Stack Overflow
Stack Overflow

Questions tagged [nvidia-deepstream]

54 questions
10
votes
3 answers

Installing TensorRT- facing issue with libnvinfer7 library (Cuda 10.2) on ubuntu 18.04

I was trying to install tensorRT 7.0 in ubuntu 18.4 (nv-tensorrt-repo-ubuntu1804-cuda10.2-trt7.0.0.11-ga-20191216_1-1_amd64.deb) debian. Followed the documentation…
Amarnath R
  • 973
  • 3
  • 14
  • 33
5
votes
1 answer

Reconnect RTSP stream in Gstreamer pipeline

I have a working Gstreamer pipeline using RTSP input streams. To handle these given RTSP input streams, the uridecobin element is used. My goal is to reconnect to the RTSP input streams when internet connection is unstable. When the internet…
harry_tums
  • 91
  • 7
3
votes
1 answer

GStreamer / Deepstream: No such file or directory when loading plugins

Gstreamer is giving me errors reporting that it cannot load plugins because their files do not exists. However, these files do exists. Output: Frames will be saved in frames (gst-plugin-scanner:22): GStreamer-WARNING **: 20:59:31.873: Failed to…
user1315621
  • 3,044
  • 9
  • 42
  • 86
3
votes
0 answers

Gstreamer tee branch with appsink slows down the whole pipeline, how to process buffer async?

I have a deepstream pipeline which goes like this: reading and processing video --> queue --> tee --> queue --> display |----> queue --> appsink The appsink has a callback function attached to the…
Ahmed
  • 65
  • 1
  • 4
3
votes
1 answer

Push OpenCV mat inside a DeepStream pipeline

I would like to open a video stream by OpenCv and push frame by frame inside a DeepStream pipeline to use tesornRT to make an inference on Yolov3 model, but i do not know how to make it works. I'm trying to follow the directives that I found here,…
Neorem
  • 71
  • 4
3
votes
0 answers

Unable to consume HLS stream from AWS Kinesis feed in GStreamer

I’m trying to consume HLS feed generated by AWS Kinesis as input to DeepStream pipeline but I’m getting following error: Error: gst-stream-error-quark: GStreamer encountered a general stream error.(1): qtdemux.c(7067):gst_qtdemux_process_adapter ():…
Tanmay Vakare
  • 51
  • 5
2
votes
1 answer

Save frames extracted from Deepstream pipeline to video using OpenCV

I’m trying to save extracted frames from a Deepstream pipeline to video with OpenCV but all I end up with is a 9KB file. This is my code (executed inside a probe function): batch_meta = pyds.gst_buffer_get_nvds_batch_meta(hash(gst_buffer)) l_frame =…
Giorgos Betsos
  • 71,379
  • 9
  • 63
  • 98
2
votes
0 answers

nvidia dali video decode from external_source buffer (instead of file)

This article explains how to do image decoding and preprocessing on server side with Dali while using triton-inference-server. I am trying to find something similar for doing video decoding from h.264 encoded bytes array on server side, before the…
dumbPy
  • 1,379
  • 1
  • 6
  • 19
2
votes
1 answer

DeepStream inference on Windows

If i train a model with the NVidia DeepStream SDK on linux can i use it for inference on Windows? I know that the SDK is not available for windows but is it necessary for inference? I prefer a solution without docker, but also interested in dockered…
Nemes Gyula Ádám
  • 189
  • 5
2
votes
2 answers

Can I run NVIDIA DeepStream SDK in Windows Server 2019?

System: I've a Windows Server 2019 OS installed with a NVIDIA Tesla T4 Tensor Core GPU. Goal: Planning to read real time streaming videos from an IP camera and to further process frame by frame. Goal is to leverage NVIDIA DeepStream SDK, but issue…
Aakash Basu
  • 1,689
  • 7
  • 28
  • 57
1
vote
0 answers

How to custom deepstream python sample with face_recognition library

Hardware: Jetson Nano - Jetpack 4.4 - Python 3.6 - Deepstream 6.0 I'm currently working with deepstream-imagedate-multistream.py 1 example from NVIDIA-AI-IOT repo and I want to use face_recognition library 2 (of adam geitgey) in this sample to…
Lăng Khoa
  • 11
  • 1
1
vote
1 answer

RAM use with Gstreamer filesink increases indefinitely

I've been getting OOM errors after running my Gstreamer pipeline for long periods of time. Running on a Jetson-Xavier Devkit. The smallest reproducible example: gst-launch-1.0 videotestsrc ! omxh265enc ! qtmux ! filesink location=test.mp4 -e Memory…
eden_debuggin
  • 11
  • 2
1
vote
1 answer

Is DeepStream SDK support Jetson Nano?

My goal is to run DeepStream SDK 6.2 (or older version). The official SD Card Image is JP461 (I assume it's JetPack 4.6.1). However, DeepStream SDK 6.2 require JetPack 5.1. The problem is JetPack 5.1 does not mention Nano at all and I can't find…
Jason Rich Darmawan
  • 1,607
  • 3
  • 14
  • 31
1
vote
1 answer

Jetson Orin Deepstream vs conventional python program

Does anyone have a independent evaluation of using Deepstream Gstream pipline instead of a conventional python code? Gstreamer: USB-CAM -> Appsink -> (CPU to GPU) AI analysis (TensorRT) -> CV2.ImShow I think I understand that deepstream uses the GPU…
Magnus_G
  • 49
  • 8
1
vote
0 answers

Issues with Azure IOT Edge & Jetson Nano - DeepStream Module

I'm trying to install the Nvidia DeepStream SDK module on my Jetson Nano running JetPack 4.6.1 with Azure IOT Edge. Following this example, but it is based on DeepStream 5.1, and since I have JetPack 4.6.1 I have DeepStream SDK…
Jonas Nilsson
  • 67
  • 5
1
2 3 4