Open SIGLOST opened 1 year ago
I'm not sure, but maybe the problem is in PyTorch >= 2. I will test today.
I can reproduce this issue in the DeepStream 6.1.1 using docker.
Try again with new updated files I just uploaded to the repo. Export the ONNX model with the new export file, generate the TensorRT engine again with the updated files, and use the new config_infer_primary file according to the model.
Try again with new updated files I just uploaded to the repo. Export the ONNX model with the new export file, generate the TensorRT engine again with the updated files, and use the new config_infer_primary file according to the model.
thanks, it's working now
@marcoslucianops I've tested successfully export to ONNX and deploying with DS 6.1.1 (dGPU) container the following variants: yolov5
/ yolov8
/ yolonas
Thanks a lot!
Hi Marcos,
Thank you for the great work!
I've been testing the last iteration and apparently there's a mismatch between the export scripts and the bounding box parser.
Followed the instructions and used the Ultralytics container with the latest available export script (defaulting to ONNX opset 17):
This is what I get when deploying the resulting model on a dGPU with DeepStream 6.1.1 container (NMS clustering is enabled):
Tried other YOLO variants like
yoloV8
andyolonas
, and in such cases we get the correct bounding boxes positions but always the same object classperson
(which is the 1st occurrence of the 80 classes present in the labels.txt of COCO dataset):