@JungOscar, Yes, @jakaskerl is correct; the exported model is working (though it recognizes other objects as fish, it's not crashing). I wanted to check that it is. What is your goal? Do you need to set up a tracking pipeline, or is detection enough for you?

For testing an YOLO object detection model I used this experiment (link).

Best,
Jan

    JungOscar
    The NN is quite complex and can only run at about 5FPS. The WARP_SWCH_ERR_CACHE_TO_SMALL is due to the big image size, there are 3 ImageManip nodes in the pipeline which all share resources. The bigger NN size maxes out these resources.

    Consider using a smaller input size for NN.

    Thanks,
    Jaka

        JanCuhel I don't understand your question, but just want to create applicaiton using cutom NN based on YOLO. I will follow your linked experimental guide next time.

          jakaskerl I understand your points. I might need guidance on reducing input size for the neural network. Any documentation or sharing of experience or knowledge on this would be helpfull.

          Thanks,

          Oscar

            jakaskerl Hi,

            I will change the resolution to a smaller width and height in tools.luxonis.com.

            Thanks,

            Oscar

                JungOscar

                Yes, using a smaller width and height will definitely help, but more importantly, using a small model is essential. For RVC2, I'd encourage you to use the smallest YOLO variants (e.g., nano in the case of YOLOv5, v6, v8, v10; and t for YOLOv7 and YOLOv9)

                Best,
                Jan

                  a month later

                  Hi,

                  What about supporting YOLOv9 custom weights, not just from official ultralytics weights?

                  I have tried converting my custom model and it does not work.

                  Thanks in advance.

                  Regards,

                  Javier.

                  Hi @takgoya,

                  unfortunately, we currently support only the YOLOv9 weights from Ultralytics.

                  Best,
                  Jan

                  takgoya

                  As far as I know, not in the foreseeing future, I am sorry about that. However, if anything would change, I'll let you know!

                  In the meantime, you could try to implement it yourself, good place to start would be to check this.

                  Kind regards,
                  Jan