Please provide complete information as applicable to your setup. • Hardware Platform (Jetson / GPU) Jetson Xavier • DeepStream Version 6.0.1 • JetPack Version (valid for Jetson only) 4.6.2 • TensorRT Version 8.2.1 • Issue Type( questions, new requirements, bugs) Question I’m new to DS and…

[image] andhover: do not use nvstreammux and directly connect to nvinfer? please link nvstreammux and nvinfer, please refer to deepstream samples deepstream-test1

[image] andhover: batch-size=4 [image] andhover: s there posibility to use some kind of query what do you want to query? here is the batch-size setting method, Frequently Asked Questions — DeepStream 6.1.1 Release documentation

Ok, may be my explanation was not explicit. Here is the quote from your link: We recommend that the nvstreammux’s batch-size be set to either number of sources linked to it or the primary nvinfer’s batch-size. I have only one source and if I put in [property] batch-size=1 and set batch-size o…

@fanzh So the fps do not increase as expected. Can ds work with batches greater than 1 for one source to increase fps? For calculating fps I use standart class from examples ( deepstream_python_apps/FPS.py at v1.1.0 · NVIDIA-AI-IOT/deepstream_python_apps · GitHub )

@fanzh My source fps is 24, I’m developing with Python Bindings. So my question was if there is some solution to work with one source and batch size greater than 1, some kind of query after source to wait for number of frames equal to batch size and after that to output to streammux → nvinfer

The muxer uses a round-robin algorithm to collect frames from the sources, one batch will get only one frame from each source even the batch-size is greater than 1. which sample are you testing? did you use custom model? please use deepstream_test_1.py to check if fps is ok.

here are more details about nvstreammux Gst-nvstreammux — DeepStream 6.1.1 Release documentation .

Thanks? I’ve read this. Is it possible to take one source let’s say rtsp stream make from it several sources and input it to nvstreammux, to infer on one stream with batch greater than 1?

do you mean many of the same sources will feed into nvstreammux? in that case, the nvstreammux’s batch-size should be the number of sources linked to it.

I mean if there is any way to divide one source to several and after than to feed into nvstrreammux

How to accelerate single stream pipeline with batch size grater then 1

Accelerated Computing Intelligent Video Analytics DeepStream SDK

fanzh November 29, 2022, 7:33am 6

no, batch-size should be same with source number, what is your source 's fps? if you developed your own DS C++ code, you could also refer to DeepStream SDK FAQ - #12 by bcao 4 to measure the latency of the pipeline comonents. please refer to this topic The deepstream-test3 demo using rtsp webcam delayed

Topic		Replies	Views
Batch size is smaller than number of streams in DS pipeline DeepStream SDK	3	596	November 21, 2020
Nvinfer batch-size from video file input DeepStream SDK jetson-inference	13	1226	March 5, 2024
Nvstreamux process 1 frame in a batch at a time instead of 32 frames DeepStream SDK deepstream	12	345	November 15, 2024
Batch size adjustment DeepStream SDK	4	324	July 2, 2024
Disable frame batching from same stream - batch only from different streams in Deepstream DeepStream SDK	1	519	March 15, 2023
Create batch of frames for a single file stream DeepStream SDK tensorrt , gstreamer	5	1383	September 23, 2021
Temporal batching support in deepstream DeepStream SDK	1	474	September 16, 2021
DeepStream Inference Fails for ONNX Model with Batch Size different than 1 DeepStream SDK tensorrt , jetson-inference , onnx , deepstream	15	520	February 21, 2025
Error when setting streammux's batchsize >1 for custom model DeepStream SDK	4	890	February 19, 2022
Inference FLickers on Nvstreeammux Batch-size increase to number of streams DeepStream SDK deepstream	42	779	September 30, 2025

How to accelerate single stream pipeline with batch size grater then 1

Related topics