Stack Overflow
Stack Overflow

Questions tagged [nvidia-deepstream]

54 questions
0
votes
1 answer

Segmentation Fault: Running nvidia deepstream 5.0 SDK on Ubuntu

Trying to run nvidia’s deepstream5.0 sdk (sample program) on ubuntu 18.04 by following the document (DeepStream Development Guide — DeepStream DeepStream Version: 5.0 documentation). Hardware Platform (Jetson / GPU)=GPU NVIDIA GEFORCE RTX…
SALINI
  • 1
  • 1
0
votes
0 answers

How to enable NVIDIADeepstreamSDK Azure IoTEdge module to recieve messages from local rtsp?

I installed Azure IoTEdge on my Jetson nano and provisioned the IoTEdge runtime to the device using the security daemon file at /etc/iotedge/config.yaml . I see that the status of the IoT Edge Daemon is active (running) and all the 6 IoTEdge runtime…
rensc
  • 1
  • 2
0
votes
1 answer

Unable to link Nvstreamdemux to rtph264pay element using PyGObject

Please provide complete information as applicable to your setup. • Hardware Platform (Jetson / GPU) Jetson • DeepStream Version 5.0 • JetPack Version (valid for Jetson only) 4.4 • TensorRT Version 7.0 • NVIDIA GPU Driver Version (valid for GPU…
tathagat dasgupta
  • 11
  • 1
  • 4
0
votes
0 answers

Frame-rate drop while using custom python app in Deepstream SDK

Using the deepstream_app_config_yoloV3.txt and TRT engine file fp16.engine, I got a FPS of 15 on yolov3-spp and a FPS of 30 on yolov3-tiny . My question is this: Is there a way to recreate the fps I got running the deepstream_app_config_yoloV3.txt…
Bezal-el
  • 33
  • 1
  • 2
  • 8
0
votes
1 answer

DeepStream python apps in custom application

In this link, we can access to gstreamer pipeline buffer and convert the frame buffers in numpy array, I want to know, How I can to accesses the frame buffers in GPU mem and then feed into my custom processor without convert frames into numpy…
DeeeepNet
  • 347
  • 3
  • 11
0
votes
1 answer

Unable to get result of secondary1-nvinference-engine and secondary2-nvinference-engine on each frame

Working on nvidia deep stream - inference engine, unable to get the classifier class. Always it shows index 0. Any help is appreciated. l_classifier = obj_meta.classifier_meta_list print('First Classifier at: ', l_classifier) classifier_cnt =…
Amarnath R
  • 973
  • 3
  • 14
  • 33
0
votes
1 answer

How to stream the video job running on one of the worker nodes of kubernetes cluster?

I was running a Nvidia deepstream container on one of the GPU worker nodes in kubernetes cluster which is deployed as a job and below is my YAML file, apiVersion: batch/v1 kind: Job metadata: name: deepstream-test spec: backoffLimit: 1 …
Leela Krishna Uppuluri
  • 1
  • 1
-1
votes
1 answer

How can I convert NHWC to NCHW in python for deepstream

I have a TensorFlow Keras model which is stored in .pb format and from .pb format I am converting the model to .onnx format using the tf2onnx model !python -m tf2onnx.convert --saved-model model.pb --output model.onnx now after converting I see…
Sovik Gupta
  • 147
  • 2
  • 13
-1
votes
1 answer

Extract frames simultaneously from two video using ffmpeg

I would like to know the CLI command and the script to extract images using FFmpeg of two videos simultaneously and not sequentially. For example - the first frame of the first video the first frame of the second video and the second frame of first…
devl
  • 19
  • 6
1 2 3
4