deepstream_triton_model_deploy icon indicating copy to clipboard operation
deepstream_triton_model_deploy copied to clipboard

Published 20 hours ago • verified publisher icon NVIDIA-AI-IOT

Using Centernet model with batching in Deepstream

Open akashmanna opened this issue 4 years ago • 3 comments

Hi, What changes should I make to use the centernet model with nvinferserver with batch size more than 1?

akashmanna avatar Feb 01 '21 13:02 akashmanna

Hi, If your model can support the batching then you can update the batch size in the configuration files. Update config.pbtxt and centerface.txt for the BS you want to use.

monjha avatar Feb 25 '21 07:02 monjha

Hi～ Have you successfully deployed CenterNet model in Deepstream? I meet a problem when I deploy trt model converted from CenterNet on Deepstream, because I do not know how Deepstream pre-process the input image and post-process the output of model. Looking forward to your kind reply~

PiPiNam avatar Jul 05 '21 07:07 PiPiNam

https://github.com/mAy-I/deepstream_centernet I made it here !

jaemin93 avatar Feb 03 '22 12:02 jaemin93