docker pull nvcr.io/nvidia/deepstream:3.0-18.11
3.0-18.11: Pulling from nvidia/deepstream
Digest: sha256:3c4aaa5fc3821fc4c45a30735f988b8d6f1ac2dcae9320fb26ea3946abfd8329
Status: Image is up to date for nvcr.io/nvidia/deepstream:3.0-18.11
nvidia@nvidia-WS-Z390-PRO:~$ xhost +
access control disabled, clients can connect from any host
nvidia-docker run -it --rm -v /tmp/.X11-unix:/tmp/.X11-unix -e DISPLAY=$DISPLAY -w /root nvcr.io/nvidia/deepstream:3.0-18.11
root@f3297f496cdb:~# cat /root/DeepStream_Release/README
*****************************************************************************
* Copyright (c) 2018 NVIDIA Corporation. All rights reserved.
*
* NVIDIA Corporation and its licensors retain all intellectual property
* and proprietary rights in and to this software, related documentation
* and any modifications thereto. Any use, reproduction, disclosure or
* distribution of this software and related documentation without an express
* license agreement from NVIDIA Corporation is strictly prohibited.
*****************************************************************************
================================================================================
DeepStream SDK
================================================================================
Setup pre-requisites:
- Ubuntu 16.04
- Gstreamer 1.8.3
- NVIDIA driver 410+
- CUDA 10.0
- TensorRT 5.0
--------------------------------------------------------------------------------
Package Contents
--------------------------------------------------------------------------------
The DeepStream packages include:
1. binaries.tbz2 - Core binaries
2. sources - Sources for sample application and plugin
3. samples - Config files, Models, streams and tools to run the sample app
Note for running with docker
-----------------------------
While running DeepStream with docker, necessary packages are already pre-installed.
Hence please skip the installation steps and proceed to "Running the samples" section of this document.
--------------------------------------------------------------------------------
Installing Pre-requisites:
--------------------------------------------------------------------------------
Packages to be installed:
$ sudo apt-get install \
libssl1.0.0 \
libgstreamer1.0-0 \
gstreamer1.0-tools \
gstreamer1.0-plugins-good \
gstreamer1.0-plugins-bad \
gstreamer1.0-plugins-ugly \
gstreamer1.0-libav \
libgstrtspserver-1.0-0 \
libjansson4
CUDA 10.0
--------
Download and install Cuda-10.0 from nvidia website
https://developer.nvidia.com/cuda-toolkit-archive
TensorRT 5.0
-------------
Download and install TensorRT 5.0 from nvidia website
https://developer.nvidia.com/nvidia-tensorrt-download
Create symlink for libnvcuvid.so:
---------------------------------
sudo ln -s /usr/lib/nvidia-<driver-version>/libnvcuvid.so \
/usr/lib/x86_64-linux-gnu/libnvcuvid.so
-------------------------------------------------------------------------------
librdkafka: to enable kafka protocol adaptor for message broker
-------------------------------------------------------------------------------
git clone https://github.com/edenhill/librdkafka.git
cd librdkafka
git reset --hard 7101c2310341ab3f4675fc565f64f0967e135a6a
./configure
make
sudo make install
sudo mkdir -p /usr/local/deepstream
sudo cp /usr/local/lib/librdkafka* /usr/local/deepstream
--------------------------------------------------------------------------------
Extract and Install DeepStream SDK
--------------------------------------------------------------------------------
1. This package will have binaries.tbz2 and samples directory.
2. Untar binaries.tbz2
sudo tar -xvf binaries.tbz2 -C /
--------------------------------------------------------------------------------
Running the samples
--------------------------------------------------------------------------------
1. Go to samples directory and run
deepstream-app -c <path to config.txt>
2. Application config files included in `configs/deepstream-app/`
a. source30_720p_dec_infer-resnet_tiled_display_int8.txt (30 Decode + Infer)
b. source4_720p_dec_infer-resnet_tracker_sgie_tiled_display_int8.txt
(4 Decode + Infer + SGIE + Tracker)
c. source4_720p_dec_infer-resnet_tracker_sgie_tiled_display_int8_gpu1.txt
(4 Decode + Infer + SGIE + Tracker executed on gpu1)
3. Configuration files for "nvinfer" element in `configs/deepstream-app/`
a. config_infer_primary.txt (Primary Object Detector)
b. config_infer_secondary_carcolor.txt (Secondary Car Color Classifier)
c. config_infer_secondary_carmake.txt (Secondary Car Make Classifier)
d. config_infer_secondary_vehicletypes.txt (Secondary Vehicle Type Classifier)
--------------------------------------------------------------------------------
Notes:
--------------------------------------------------------------------------------
1. If the application runs into errors, cannot create gst elements, try again
after removing gstreamer cache
rm ${HOME}/.cache/gstreamer-1.0/registry.x86_64.bin
root@f3297f496cdb:~# rm ${HOME}/.cache/gstreamer-1.0/registry.x86_64.bin
rm: cannot remove '/root/.cache/gstreamer-1.0/registry.x86_64.bin': No such file or directory
root@f3297f496cdb:~# deepstream-app -c source4_720p_dec_infer-resnet_tracker_sgie_tiled_display_int8.txt
** ERROR: <parse_config_file:287>: parse_config_file failed
** ERROR: <main:535>: Failed to parse config file 'source4_720p_dec_infer-resnet_tracker_sgie_tiled_display_int8.txt'
Quitting
App run failed
root@f3297f496cdb:~#
root@f3297f496cdb:~/DeepStream_Release/samples# deepstream-app -c configs/deepstream-app/source4_720p_dec_infer-resnet_tracker_sgie_tiled_display_int8.txt
>>> Warning. Could not open model engine file /root/DeepStream_Release/samples/configs/deepstream-app/../../models/Secondary_CarMake/resnet18.caffemodel_b16_int8.engine
>>> Generating new TRT model engine
Using INT8 data type.
Warning: Flatten layer ignored. TensorRT implicitly flattens input to FullyConnected layers, but in other circumstances this will result in undefined behavior.
***** Storing serialized engine file as /root/DeepStream_Release/samples/configs/deepstream-app/../../models/Secondary_CarMake/resnet18.caffemodel_b16_int8.engine batchsize = 16 *****
>>> Warning. Could not open model engine file /root/DeepStream_Release/samples/configs/deepstream-app/../../models/Secondary_CarColor/resnet18.caffemodel_b16_int8.engine
>>> Generating new TRT model engine
Using INT8 data type.
Warning: Flatten layer ignored. TensorRT implicitly flattens input to FullyConnected layers, but in other circumstances this will result in undefined behavior.
***** Storing serialized engine file as /root/DeepStream_Release/samples/configs/deepstream-app/../../models/Secondary_CarColor/resnet18.caffemodel_b16_int8.engine batchsize = 16 *****
>>> Warning. Could not open model engine file /root/DeepStream_Release/samples/configs/deepstream-app/../../models/Secondary_VehicleTypes/resnet18.caffemodel_b16_int8.engine
>>> Generating new TRT model engine
Using INT8 data type.
Warning: Flatten layer ignored. TensorRT implicitly flattens input to FullyConnected layers, but in other circumstances this will result in undefined behavior.
***** Storing serialized engine file as /root/DeepStream_Release/samples/configs/deepstream-app/../../models/Secondary_VehicleTypes/resnet18.caffemodel_b16_int8.engine batchsize = 16 *****
>>> Warning. Could not open model engine file /root/DeepStream_Release/samples/configs/deepstream-app/../../models/Primary_Detector/resnet10.caffemodel_b4_int8.engine
>>> Generating new TRT model engine
Using INT8 data type.
***** Storing serialized engine file as /root/DeepStream_Release/samples/configs/deepstream-app/../../models/Primary_Detector/resnet10.caffemodel_b4_int8.engine batchsize = 4 *****
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) FPS 1 (Avg) FPS 2 (Avg) FPS 3 (Avg)
**PERF: 0.00 (0.00) 0.00 (0.00) 0.00 (0.00) 0.00 (0.00)
** INFO: <bus_callback:98>: Pipeline ready
** INFO: <bus_callback:84>: Pipeline running
**PERF: 33.61 (33.61) 33.61 (33.61) 33.61 (33.61) 33.61 (33.61)
**PERF: 30.01 (31.75) 30.01 (31.75) 30.01 (31.75) 30.01 (31.75)