU 464/464 CPU 930/710 SOC 1239/1162 CV 0/0 VDDRQ 155/77 SYS5V 2924/2867
RAM 4727/15823MB (lfb 2134x4MB) SWAP 0/40679MB (cached 0MB) CPU [13%AT1140,13%AT1141,12%AT1142,81%AT1142,14%AT1141,15%AT1140,12%AT1142,15%AT1140] EMC_FREQ 9%AT1065 GR3D_FREQ 31%AT522 APE 150 MTS fg 0% bg 19% AOAT32C GPUAT33C TdiodeAT38C PMICAT100C AUXAT33C CPUAT34C thermalAT33.15C TboardAT34C GPU 929/500 CPU 929/727 SOC 1239/1168 CV 0/0 VDDRQ 309/95 SYS5V 3004/2877
RAM 4948/15823MB (lfb 2107x4MB) SWAP 0/40679MB (cached 0MB) CPU [9%AT1143,9%AT1143,9%AT1144,87%AT1142,7%AT1142,10%AT1143,3%AT1143,3%AT1142] EMC_FREQ 5%AT1600 GR3D_FREQ 0%AT905 APE 150 MTS fg 0% bg 17% AOAT32.5C GPUAT33C TdiodeAT38C PMICAT100C AUXAT33C CPUAT34.5C thermalAT33.3C TboardAT34C GPU 1083/542 CPU 929/741 SOC 1702/1206 CV 0/0 VDDRQ 309/110 SYS5V 3124/2895
RAM 5171/15823MB (lfb 2053x4MB) SWAP 0/40679MB (cached 0MB) CPU [10%AT1143,21%AT1143,17%AT1143,74%AT1143,8%AT1143,11%AT1143,12%AT1144,11%AT1145] EMC_FREQ 19%AT1600 GR3D_FREQ 73%AT905 APE 150 MTS fg 0% bg 18% AOAT32.5C GPUAT34C TdiodeAT38C PMICAT100C AUXAT33C CPUAT34.5C thermalAT33.45C TboardAT34C GPU 2473/670 CPU 927/753 SOC 2164/1270 CV 0/0 VDDRQ 927/164 SYS5V 3445/2932
RAM 5172/15823MB (lfb 2052x4MB) SWAP 0/40679MB (cached 0MB) CPU [5%AT1144,7%AT1144,9%AT1143,26%AT1143,4%AT1143,5%AT1143,4%AT1144,9%AT1144] EMC_FREQ 28%AT1600 GR3D_FREQ 77%AT905 APE 150 MTS fg 0% bg 15% AOAT32.5C GPUAT35C TdiodeAT38.5C PMICAT100C AUXAT33C CPUAT34.5C thermalAT33.75C TboardAT34C GPU 4478/908 CPU 617/745 SOC 2162/1325 CV 0/0 VDDRQ 926/212 SYS5V 3445/2964
RAM 5174/15823MB (lfb 2052x4MB) SWAP 0/40679MB (cached 0MB) CPU [8%AT1143,5%AT1144,9%AT1143,33%AT1144,7%AT1143,6%AT1143,8%AT1143,6%AT1144] EMC_FREQ 29%AT1600 GR3D_FREQ 87%AT905 APE 150 MTS fg 0% bg 16% AOAT33C GPUAT34.5C TdiodeAT38.5C PMICAT100C AUXAT33C CPUAT35C thermalAT33.75C TboardAT34C GPU 3862/1082 CPU 617/737 SOC 2162/1375 CV 0/0 VDDRQ 926/254 SYS5V 3445/2992
RAM 5174/15823MB (lfb 2051x4MB) SWAP 0/40679MB (cached 0MB) CPU [31%AT1143,35%AT1142,32%AT1143,36%AT1144,27%AT1143,26%AT1144,19%AT1145,24%AT1145] EMC_FREQ 42%AT1600 GR3D_FREQ 81%AT905 APE 150 MTS fg 1% bg 15% AOAT33C GPUAT34.5C TdiodeAT38.75C PMICAT100C AUXAT33.5C CPUAT35C thermalAT34.4C TboardAT35C GPU 3089/1193 CPU 1235/765 SOC 2317/1427 CV 0/0 VDDRQ 1081/300 SYS5V 3560/3023
RAM 5172/15823MB (lfb 2051x4MB) SWAP 0/40679MB (cached 0MB) CPU [21%AT1144,15%AT1143,34%AT1144,9%AT1144,9%AT1144,11%AT1146,15%AT1146,9%AT1145] EMC_FREQ 31%AT1600 GR3D_FREQ 51%AT905 APE 150 MTS fg 0% bg 14% AOAT33.5C GPUAT35C TdiodeAT39C PMICAT100C AUXAT33.5C CPUAT35C thermalAT34.4C TboardAT35C GPU 3862/1334 CPU 772/765 SOC 2008/1457 CV 0/0 VDDRQ 772/325 SYS5V 3365/3041
RAM 5177/15823MB (lfb 2051x4MB) SWAP 0/40679MB (cached 0MB) CPU [9%AT1145,11%AT1144,27%AT1145,25%AT1144,8%AT1144,9%AT1144,8%AT1144,7%AT1144] EMC_FREQ 44%AT1600 GR3D_FREQ 93%AT905 APE 150 MTS fg 0% bg 16% AOAT33.5C GPUAT35C TdiodeAT38.75C PMICAT100C AUXAT33.5C CPUAT35C thermalAT34.25C TboardAT35C GPU 3243/1429 CPU 772/766 SOC 2316/1500 CV 0/0 VDDRQ 1235/370 SYS5V 3560/3067
RAM 5177/15823MB (lfb 2050x4MB) SWAP 0/40679MB (cached 0MB) CPU [9%AT1143,9%AT1143,13%AT1143,44%AT1143,4%AT1143,2%AT1142,4%AT1142,6%AT1143] EMC_FREQ 35%AT1600 GR3D_FREQ 58%AT905 APE 150 MTS fg 0% bg 13% AOAT33.5C GPUAT35C TdiodeAT39C PMICAT100C AUXAT33.5C CPUAT35C thermalAT34.4C TboardAT35C GPU 3400/1523 CPU 772/766 SOC 2162/1532 CV 0/0 VDDRQ 772/389 SYS5V 3405/3083
RAM 5177/15823MB (lfb 2050x4MB) SWAP 0/40679MB (cached 0MB) CPU [7%AT1145,6%AT1143,12%AT1144,48%AT1144,4%AT1144,6%AT1144,6%AT1145,5%AT1145] EMC_FREQ 37%AT1600 GR3D_FREQ 34%AT905 APE 150 MTS fg 0% bg 15% AOAT33.5C GPUAT34.5C TdiodeAT39C PMICAT100C AUXAT33.5C CPUAT35C thermalAT34.4C TboardAT35C GPU 2936/1587 CPU 773/766 SOC 2163/1560 CV 0/0 VDDRQ 927/414 SYS5V 3445/3100
RAM 5175/15823MB (lfb 2049x4MB) SWAP 0/40679MB (cached 0MB) CPU [10%AT1144,12%AT1144,20%AT1143,43%AT1143,12%AT1142,16%AT1143,10%AT1143,8%AT1143] EMC_FREQ 34%AT1600 GR3D_FREQ 41%AT905 APE 150 MTS fg 0% bg 19% AOAT33.5C GPUAT34.5C TdiodeAT39.25C PMICAT100C AUXAT33.5C CPUAT35.5C thermalAT34.25C TboardAT35C GPU 3091/1653 CPU 927/773 SOC 2163/1587 CV 0/0 VDDRQ 772/429 SYS5V 3405/3113
RAM 5177/15823MB (lfb 2049x4MB) SWAP 0/40679MB (cached 0MB) CPU [11%AT1143,11%AT1144,23%AT1145,39%AT1144,4%AT1145,4%AT1144,2%AT1145,7%AT1145] EMC_FREQ 28%AT1600 GR3D_FREQ 35%AT905 APE 150 MTS fg 0% bg 15% AOAT33.5C GPUAT34.5C TdiodeAT39.25C PMICAT100C AUXAT34C CPUAT35.5C thermalAT34.6C TboardAT35C GPU 2936/1706 CPU 773/773 SOC 2009/1604 CV 0/0 VDDRQ 618/437 SYS5V 3365/3124
RAM 5177/15823MB (lfb 2049x4MB) SWAP 0/40679MB (cached 0MB) CPU [18%AT1144,12%AT1145,34%AT1143,16%AT1143,28%AT1144,16%AT1143,8%AT1144,13%AT1145] EMC_FREQ 43%AT1600 GR3D_FREQ 61%AT905 APE 150 MTS fg 0% bg 20% AOAT33.5C GPUAT35C TdiodeAT39.25C PMICAT100C AUXAT33.5C CPUAT35.5C thermalAT34.4C TboardAT35C GPU 2935/1755 CPU 927/779 SOC 2317/1633 CV 0/0 VDDRQ 1081/463 SYS5V 3520/3139
RAM 5186/15823MB (lfb 2048x4MB) SWAP 0/40679MB (cached 0MB) CPU [9%AT1144,12%AT1143,41%AT1144,17%AT1143,13%AT1143,10%AT1143,35%AT1145,5%AT1144] EMC_FREQ 31%AT1600 GR3D_FREQ 0%AT905 APE 150 MTS fg 0% bg 20% AOAT33.5C GPUAT34C TdiodeAT39C PMICAT100C AUXAT33.5C CPUAT35.5C thermalAT34.55C TboardAT35C GPU 1392/1741 CPU 1083/791 SOC 1857/1641 CV 0/0 VDDRQ 464/463 SYS5V 3245/3143
RAM 5197/15823MB (lfb 2044x4MB) SWAP 0/40679MB (cached 0MB) CPU [12%AT1143,10%AT1144,89%AT1142,7%AT1142,7%AT1142,9%AT1143,14%AT1143,16%AT1143] EMC_FREQ 15%AT1600 GR3D_FREQ 0%AT905 APE 150 MTS fg 0% bg 21% AOAT33C GPUAT33.5C TdiodeAT39C PMICAT100C AUXAT33.5C CPUAT35C thermalAT34.25C TboardAT35C GPU 619/1700 CPU 1084/802 SOC 1702/1644 CV 0/0 VDDRQ 154/451 SYS5V 3124/3143
RAM 5201/15823MB (lfb 2044x4MB) SWAP 0/40679MB (cached 0MB) CPU [14%AT1144,8%AT1144,79%AT1144,3%AT1143,6%AT1143,6%AT1142,4%AT1142,4%AT1142] EMC_FREQ 7%AT1600 GR3D_FREQ 6%AT905 APE 150 MTS fg 0% bg 16% AOAT33C GPUAT33.5C TdiodeAT39C PMICAT100C AUXAT33.5C CPUAT35C thermalAT34.15C TboardAT35C GPU 619/1661 CPU 929/806 SOC 1703/1646 CV 0/0 VDDRQ 154/441 SYS5V 3084/3141
RAM 5201/15823MB (lfb 2044x4MB) SWAP 0/40679MB (cached 0MB) CPU [22%AT1143,7%AT1144,3%AT1143,7%AT1142,4%AT1142,6%AT1143,4%AT1143,4%AT1143] EMC_FREQ 4%AT1600 GR3D_FREQ 0%AT905 APE 150 MTS fg 0% bg 10% AOAT33C GPUAT34C TdiodeAT38.75C PMICAT100C AUXAT34C CPUAT35C thermalAT34.15C TboardAT35C GPU 774/1630 CPU 619/800 SOC 1703/1648 CV 0/0 VDDRQ 154/431 SYS5V 3124/3140
RAM 5198/15823MB (lfb 2043x4MB) SWAP 0/40679MB (cached 0MB) CPU [20%AT1142,10%AT1142,5%AT1141,7%AT1143,3%AT1142,2%AT1143,7%AT1143,4%AT1144] EMC_FREQ 3%AT1600 GR3D_FREQ 5%AT905 APE 150 MTS fg 0% bg 11% AOAT33C GPUAT33.5C TdiodeAT38.75C PMICAT100C AUXAT34C CPUAT35C thermalAT34.15C TboardAT35C GPU 774/1602 CPU 619/794 SOC 1703/1649 CV 0/0 VDDRQ 154/422 SYS5V 3165/3141
RAM 5200/15823MB (lfb 2043x4MB) SWAP 0/40679MB (cached 0MB) CPU [18%AT1144,5%AT1143,8%AT1143,10%AT1143,15%AT1144,5%AT1143,4%AT1143,3%AT1143] EMC_FREQ 3%AT1600 GR3D_FREQ 0%AT905 APE 150 MTS fg 0% bg 14% AOAT33.5C GPUAT33.5C TdiodeAT38.75C PMICAT100C AUXAT33.5C CPUAT35C thermalAT33.95C TboardAT35C GPU 774/1575 CPU 619/788 SOC 1703/1651 CV 0/0 VDDRQ 154/413 SYS5V 3124/3140
RAM 3935/15823MB (lfb 2119x4MB) SWAP 0/40679MB (cached 0MB) CPU [9%AT1144,3%AT1144,3%AT1144,4%AT1144,58%AT1144,16%AT1143,6%AT1145,4%AT1144] EMC_FREQ 3%AT1331 GR3D_FREQ 0%AT624 APE 150 MTS fg 0% bg 17% AOAT32.5C GPUAT33.5C TdiodeAT38.75C PMICAT100C AUXAT33.5C CPUAT34.5C thermalAT33.95C TboardAT35C GPU 619/1545 CPU 619/783 SOC 1703/1653 CV 0/0 VDDRQ 154/405 SYS5V 3124/3140
RAM 3936/15823MB (lfb 2119x4MB) SWAP 0/40679MB (cached 0MB) CPU [2%AT1143,3%AT1143,5%AT1143,4%AT1143,4%AT1143,4%AT1143,4%AT1143,2%AT1143] EMC_FREQ 4%AT800 GR3D_FREQ 0%AT522 APE 150 MTS fg 0% bg 9% AOAT33C GPUAT34.5C TdiodeAT38.5C PMICAT100C AUXAT33.5C CPUAT34.5C thermalAT33.95C TboardAT35C GPU 310/1508 CPU 465/773 SOC 1240/1640 CV 0/0 VDDRQ 0/393 SYS5V 2844/3131

Camera config

Type - 1=CameraV4L2 2=URI 3=MultiURI
type=1
camera-width=640
camera-height=480
camera-fps-n=30
camera-fps-d=1
camera-v4l2-dev-node=0

Camera config

Bus 001 Device 007: ID 046d:0991 Logitech, Inc. QuickCam Pro for Notebooks

[30260.055988] usb 1-4.2: usb_suspend_both: status 0
[30414.906228] usb 1-4.2: USB disconnect, device number 3
[30417.177822] usb 1-4.2: new high-speed USB device number 6 using tegra-xusb
[30417.326452] usb 1-4.2: New USB device found, idVendor=046d, idProduct=0991
[30417.326477] usb 1-4.2: New USB device strings: Mfr=0, Product=0, SerialNumber=2
[30417.326485] usb 1-4.2: SerialNumber: AEC8EAEF
[30417.329309] uvcvideo: Found UVC 1.00 device (046d:0991)
[30417.360228] uvcvideo 1-4.2:1.0: Entity type for entity Extension 4 was not initialized!
[30417.360434] uvcvideo 1-4.2:1.0: Entity type for entity Extension 10 was not initialized!
[30417.360594] uvcvideo 1-4.2:1.0: Entity type for entity Extension 12 was not initialized!
[30417.360778] uvcvideo 1-4.2:1.0: Entity type for entity Extension 8 was not initialized!
[30417.360933] uvcvideo 1-4.2:1.0: Entity type for entity Extension 11 was not initialized!
[30417.361090] uvcvideo 1-4.2:1.0: Entity type for entity Extension 9 was not initialized!
[30417.361246] uvcvideo 1-4.2:1.0: Entity type for entity Processing 2 was not initialized!
[30417.361401] uvcvideo 1-4.2:1.0: Entity type for entity Extension 13 was not initialized!
[30417.361574] uvcvideo 1-4.2:1.0: Entity type for entity Camera 1 was not initialized!
[30417.362371] input: UVC Camera (046d:0991) as /devices/3610000.xhci/usb1/1-4/1-4.2/1-4.2:1.0/input/input11
[30417.384441] usb 1-4.2: set resolution quirk: cval->res = 384

I’ve also saw in the dmesg

[29703.512823] nvmap_alloc_handle: PID 15620: deepstream-test: WARNING: All NvMap Allocations must have a tag to identify the subsystem allocating memory.Please pass the tag to the API call NvRmMemHanldeAllocAttr() or relevant.

I’ve tried with different fps on camera and still crashing.

I’ve observed that this is crashing when human starts to be visible in the frame.

Thanks for helping.

Hi,

Sorry for the late update.

It sounds like this issue is context related.
Would you mind to record a video that can reproduce this issue for us?

Thanks.

There is no update from you for a period, assuming this is not an issue any more.
Hence we are closing this topic. If need further support, please open a new one.
Thanks

Hi mibartecki,

Is this still an issue to support?
Please record a video that can reproduce this issue for us.

Thanks