DeepStream-Yolo

DeepStream-Yolo copied to clipboard

FPS on jetson xavier NX

1

Hi, I have run YoloV5s and everything has worked. However, the average FPS is just around 21 FPS with default setting (FP32) for camera webcam. Is that normal ? In...

anhtr-nguyn

when i Change the YoloLayer plugin version](https://github.com/marcoslucianops/DeepStream-Yolo/blob/master/docs/multipleGIEs.md#change-the-yololayer-plugin-version) in gie2 nvdsinfer_custom_impl_Yolo folder,then [Compile the libs](https://github.com/marcoslucianops/DeepStream-Yolo/blob/master/docs/multipleGIEs.md#compile-the-libs),used “CUDA_VER=11.4 make -C gie2/nvdsinfer_custom_impl_Yolo”， I encounter an error： g++ -c -o utils.o -Wall -std=c++11 -shared -fPIC...

LIANG180828

appreciate your great work! In our case, we use Deepstrean-Yolo to convert the model to deploy Yolov7 in Tensorrt. But I want to know if I have a live video...

PX-Xu

TypeError: attempt_load() got an unexpected keyword argument 'device'

5

When running export_yoloV5.py, It supported an error, " TypeError: attempt_load() got an unexpected keyword argument 'device' "

trameshape

how to use rtsp

4

May I ask the author, I have now completed running Deepstream on the host Jetson nano, and I want to use RTSP to push the stream to display it on...

ghty11468

Create release branches

18

I want to start by saying thank you for all your hard work with this code repo. Its clear it was no easy feat and its been a life saver...

HeeebsInc

config_tracker_NvDeepSORT.yml dose not work

2

Hi when i add this part `ll-lib-file=/opt/nvidia/deepstream/deepstream/lib/libnvds_nvmultiobjecttracker.so ll-config-file=config_tracker_NvDeepSORT.yml` to deepstream_app_config.txt i get this error  how to fixe it another tacker.yml are completely correct but deep sort...

khosrooo

Feature request: support for Gold-YOLO

2

It would be great to add support for the recent Gold-YOLO model: https://paperswithcode.com/paper/gold-yolo-efficient-object-detector-via

cgrtrifork

yolov8m-cls.pt

1

I would like to use yolov8m-cls.pt tuned on custom data for classifier after yolov7 detector how can I do that

jugal-sheth

How to reuse the generated engine file?

1

How do you reuse the generated engine file instead of creating the engine file every time you launch the demo?

snehakondur