DS4.0.2 TX2 : precision detection decreased a lot after update yoloV3 network model

Hello,
I updated yolov3 model based on DS4.0.2 ,and modified yolo parse code, then tensorRT could parse the net successfully ,but the precision detection decreased a lot, I double check the yolo parse code and all the config file ,not found any problem.

I updated yolov3 model network according yoloV3-spp and Slim yoloV3 ,both decreased a lot of precision detection.

I have created this topic last year ,but didn’t solved until now, for detail please see

Environment

Jetpack 4.2.2
TX2
DS4.0.2
project based on objectDetector_Yolo

It’s very import for me ,I can’t sure where is the issue points.
Thanks for your support .

Moving to Jetson forum so that Jetson team can take a look.

thanks a lot

Hi @guibli,
Do you mean the accuracy drop is caused by deepstream?

BTW, we just released a project that demonstrate how to run TLT2.0 models on DeepStream - https://github.com/NVIDIA-AI-IOT/deepstream_tlt_apps, would you take a look if the YoloV3 in this project can help you?

OK,I will try ,thanks