I’m trying to run deepstream-preprocess-test on Jetson Xavier NX using image nvcr.io/nvidia/deepstream-l4t:6.0-base. For some reason, I got the following errors (only part of the errors)
0:00:00.099923249 3110 0x55a9ddae00 INFO GST_PLUGIN_LOADING gstplugin.c:901:_priv_gst_plugin_load_file_for_registry: plugin "/usr/lib/aarch64-linux-gnu/gstreamer-1.0/deepstream/libnvdsgst_multistreamtiler.so" loaded
0:00:00.100000722 3110 0x55a9ddae00 INFO GST_ELEMENT_FACTORY gstelementfactory.c:359:gst_element_factory_create: creating element "nvmultistreamtiler" named "nvtiler"
0:00:00.100802013 3110 0x55a9ddae00 INFO GST_ELEMENT_PADS gstelement.c:670:gst_element_add_pad:<GstBaseTransform@0x55aa0a83f0> adding pad 'sink'
0:00:00.100857822 3110 0x55a9ddae00 INFO GST_ELEMENT_PADS gstelement.c:670:gst_element_add_pad:<GstBaseTransform@0x55aa0a83f0> adding pad 'src'
0:00:00.102135950 3110 0x55a9ddae00 INFO GST_PLUGIN_LOADING gstplugin.c:901:_priv_gst_plugin_load_file_for_registry: plugin "/usr/lib/aarch64-linux-gnu/gstreamer-1.0/deepstream/libgstnvvideoconvert.so" loaded
0:00:00.102263952 3110 0x55a9ddae00 INFO GST_ELEMENT_FACTORY gstelementfactory.c:359:gst_element_factory_create: creating element "nvvideoconvert" named "nvvideo-converter"
0:00:00.102657685 3110 0x55a9ddae00 INFO GST_ELEMENT_PADS gstelement.c:670:gst_element_add_pad:<GstBaseTransform@0x55aa0ab2f0> adding pad 'sink'
0:00:00.102714966 3110 0x55a9ddae00 INFO GST_ELEMENT_PADS gstelement.c:670:gst_element_add_pad:<GstBaseTransform@0x55aa0ab2f0> adding pad 'src'
0:00:00.102790647 3110 0x55a9ddae00 WARN GST_ELEMENT_FACTORY gstelementfactory.c:456:gst_element_factory_make: no such element factory "nvdsosd"!
0:00:00.103687554 3110 0x55a9ddae00 INFO GST_PLUGIN_LOADING gstplugin.c:901:_priv_gst_plugin_load_file_for_registry: plugin "/usr/lib/aarch64-linux-gnu/gstreamer-1.0/libgstnvegltransform.so" loaded
0:00:00.103738915 3110 0x55a9ddae00 INFO GST_ELEMENT_FACTORY gstelementfactory.c:359:gst_element_factory_create: creating element "nvegltransform" named "nvegl-transform"
0:00:00.104048423 3110 0x55a9ddae00 INFO GST_ELEMENT_PADS gstelement.c:670:gst_element_add_pad:<GstBaseTransform@0x55aa0b0130> adding pad 'sink'
0:00:00.104100968 3110 0x55a9ddae00 INFO GST_ELEMENT_PADS gstelement.c:670:gst_element_add_pad:<GstBaseTransform@0x55aa0b0130> adding pad 'src'
0:00:00.104138568 3110 0x55a9ddae00 INFO GST_ELEMENT_FACTORY gstelementfactory.c:359:gst_element_factory_create: creating element "fakesink" named "nvvideo-renderer"
0:00:00.104519405 3110 0x55a9ddae00 INFO GST_ELEMENT_PADS gstelement.c:670:gst_element_add_pad:<GstBaseSink@0x55aa0a6a40> adding pad 'sink'
the plugins can’t be created. Attached is the resources to reproduce this.
deepstream_test_apps.tar.gz (6.8 MB)
Steps to reproduce
docker run --gpus all -it --rm nvcr.io/nvidia/deepstream-l4t:6.0-base- install the some libs
apt-get install libgstreamer1.0-dev libgstreamer-plugins-base1.0-dev libgstreamer-plugins-bad1.0-dev gstreamer1.0-plugins-base gstreamer1.0-plugins-good gstreamer1.0-plugins-bad gstreamer1.0-plugins-ugly gstreamer1.0-libav gstreamer1.0-doc gstreamer1.0-tools gstreamer1.0-x gstreamer1.0-alsa gstreamer1.0-gl gstreamer1.0-gtk3 gstreamer1.0-qt5 gstreamer1.0-pulseaudio
- modify Makefile, model paths to correct the paths
- build and run the following
GST_DEBUG="*:4" ./deepstream-preprocess-test config_preprocess.txt config_infer.txt file:///root/sample_720p.h264
I tried this code on X86_64 and it worked fine.
Environment
HW: Jetson Xavier NX
Package: L4T 32.5.0 [ JetPack 4.5 ]
CUDA: 10.2.89
Architecture: arm64
Issue Type: Question
head /etc/nv_tegra_release
# R32 (release), REVISION: 5.0, GCID: 25531747, BOARD: t186ref, EABI: aarch64, DATE: Fri Jan 15 23:21:05 UTC 2021
-
Have you installed JetPack 4.5 correctly in the host NX board? The cuda and TensorRT maust be installed in host before you start the docker.
-
Please make sure you have installed nvidia-container correct before you start the docker container.
Run "sudo apt update"
Run "sudo apt install nvidia-container"
Run "sudo service docker restart"
- Please use the docker command recommended in Your First Jetson Container | NVIDIA Developer to start your container.
No error in what you post here.
please check the warning log
WARN GST_ELEMENT_FACTORY gstelementfactory.c:456:gst_element_factory_make: no such element factory "nvdsosd"!
The following is the full log
root@e289f501b83f:~/deepstream-preprocess-test# GST_DEBUG="*:4" ./deepstream-preprocess-test config_preprocess.txt config_infer.txt file:///root/sample_720p.h264
0:00:00.000180610 29 0x55be701e00 INFO GST_INIT gst.c:586:init_pre: Initializing GStreamer Core Library version 1.14.5
0:00:00.000279747 29 0x55be701e00 INFO GST_INIT gst.c:587:init_pre: Using library installed in /usr/lib/aarch64-linux-gnu
0:00:00.000315331 29 0x55be701e00 INFO GST_INIT gst.c:607:init_pre: Linux e289f501b83f 4.9.201-tegra #1 SMP PREEMPT Wed Mar 17 17:10:20 CST 2021 aarch64
0:00:00.000915657 29 0x55be701e00 INFO GST_INIT gstmessage.c:127:_priv_gst_message_initialize: init messages
0:00:00.002507768 29 0x55be701e00 INFO GST_INIT gstcontext.c:84:_priv_gst_context_initialize: init contexts
0:00:00.003083517 29 0x55be701e00 INFO GST_PLUGIN_LOADING gstplugin.c:317:_priv_gst_plugin_initialize: registering 0 static plugins
0:00:00.003359744 29 0x55be701e00 INFO GST_PLUGIN_LOADING gstplugin.c:225:gst_plugin_register_static: registered static plugin "staticelements"
0:00:00.003421377 29 0x55be701e00 INFO GST_PLUGIN_LOADING gstplugin.c:227:gst_plugin_register_static: added static plugin "staticelements", result: 1
0:00:00.003494497 29 0x55be701e00 INFO GST_REGISTRY gstregistry.c:1727:ensure_current_registry: reading registry cache: /root/.cache/gstreamer-1.0/registry.aarch64.bin
0:00:00.058329833 29 0x55be701e00 INFO GST_REGISTRY gstregistrybinary.c:621:priv_gst_registry_binary_read_cache: loaded /root/.cache/gstreamer-1.0/registry.aarch64.bin in 0.054746 seconds
0:00:00.058487691 29 0x55be701e00 INFO GST_REGISTRY gstregistry.c:1583:scan_and_update_registry: Validating plugins from registry cache: /root/.cache/gstreamer-1.0/registry.aarch64.bin
0:00:00.063883582 29 0x55be701e00 INFO GST_REGISTRY gstregistry.c:1685:scan_and_update_registry: Registry cache has not changed
0:00:00.063930590 29 0x55be701e00 INFO GST_REGISTRY gstregistry.c:1762:ensure_current_registry: registry reading and updating done, result = 1
0:00:00.063953407 29 0x55be701e00 INFO GST_INIT gst.c:807:init_post: GLib runtime version: 2.56.4
0:00:00.063972415 29 0x55be701e00 INFO GST_INIT gst.c:809:init_post: GLib headers version: 2.56.4
0:00:00.063985503 29 0x55be701e00 INFO GST_INIT gst.c:810:init_post: initialized GStreamer successfully
0:00:00.064063776 29 0x55be701e00 INFO GST_ELEMENT_FACTORY gstelementfactory.c:359:gst_element_factory_create: creating element "pipeline" named "preprocess-test-pipeline"
0:00:00.088598600 29 0x55be701e00 INFO GST_PLUGIN_LOADING gstplugin.c:901:_priv_gst_plugin_load_file_for_registry: plugin "/usr/lib/aarch64-linux-gnu/gstreamer-1.0/deepstream/libnvdsgst_multistream.so" loaded
0:00:00.088660553 29 0x55be701e00 INFO GST_ELEMENT_FACTORY gstelementfactory.c:359:gst_element_factory_create: creating element "nvstreammux" named "stream-muxer"
0:00:00.089379312 29 0x55be701e00 INFO GST_ELEMENT_PADS gstelement.c:670:gst_element_add_pad:<GstNvStreamMux@0x55be9a6090> adding pad 'src'
0:00:00.089601874 29 0x55be701e00 INFO GST_ELEMENT_FACTORY gstelementfactory.c:359:gst_element_factory_create: creating element "bin" named "source-bin-00"
0:00:00.091356098 29 0x55be701e00 INFO GST_PLUGIN_LOADING gstplugin.c:901:_priv_gst_plugin_load_file_for_registry: plugin "/usr/lib/aarch64-linux-gnu/gstreamer-1.0/libgstplayback.so" loaded
0:00:00.091395107 29 0x55be701e00 INFO GST_ELEMENT_FACTORY gstelementfactory.c:359:gst_element_factory_create: creating element "uridecodebin" named "uri-decode-bin"
0:00:00.092228331 29 0x55be701e00 INFO GST_ELEMENT_PADS gstelement.c:670:gst_element_add_pad:<source-bin-00> adding pad 'src'
0:00:00.092314315 29 0x55be701e00 INFO GST_ELEMENT_PADS gstelement.c:917:gst_element_get_static_pad: no such pad 'sink_0' in element "stream-muxer"
0:00:00.092393292 29 0x55be701e00 INFO GST_ELEMENT_PADS gstelement.c:670:gst_element_add_pad:<stream-muxer> adding pad 'sink_0'
0:00:00.092436237 29 0x55be701e00 INFO GST_ELEMENT_PADS gstelement.c:920:gst_element_get_static_pad: found pad source-bin-00:src
0:00:00.092479853 29 0x55be701e00 INFO GST_PADS gstpad.c:2378:gst_pad_link_prepare: trying to link source-bin-00:src and stream-muxer:sink_0
0:00:00.092549390 29 0x55be701e00 INFO GST_PADS gstpad.c:4232:gst_pad_peer_query:<src:proxypad0> pad has no peer
0:00:00.092770832 29 0x55be701e00 INFO GST_PADS gstpad.c:4232:gst_pad_peer_query:<stream-muxer:src> pad has no peer
0:00:00.092883377 29 0x55be701e00 INFO GST_PADS gstpad.c:2586:gst_pad_link_full: linked source-bin-00:src and stream-muxer:sink_0, successful
0:00:00.092905553 29 0x55be701e00 INFO GST_EVENT gstevent.c:1517:gst_event_new_reconfigure: creating reconfigure event
0:00:00.092923377 29 0x55be701e00 INFO GST_EVENT gstpad.c:5808:gst_pad_send_event_unchecked:<source-bin-00:src> Received event on flushing pad. Discarding
0:00:00.092965074 29 0x55be701e00 WARN GST_ELEMENT_FACTORY gstelementfactory.c:456:gst_element_factory_make: no such element factory "nvdspreprocess"!
0:00:00.092986866 29 0x55be701e00 WARN GST_ELEMENT_FACTORY gstelementfactory.c:456:gst_element_factory_make: no such element factory "nvinfer"!
0:00:00.094174333 29 0x55be701e00 INFO GST_PLUGIN_LOADING gstplugin.c:901:_priv_gst_plugin_load_file_for_registry: plugin "/usr/lib/aarch64-linux-gnu/gstreamer-1.0/libgstcoreelements.so" loaded
0:00:00.094243838 29 0x55be701e00 INFO GST_ELEMENT_FACTORY gstelementfactory.c:359:gst_element_factory_create: creating element "queue" named "queue1"
0:00:00.094575617 29 0x55be701e00 INFO GST_ELEMENT_PADS gstelement.c:670:gst_element_add_pad:<GstQueue@0x55be9bc080> adding pad 'sink'
0:00:00.094638369 29 0x55be701e00 INFO GST_ELEMENT_PADS gstelement.c:670:gst_element_add_pad:<GstQueue@0x55be9bc080> adding pad 'src'
0:00:00.094712546 29 0x55be701e00 INFO GST_ELEMENT_FACTORY gstelementfactory.c:359:gst_element_factory_create: creating element "queue" named "queue2"
0:00:00.094808643 29 0x55be701e00 INFO GST_ELEMENT_PADS gstelement.c:670:gst_element_add_pad:<GstQueue@0x55be9bc380> adding pad 'sink'
0:00:00.094864836 29 0x55be701e00 INFO GST_ELEMENT_PADS gstelement.c:670:gst_element_add_pad:<GstQueue@0x55be9bc380> adding pad 'src'
0:00:00.094935300 29 0x55be701e00 INFO GST_ELEMENT_FACTORY gstelementfactory.c:359:gst_element_factory_create: creating element "queue" named "queue3"
0:00:00.094992997 29 0x55be701e00 INFO GST_ELEMENT_PADS gstelement.c:670:gst_element_add_pad:<GstQueue@0x55be9bc680> adding pad 'sink'
0:00:00.095045253 29 0x55be701e00 INFO GST_ELEMENT_PADS gstelement.c:670:gst_element_add_pad:<GstQueue@0x55be9bc680> adding pad 'src'
0:00:00.095122278 29 0x55be701e00 INFO GST_ELEMENT_FACTORY gstelementfactory.c:359:gst_element_factory_create: creating element "queue" named "queue4"
0:00:00.095179527 29 0x55be701e00 INFO GST_ELEMENT_PADS gstelement.c:670:gst_element_add_pad:<GstQueue@0x55be9bc980> adding pad 'sink'
0:00:00.095231111 29 0x55be701e00 INFO GST_ELEMENT_PADS gstelement.c:670:gst_element_add_pad:<GstQueue@0x55be9bc980> adding pad 'src'
0:00:00.095279208 29 0x55be701e00 INFO GST_ELEMENT_FACTORY gstelementfactory.c:359:gst_element_factory_create: creating element "queue" named "queue5"
0:00:00.095389385 29 0x55be701e00 INFO GST_ELEMENT_PADS gstelement.c:670:gst_element_add_pad:<GstQueue@0x55be9bcc80> adding pad 'sink'
0:00:00.095444873 29 0x55be701e00 INFO GST_ELEMENT_PADS gstelement.c:670:gst_element_add_pad:<GstQueue@0x55be9bcc80> adding pad 'src'
0:00:00.095510282 29 0x55be701e00 INFO GST_ELEMENT_FACTORY gstelementfactory.c:359:gst_element_factory_create: creating element "queue" named "queue6"
0:00:00.095582218 29 0x55be701e00 INFO GST_ELEMENT_PADS gstelement.c:670:gst_element_add_pad:<GstQueue@0x55be9bcf80> adding pad 'sink'
0:00:00.095664331 29 0x55be701e00 INFO GST_ELEMENT_PADS gstelement.c:670:gst_element_add_pad:<GstQueue@0x55be9bcf80> adding pad 'src'
0:00:00.096922103 29 0x55be701e00 INFO GST_PLUGIN_LOADING gstplugin.c:901:_priv_gst_plugin_load_file_for_registry: plugin "/usr/lib/aarch64-linux-gnu/gstreamer-1.0/deepstream/libnvdsgst_multistreamtiler.so" loaded
0:00:00.096957047 29 0x55be701e00 INFO GST_ELEMENT_FACTORY gstelementfactory.c:359:gst_element_factory_create: creating element "nvmultistreamtiler" named "nvtiler"
0:00:00.097341211 29 0x55be701e00 INFO GST_ELEMENT_PADS gstelement.c:670:gst_element_add_pad:<GstBaseTransform@0x55be9cee90> adding pad 'sink'
0:00:00.097413180 29 0x55be701e00 INFO GST_ELEMENT_PADS gstelement.c:670:gst_element_add_pad:<GstBaseTransform@0x55be9cee90> adding pad 'src'
0:00:00.098495782 29 0x55be701e00 INFO GST_PLUGIN_LOADING gstplugin.c:901:_priv_gst_plugin_load_file_for_registry: plugin "/usr/lib/aarch64-linux-gnu/gstreamer-1.0/deepstream/libgstnvvideoconvert.so" loaded
0:00:00.098534342 29 0x55be701e00 INFO GST_ELEMENT_FACTORY gstelementfactory.c:359:gst_element_factory_create: creating element "nvvideoconvert" named "nvvideo-converter"
0:00:00.098975403 29 0x55be701e00 INFO GST_ELEMENT_PADS gstelement.c:670:gst_element_add_pad:<GstBaseTransform@0x55be9d1d70> adding pad 'sink'
0:00:00.099032075 29 0x55be701e00 INFO GST_ELEMENT_PADS gstelement.c:670:gst_element_add_pad:<GstBaseTransform@0x55be9d1d70> adding pad 'src'
0:00:00.099125324 29 0x55be701e00 WARN GST_ELEMENT_FACTORY gstelementfactory.c:456:gst_element_factory_make: no such element factory "nvdsosd"!
0:00:00.099799250 29 0x55be701e00 INFO GST_PLUGIN_LOADING gstplugin.c:901:_priv_gst_plugin_load_file_for_registry: plugin "/usr/lib/aarch64-linux-gnu/gstreamer-1.0/libgstnvegltransform.so" loaded
0:00:00.099839187 29 0x55be701e00 INFO GST_ELEMENT_FACTORY gstelementfactory.c:359:gst_element_factory_create: creating element "nvegltransform" named "nvegl-transform"
0:00:00.100073909 29 0x55be701e00 INFO GST_ELEMENT_PADS gstelement.c:670:gst_element_add_pad:<GstBaseTransform@0x55be9d8130> adding pad 'sink'
0:00:00.100120565 29 0x55be701e00 INFO GST_ELEMENT_PADS gstelement.c:670:gst_element_add_pad:<GstBaseTransform@0x55be9d8130> adding pad 'src'
0:00:00.100155478 29 0x55be701e00 INFO GST_ELEMENT_FACTORY gstelementfactory.c:359:gst_element_factory_create: creating element "fakesink" named "nvvideo-renderer"
0:00:00.100498009 29 0x55be701e00 INFO GST_ELEMENT_PADS gstelement.c:670:gst_element_add_pad:<GstBaseSink@0x55be9cd120> adding pad 'sink'
TensorRT and CUDA were installed currectly
root@e289f501b83f:~/deepstream-preprocess-test# /usr/local/cuda/bin/deviceQuery
/usr/local/cuda/bin/deviceQuery Starting...
CUDA Device Query (Runtime API) version (CUDART static linking)
Detected 1 CUDA Capable device(s)
Device 0: "Xavier"
CUDA Driver Version / Runtime Version 10.2 / 10.2
CUDA Capability Major/Minor version number: 7.2
Total amount of global memory: 7774 MBytes (8151154688 bytes)
( 6) Multiprocessors, ( 64) CUDA Cores/MP: 384 CUDA Cores
GPU Max Clock rate: 1109 MHz (1.11 GHz)
Memory Clock rate: 1109 Mhz
Memory Bus Width: 256-bit
L2 Cache Size: 524288 bytes
Maximum Texture Dimension Size (x,y,z) 1D=(131072), 2D=(131072, 65536), 3D=(16384, 16384, 16384)
Maximum Layered 1D Texture Size, (num) layers 1D=(32768), 2048 layers
Maximum Layered 2D Texture Size, (num) layers 2D=(32768, 32768), 2048 layers
Total amount of constant memory: 65536 bytes
Total amount of shared memory per block: 49152 bytes
Total number of registers available per block: 65536
Warp size: 32
Maximum number of threads per multiprocessor: 2048
Maximum number of threads per block: 1024
Max dimension size of a thread block (x,y,z): (1024, 1024, 64)
Max dimension size of a grid size (x,y,z): (2147483647, 65535, 65535)
Maximum memory pitch: 2147483647 bytes
Texture alignment: 512 bytes
Concurrent copy and kernel execution: Yes with 1 copy engine(s)
Run time limit on kernels: No
Integrated GPU sharing Host Memory: Yes
Support host page-locked memory mapping: Yes
Alignment requirement for Surfaces: Yes
Device has ECC support: Disabled
Device supports Unified Addressing (UVA): Yes
Device supports Compute Preemption: Yes
Supports Cooperative Kernel Launch: Yes
Supports MultiDevice Co-op Kernel Launch: Yes
Device PCI Domain ID / Bus ID / location ID: 0 / 0 / 0
Compute Mode:
< Default (multiple host threads can use ::cudaSetDevice() with device simultaneously) >
deviceQuery, CUDA Driver = CUDART, CUDA Driver Version = 10.2, CUDA Runtime Version = 10.2, NumDevs = 1
Result = PASS
root@e289f501b83f:~/deepstream-preprocess-test# /usr/src/tensorrt/
bin/ data/ samples/
root@e289f501b83f:~/deepstream-preprocess-test# /usr/src/tensorrt/bin/trtexec
&&&& RUNNING TensorRT.trtexec # /usr/src/tensorrt/bin/trtexec
...
aaeon@aaeon-desktop:~$ sudo apt install nvidia-container
Reading package lists... Done
Building dependency tree
Reading state information... Done
E: Unable to locate package nvidia-container
are you sure it’s the right name?
When I changed from --gpus all to --runtime nvidia I still got the same error e.g. no such element factory "nvdsosd"!
Do I need to change docker image to nvcr.io/nvidia/l4t-base:r32.4.3 too? What’s the difference between this image and nvcr.io/nvidia/deepstream-l4t:6.0-base?
I’m using the same docker command but in Jetson Nano, every worked .
Have you run “sudo apt update” before installing nvidia-container?
There is no DeepStream on JetPack 4.5. Please upgrade to JetPack 4.5.1 with DeepStream 5.1 GA at least. Even better to the latest JetPack 5.0.2 with DeepStream 6.1.1
There is no “nvdspreprocess” plugin in DeepStream 5.1. Why do you run an application which is not compatible to your JetPack version and DeepStream version?
Please follow the platform compatibility. Quickstart Guide — DeepStream 6.3 Release documentation
1 Like
Thanks for your response. I checked the link you sent, right now I need JetPack 4.6. I’m trying to install it using ubuntu command line. According to How to Install JetPack :: NVIDIA JetPack Documentation , we can do
sudo apt update
sudo apt install nvidia-jetpack
In my case, after sudo apt update, i got
aaeon@aaeon-desktop:~$ sudo apt install nvidia-jetpack
Reading package lists... Done
Building dependency tree
Reading state information... Done
E: Unable to locate package nvidia-jetpack
Do you know the fix? and also can we specify the version we want e.g. nvidia-jetpack-4.6?
Thanks
I followed Quickstart Guide — DeepStream 6.0 Release documentation and followed the following sections
- Install latest NVIDIA BSP packages
- and check
aaeon@aaeon-desktop:~$ sudo apt-cache show nvidia-jetpack
[sudo] password for aaeon:
Package: nvidia-jetpack
Version: 4.6-b199
Architecture: arm64
Maintainer: NVIDIA Corporation
Installed-Size: 194
Depends: nvidia-cuda (= 4.6-b199), nvidia-opencv (= 4.6-b199), nvidia-cudnn8 (= 4.6-b199), nvidia-tensorrt (= 4.6-b199), nvidia-visionworks (= 4.6-b199), nvidia-container (= 4.6-b199), nvidia-vpi (= 4.6-b199), nvidia-l4t-jetson-multimedia-api (>> 32.6-0), nvidia-l4t-jetson-multimedia-api (<< 32.7-0)
Homepage: http://developer.nvidia.com/jetson
Priority: standard
Section: metapackages
Filename: pool/main/n/nvidia-jetpack/nvidia-jetpack_4.6-b199_arm64.deb
Size: 29376
SHA256: d67b85293cade45d81dcafebd46c70a97a0b0d1379ca48aaa79d70d8ba99ddf8
SHA1: 74d9cbdfe9af52baa667e321749b9771101fc6de
MD5sum: cd1b3a0b651cd214b15fa76f6b5af2cd
Description: NVIDIA Jetpack Meta Package
Description-md5: ad1462289bdbc54909ae109d1d32c0a8
Package: nvidia-jetpack
Version: 4.6-b197
Architecture: arm64
Maintainer: NVIDIA Corporation
Installed-Size: 194
Depends: nvidia-cuda (= 4.6-b197), nvidia-opencv (= 4.6-b197), nvidia-cudnn8 (= 4.6-b197), nvidia-tensorrt (= 4.6-b197), nvidia-visionworks (= 4.6-b197), nvidia-container (= 4.6-b197), nvidia-vpi (= 4.6-b197), nvidia-l4t-jetson-multimedia-api (>> 32.6-0), nvidia-l4t-jetson-multimedia-api (<< 32.7-0)
Homepage: http://developer.nvidia.com/jetson
Priority: standard
Section: metapackages
Filename: pool/main/n/nvidia-jetpack/nvidia-jetpack_4.6-b197_arm64.deb
Size: 29372
SHA256: acec83ad0c1ef05caf9b8ccc6a975c4fb2a7f7830cbe63bbcf7b196a6c1f350e
SHA1: 3e11456cf0ec6b3a40d81b80ca1e14cebafa65ff
MD5sum: 72b2b7b280793bd4abdabe0d38b08535
Description: NVIDIA Jetpack Meta Package
Description-md5: ad1462289bdbc54909ae109d1d32c0a8
JetPack 4.6 has been installed then I tried
docker run --runtime nvidia -it --name test nvcr.io/nvidia/deepstream-l4t:6.0-base- copy the files to this docker container under /root
- build
CUDA_VER=10.2 make
- then run
GST_DEBUG="*:4" ./deepstream-preprocess-test config_preprocess.txt config_infer.txt file:///root/sample_720p.h264
I still got the same result
...
0:00:00.119870927 725 0x55bbf37e00 WARN GST_ELEMENT_FACTORY gstelementfactory.c:456:gst_element_factory_make: no such element factory "nvinfer"!
:00:00.128628358 725 0x55bbf37e00 WARN GST_ELEMENT_FACTORY gstelementfactory.c:456:gst_element_factory_make: no such element factory "nvdsosd"!
...
Is CUDA installed? Can you run “ldd /opt/nvidia/deepstream/deepstream/lib/gst-plugins/libnvdsgst_osd.so”?
outside docker /opt/nvidia/deepstream/deepstream/lib/gst-plugins/libnvdsgst_osd.so does not exist. In side docker container, I got
linux-vdso.so.1 (0x0000007f919af000)
libgstbase-1.0.so.0 => /usr/lib/aarch64-linux-gnu/libgstbase-1.0.so.0 (0x0000007f91877000)
libgstreamer-1.0.so.0 => /usr/lib/aarch64-linux-gnu/libgstreamer-1.0.so.0 (0x0000007f91747000)
libglib-2.0.so.0 => /usr/lib/aarch64-linux-gnu/libglib-2.0.so.0 (0x0000007f91638000)
libgobject-2.0.so.0 => /usr/lib/aarch64-linux-gnu/libgobject-2.0.so.0 (0x0000007f915db000)
libnvds_osd.so => /opt/nvidia/deepstream/deepstream-6.0/lib/libnvds_osd.so (0x0000007f9155a000)
libnvdsgst_meta.so => /opt/nvidia/deepstream/deepstream-6.0/lib/libnvdsgst_meta.so (0x0000007f91545000)
libdl.so.2 => /lib/aarch64-linux-gnu/libdl.so.2 (0x0000007f91530000)
libpthread.so.0 => /lib/aarch64-linux-gnu/libpthread.so.0 (0x0000007f91504000)
librt.so.1 => /lib/aarch64-linux-gnu/librt.so.1 (0x0000007f914ed000)
libc.so.6 => /lib/aarch64-linux-gnu/libc.so.6 (0x0000007f91394000)
/lib/ld-linux-aarch64.so.1 (0x0000007f91983000)
libgmodule-2.0.so.0 => /usr/lib/aarch64-linux-gnu/libgmodule-2.0.so.0 (0x0000007f91380000)
libm.so.6 => /lib/aarch64-linux-gnu/libm.so.6 (0x0000007f912c7000)
libpcre.so.3 => /lib/aarch64-linux-gnu/libpcre.so.3 (0x0000007f91255000)
libffi.so.6 => /usr/lib/aarch64-linux-gnu/libffi.so.6 (0x0000007f9123d000)
libcairo.so.2 => /usr/lib/aarch64-linux-gnu/libcairo.so.2 (0x0000007f91143000)
libpango-1.0.so.0 => /usr/lib/aarch64-linux-gnu/libpango-1.0.so.0 (0x0000007f910ec000)
libpangocairo-1.0.so.0 => /usr/lib/aarch64-linux-gnu/libpangocairo-1.0.so.0 (0x0000007f910d0000)
libnvbufsurface.so.1.0.0 => /usr/lib/aarch64-linux-gnu/tegra/libnvbufsurface.so.1.0.0 (0x0000007f91052000)
libnvbufsurftransform.so.1.0.0 => /usr/lib/aarch64-linux-gnu/tegra/libnvbufsurftransform.so.1.0.0 (0x0000007f8f0fa000)
libnvds_utils.so => /opt/nvidia/deepstream/deepstream-6.0/lib/libnvds_utils.so (0x0000007f8eb88000)
libcuda.so.1 => /usr/lib/aarch64-linux-gnu/libcuda.so.1 (0x0000007f8dc45000)
libstdc++.so.6 => /usr/lib/aarch64-linux-gnu/libstdc++.so.6 (0x0000007f8dab1000)
libnvds_meta.so => /opt/nvidia/deepstream/deepstream-6.0/lib/libnvds_meta.so (0x0000007f8da9a000)
libpixman-1.so.0 => /usr/lib/aarch64-linux-gnu/libpixman-1.so.0 (0x0000007f8da36000)
libfontconfig.so.1 => /usr/lib/aarch64-linux-gnu/libfontconfig.so.1 (0x0000007f8d9e6000)
libfreetype.so.6 => /usr/lib/aarch64-linux-gnu/libfreetype.so.6 (0x0000007f8d93e000)
libpng16.so.16 => /usr/lib/aarch64-linux-gnu/libpng16.so.16 (0x0000007f8d903000)
libxcb-shm.so.0 => /usr/lib/aarch64-linux-gnu/libxcb-shm.so.0 (0x0000007f8d8f0000)
libxcb.so.1 => /usr/lib/aarch64-linux-gnu/libxcb.so.1 (0x0000007f8d8c0000)
libxcb-render.so.0 => /usr/lib/aarch64-linux-gnu/libxcb-render.so.0 (0x0000007f8d8a5000)
libXrender.so.1 => /usr/lib/aarch64-linux-gnu/libXrender.so.1 (0x0000007f8d88c000)
libX11.so.6 => /usr/lib/aarch64-linux-gnu/libX11.so.6 (0x0000007f8d762000)
libXext.so.6 => /usr/lib/aarch64-linux-gnu/libXext.so.6 (0x0000007f8d742000)
libz.so.1 => /lib/aarch64-linux-gnu/libz.so.1 (0x0000007f8d715000)
libthai.so.0 => /usr/lib/aarch64-linux-gnu/libthai.so.0 (0x0000007f8d6fd000)
libpangoft2-1.0.so.0 => /usr/lib/aarch64-linux-gnu/libpangoft2-1.0.so.0 (0x0000007f8d6da000)
libnvrm.so => /usr/lib/aarch64-linux-gnu/tegra/libnvrm.so (0x0000007f8d697000)
libEGL.so.1 => /usr/lib/aarch64-linux-gnu/libEGL.so.1 (0x0000007f8d676000)
libnvos.so => /usr/lib/aarch64-linux-gnu/tegra/libnvos.so (0x0000007f8d658000)
libnvbuf_fdmap.so.1.0.0 => /usr/lib/aarch64-linux-gnu/tegra/libnvbuf_fdmap.so.1.0.0 (0x0000007f8d645000)
libnvrm_graphics.so => /usr/lib/aarch64-linux-gnu/tegra/libnvrm_graphics.so (0x0000007f8d625000)
libnvddk_vic.so => /usr/lib/aarch64-linux-gnu/tegra/libnvddk_vic.so (0x0000007f8d605000)
libnvddk_2d_v2.so => /usr/lib/aarch64-linux-gnu/tegra/libnvddk_2d_v2.so (0x0000007f8d5e0000)
libgcc_s.so.1 => /lib/aarch64-linux-gnu/libgcc_s.so.1 (0x0000007f8d5bc000)
libnvinfer.so.8 => not found
libnvrm_gpu.so => /usr/lib/aarch64-linux-gnu/tegra/libnvrm_gpu.so (0x0000007f8d578000)
libnvidia-fatbinaryloader.so.440.18 => /usr/lib/aarch64-linux-gnu/libnvidia-fatbinaryloader.so.440.18 (0x0000007f8d507000)
libexpat.so.1 => /lib/aarch64-linux-gnu/libexpat.so.1 (0x0000007f8d4c8000)
libXau.so.6 => /usr/lib/aarch64-linux-gnu/libXau.so.6 (0x0000007f8d4b5000)
libXdmcp.so.6 => /usr/lib/aarch64-linux-gnu/libXdmcp.so.6 (0x0000007f8d4a0000)
libdatrie.so.1 => /usr/lib/aarch64-linux-gnu/libdatrie.so.1 (0x0000007f8d48a000)
libharfbuzz.so.0 => /usr/lib/aarch64-linux-gnu/libharfbuzz.so.0 (0x0000007f8d3ea000)
libGLdispatch.so.0 => /usr/lib/aarch64-linux-gnu/libGLdispatch.so.0 (0x0000007f8d2bc000)
libbsd.so.0 => /lib/aarch64-linux-gnu/libbsd.so.0 (0x0000007f8d29a000)
libgraphite2.so.3 => /usr/lib/aarch64-linux-gnu/libgraphite2.so.3 (0x0000007f8d269000)
Yes, CUDA is installed (I ran this outside docker container)
aaeon@aaeon-desktop:/usr/local/cuda/samples/1_Utilities/deviceQuery$ deviceQuery
deviceQuery Starting...
CUDA Device Query (Runtime API) version (CUDART static linking)
Detected 1 CUDA Capable device(s)
Device 0: "Xavier"
CUDA Driver Version / Runtime Version 10.2 / 10.2
CUDA Capability Major/Minor version number: 7.2
Total amount of global memory: 7772 MBytes (8149737472 bytes)
( 6) Multiprocessors, ( 64) CUDA Cores/MP: 384 CUDA Cores
GPU Max Clock rate: 1109 MHz (1.11 GHz)
Memory Clock rate: 1109 Mhz
Memory Bus Width: 256-bit
L2 Cache Size: 524288 bytes
Maximum Texture Dimension Size (x,y,z) 1D=(131072), 2D=(131072, 65536), 3D=(16384, 16384, 16384)
Maximum Layered 1D Texture Size, (num) layers 1D=(32768), 2048 layers
Maximum Layered 2D Texture Size, (num) layers 2D=(32768, 32768), 2048 layers
Total amount of constant memory: 65536 bytes
Total amount of shared memory per block: 49152 bytes
Total number of registers available per block: 65536
Warp size: 32
Maximum number of threads per multiprocessor: 2048
Maximum number of threads per block: 1024
Max dimension size of a thread block (x,y,z): (1024, 1024, 64)
Max dimension size of a grid size (x,y,z): (2147483647, 65535, 65535)
Maximum memory pitch: 2147483647 bytes
Texture alignment: 512 bytes
Concurrent copy and kernel execution: Yes with 1 copy engine(s)
Run time limit on kernels: No
Integrated GPU sharing Host Memory: Yes
Support host page-locked memory mapping: Yes
Alignment requirement for Surfaces: Yes
Device has ECC support: Disabled
Device supports Unified Addressing (UVA): Yes
Device supports Compute Preemption: Yes
Supports Cooperative Kernel Launch: Yes
Supports MultiDevice Co-op Kernel Launch: Yes
Device PCI Domain ID / Bus ID / location ID: 0 / 0 / 0
Compute Mode:
< Default (multiple host threads can use ::cudaSetDevice() with device simultaneously) >
deviceQuery, CUDA Driver = CUDART, CUDA Driver Version = 10.2, CUDA Runtime Version = 10.2, NumDevs = 1
Result = PASS
Is the TensorRT installed correctly in the host? Please run “dpkg -l | grep TensorRT” in the host.
aaeon@aaeon-desktop:~$ /usr/src/tensorrt/bin/trtexec
&&&& RUNNING TensorRT.trtexec # /usr/src/tensorrt/bin/trtexec
=== Model Options ===
--uff=<file> UFF model
--onnx=<file> ONNX model
--model=<file> Caffe model (default = no model, random weights used)
--deploy=<file> Caffe prototxt file
--output=<name>[,<name>]* Output names (it can be specified multiple times); at least one output is required for UFF and Caffe
--uffInput=<name>,X,Y,Z Input blob name and its dimensions (X,Y,Z=C,H,W), it can be specified multiple times; at least one is required for UFF models
--uffNHWC Set if inputs are in the NHWC layout instead of NCHW (use X,Y,Z=H,W,C order in --uffInput)
=== Build Options ===
--maxBatch Set max batch size and build an implicit batch engine (default = 1)
--explicitBatch Use explicit batch sizes when building the engine (default = implicit)
--minShapes=spec Build with dynamic shapes using a profile with the min shapes provided
--optShapes=spec Build with dynamic shapes using a profile with the opt shapes provided
--maxShapes=spec Build with dynamic shapes using a profile with the max shapes provided
--minShapesCalib=spec Calibrate with dynamic shapes using a profile with the min shapes provided
--optShapesCalib=spec Calibrate with dynamic shapes using a profile with the opt shapes provided
--maxShapesCalib=spec Calibrate with dynamic shapes using a profile with the max shapes provided
Note: All three of min, opt and max shapes must be supplied.
However, if only opt shapes is supplied then it will be expanded so
that min shapes and max shapes are set to the same values as opt shapes.
In addition, use of dynamic shapes implies explicit batch.
Input names can be wrapped with escaped single quotes (ex: \'Input:0\').
Example input shapes spec: input0:1x3x256x256,input1:1x3x128x128
Each input shape is supplied as a key-value pair where key is the input name and
value is the dimensions (including the batch dimension) to be used for that input.
Each key-value pair has the key and value separated using a colon (:).
Multiple input shapes can be provided via comma-separated key-value pairs.
--inputIOFormats=spec Type and formats of the input tensors (default = all inputs in fp32:chw)
Note: If this option is specified, please make sure that all inputs are in the same order
as network inputs ID.
--outputIOFormats=spec Type and formats of the output tensors (default = all outputs in fp32:chw)
Note: If this option is specified, please make sure that all outputs are in the same order
as network outputs ID.
IO Formats: spec ::= IOfmt[","spec]
IOfmt ::= type:fmt
type ::= "fp32"|"fp16"|"int32"|"int8"
fmt ::= ("chw"|"chw2"|"chw4"|"hwc8"|"chw16"|"chw32")["+"fmt]
--workspace=N Set workspace size in megabytes (default = 16)
--noBuilderCache Disable timing cache in builder (default is to enable timing cache)
--nvtxMode=[default|verbose|none] Specify NVTX annotation verbosity
--minTiming=M Set the minimum number of iterations used in kernel selection (default = 1)
--avgTiming=M Set the number of times averaged in each iteration for kernel selection (default = 8)
--noTF32 Disable tf32 precision (default is to enable tf32, in addition to fp32)
--fp16 Enable fp16 precision, in addition to fp32 (default = disabled)
--int8 Enable int8 precision, in addition to fp32 (default = disabled)
--best Enable all precisions to achieve the best performance (default = disabled)
--calib=<file> Read INT8 calibration cache file
--safe Only test the functionality available in safety restricted flows
--saveEngine=<file> Save the serialized engine
--loadEngine=<file> Load a serialized engine
=== Inference Options ===
--batch=N Set batch size for implicit batch engines (default = 1)
--shapes=spec Set input shapes for dynamic shapes inference inputs.
Note: Use of dynamic shapes implies explicit batch.
Input names can be wrapped with escaped single quotes (ex: \'Input:0\').
Example input shapes spec: input0:1x3x256x256, input1:1x3x128x128
Each input shape is supplied as a key-value pair where key is the input name and
value is the dimensions (including the batch dimension) to be used for that input.
Each key-value pair has the key and value separated using a colon (:).
Multiple input shapes can be provided via comma-separated key-value pairs.
--loadInputs=spec Load input values from files (default = generate random inputs). Input names can be wrapped with single quotes (ex: 'Input:0')
Input values spec ::= Ival[","spec]
Ival ::= name":"file
--iterations=N Run at least N inference iterations (default = 10)
--warmUp=N Run for N milliseconds to warmup before measuring performance (default = 200)
--duration=N Run performance measurements for at least N seconds wallclock time (default = 3)
--sleepTime=N Delay inference start with a gap of N milliseconds between launch and compute (default = 0)
--streams=N Instantiate N engines to use concurrently (default = 1)
--exposeDMA Serialize DMA transfers to and from device. (default = disabled)
--useSpinWait Actively synchronize on GPU events. This option may decrease synchronization time but increase CPU usage and power (default = disabled)
--threads Enable multithreading to drive engines with independent threads (default = disabled)
--useCudaGraph Use cuda graph to capture engine execution and then launch inference (default = disabled)
--buildOnly Skip inference perf measurement (default = disabled)
=== Build and Inference Batch Options ===
When using implicit batch, the max batch size of the engine, if not given,
is set to the inference batch size;
when using explicit batch, if shapes are specified only for inference, they
will be used also as min/opt/max in the build profile; if shapes are
specified only for the build, the opt shapes will be used also for inference;
if both are specified, they must be compatible; and if explicit batch is
enabled but neither is specified, the model must provide complete static
dimensions, including batch size, for all inputs
=== Reporting Options ===
--verbose Use verbose logging (default = false)
--avgRuns=N Report performance measurements averaged over N consecutive iterations (default = 10)
--percentile=P Report performance for the P percentage (0<=P<=100, 0 representing max perf, and 100 representing min perf; (default = 99%)
--dumpOutput Print the output tensor(s) of the last inference iteration (default = disabled)
--dumpProfile Print profile information per layer (default = disabled)
--exportTimes=<file> Write the timing results in a json file (default = disabled)
--exportOutput=<file> Write the output tensors to a json file (default = disabled)
--exportProfile=<file> Write the profile information per layer in a json file (default = disabled)
=== System Options ===
--device=N Select cuda device N (default = 0)
--useDLACore=N Select DLA core N for layers that support DLA (default = none)
--allowGPUFallback When DLA is enabled, allow GPU fallback for unsupported layers (default = disabled)
--plugins Plugin library (.so) to load (can be specified multiple times)
=== Help ===
--help, -h Print this message
&&&& PASSED TensorRT.trtexec # /usr/src/tensorrt/bin/trtexec
Does it really matter? If we run in docker container, having TensorRT on host is not mandatory?
aaeon@aaeon-desktop:~/jetsonUtilities$ python jetsonInfo.py
NVIDIA NVIDIA Jetson Xavier NX Developer Kit
L4T 32.6.1 [ JetPack 4.6 ]
Ubuntu 18.04.5 LTS
Kernel Version: 4.9.253-tegra
CUDA 10.2.89
CUDA Architecture: 7.2
OpenCV version: 4.1.1
OpenCV Cuda: NO
CUDNN: 8.0.0.180
TensorRT: 7.1.3.0
Vision Works: 1.6.0.501
VPI: 1.0.12
Vulcan: 1.2.70
On host, I have TensorRT version 7. It has to be 8?
It is mandatory. Or else you need to install TensorRT inside docker container.
Which docker are you using? Do you install JetPack with SDKManager?
I’m using nvcr.io/nvidia/deepstream-l4t:6.0-samples
I will install TensorRT outside of docker then.
I install via apt, following Quickstart Guide — DeepStream 6.0 Release documentation
If you installed the JetPack4.6 GA correctly, TensorRT version should be 8.0.1.
ok. I will update TensorRT to 8.0.1 and let you know. Thanks
Quickstart Guide — DeepStream 6.0 Release documentation (nvidia.com) just said you need to install JetPack 4.6 GA with SDKManager. It is better to install with SDKManager from the beginning but not just to upgrade the TensorRT.