No detection for trained Yolo model on Deepstream 7.0.0

[saiesh.agre777]

I have a Jetson Orin NX running Deepstream 7.0.0. I have a yolo model trained on Visdrone dataset. I converted to to ONNX using YOLO CLI command, and Deepstream coverts to to Engine file successfully but I can’t see any detections over the feed.

The engine files created using YOLO CLI, TRTEXEC and DeepStream all work when ran on a sample video using the following command:

yolo predict model=‘model.engine’ source=‘video.mp4’ show=True.

My model input/output dimensions are for the models not working are:
Input : 1x3x640x640
Output : 1x14x8400

I have attached my infer config file and deepstream app config file below:
config_infer_primary_yoloV8.txt (871 Bytes)
deepstream_app_config.txt (881 Bytes)

Any help would be appreciated.

[fanzh]

Please provide complete information as applicable to your setup.

• Hardware Platform (Jetson / GPU)

• DeepStream Version

• JetPack Version (valid for Jetson only)

• TensorRT Version

• NVIDIA GPU Driver Version (valid for GPU only)

• Issue Type( questions, new requirements, bugs)

• How to reproduce the issue ? (This is for bugs. Including which sample app is using, the configuration files content, the command line used and other details for reproducing)

• Requirement details( This is for new requirement. Including the module name-for which plugin or for which sample application, the function description)

[fanzh]

1. please understand the meaning of output layers first, then check if parse-bbox-func-name=NvDsInferParseYolo is appliable for your model.
2. please refer to the faq 15.[DSx_All_App] Debug Tips for DeepStream Accuracy Issue for the accuracy issue.
3. please refer to NV yolov8 sample.

[yingliu]

There is no update from you for a period, assuming this is not an issue anymore. Hence we are closing this topic. If need further support, please open a new one. Thanks.