-
-
Notifications
You must be signed in to change notification settings - Fork 345
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Do I need to add parse function when I deal with other yolov5 models? #13
Comments
Hi, I didn't understand what you need. Do you want know how to run model or how to get processed metada? |
Hi, Thank you for your prompt replay. In your /examples/yolov5s/nvdsinfer_custom_impl_Yolo/nvdsparsebbox_Yolo.cpp file, there is a function named:NvDsInferParseCustomYoloV5(), I think it can parse yolov5s meta data. If I want to parse v5m or v5x, can I just use this function or I need create a new one specific for v5m/v5x? |
Do you need only TensorRT converted model to use with other yolov5 model, the nvdsparsebbox_Yolo.cpp file is the same of yolov5s. Metadata is processed stream/video data. It's location of bbox, label of detected object, etc. To get this data, you need knowledge to edit deepstream code (Python or C). |
Got it, thank you for your confirmation. |
Hi,
From your yolov5 FAQ, I'm aware something need to be changed with the config files. My question is, do I need to add functions to parse the model's data in nvdsparsebbox_Yolo.cpp? And how to do so?
Thanks,
The text was updated successfully, but these errors were encountered: