hi bro, I trained the yolov3 network with my custom data and converted it to a .engine file to successfully detect the target in the image, but put the .engine file into opt/nvidia/deepstream/deepstream/sources/objectDetector_Yolo to compile nvdsinfer_custom_impl_Yolo, and I can successfully run deepstream-app, but the result of the detection frame is not displayed, only the rstp video is displayed
Can you get the infer output using the same image you used which successfully detect the target outside deepstream?
I just use the same image for detection, .engine detects the target, but deepstream does not, deepstream only displays pictures
It shoud be related with post processing.
check nvdsinfer_custom_impl_Yolo/nvdsparsebbox_Yolo.cpp
you may need to change the post processing according to your trained model.
I’m closing this topic due to there is no update from you for a period, assuming this issue was resolved.
If still need the support, please open a new topic. Thanks
This topic was automatically closed 14 days after the last reply. New replies are no longer allowed.