alexandrebenoit

  • Jul 19, 2024
  • Joined Apr 24, 2024
  • 0 best answers
  • In Support for V10
  • In Support for V10

    Hi,

    thanks !

    Well, regarding the provided online tools, is there any up to date standardized performance comparison table on a single or multiple Luxonis products ?

    I saw some tables in the doc but it would be great if the update datetime and maybe model version could be provided.

    Alex

    • In Support for V10

      Yes, indeed, this is then mostly related to data exchange bottlenecks and some complex functions such as Silu.

      Then, next steps could be Yolov10 engineering to adapt to hardware or on the research side to look for v11 ;o)

      In this community, who would be interested in a given direction for collab ?

      Alex

    • In Support for V10

      Well, it would be nice if you could share :

      • the list of problematic yolov10 element-wise operations that are not supported by RVC2
      • the list of all available ops that the RVC2 can perform (a synthetic datasheet)

      For example, if the Pixel-Adaptive Convolutions (PAC) operator is applicable for RVC2, then element-wise products could be replaced by PAC with some specific setup and so on (not as efficient as the base element-wise product on standard processors but this could compensate in some setups, maybe RVC2).

      Alex

      • In Support for V10

        Hi guys,

        well, the 25% speed performance loss on yolo v10 vs v8 on RVC2 is surprising.

        When saying "runs slower on device, due to the operations used, which can't be optimized for the MX."

        => could you explain and provide details on the operation that are problematic ? Maybe one can try to find alternatives.

        Thanks

      • In Processing camera raw/bayer data
      • In Processing camera raw/bayer data

        Hi Luxonis community,

        Being new to those nice products, i have a question regarding the processing of the raw image data: is it possible to grab the bayer sampled image and use it in the pipelines ?
        If yes, do you have any demo/documentation and some good recommendations on this point ? Raw bayer data is generally not filtered, high dynamic range or so but this depends on the camera specs and maybe some onboard preprocessing. If there are any details on those points that would be of interest.

        Currently i work with the Oak-1 W 97.

        Thanks

        Alex