Inference fails to give detection when i change the different Deepstream 6.0 apps

Accelerated Computing Intelligent Video Analytics TAO Toolkit
#1

cuda-11.3 + cuDNN-8.2
Quadro RTX 5000 dual GPU
Driver Version: 470.82.00
CUDA Version: 11.4
Ubuntu 18.04
python 3.6
Yolo_v4

Deepstream 6

I trained TAO 3.0 custom yoloV4 model
I successfully inference using : deepstream_tao_apps on both jetson Xavior and tesla dGPU
/deepstream_tao_apps/configs/yolov4_tao

But when i run it on :
/deepstream_python_apps/apps/deepstream-test1
or normal deepstream
/opt/nvidia/deepstream/deepstream-6.0/samples/configs/deepstream-app/
source30_1080p_dec_infer-resnet_tiled_display_int8.txt

it gives no detection both using engine file or if i build it using cal.bin/etlt…

#3

For DS issue, please create topic in DS forum .Thanks.

#4

ok, Thank you

#6

This topic was automatically closed 14 days after the last reply. New replies are no longer allowed.