Search Unity

Question model inferences much slower on Barracuda compare to onnxruntime

Discussion in 'Barracuda' started by nguyenhongson303, Oct 17, 2022.

  1. nguyenhongson303

    nguyenhongson303

    Joined:
    Sep 5, 2022
    Posts:
    1
    Hi,
    I have an onnx model which is converted form pytoch model.
    I want to run it on barracuda unity. The problem is when I run it with onnxruntime, I almost achieved 135 fps.
    However when I try it with barracuda, the performance just around 10fps.
    Is is because my model is too complicate? Sorry I am very new to Barracuda.
    upload_2022-10-17_12-30-0.png upload_2022-10-17_12-30-18.png

    These pictures are my model specifications. I just use a simple script to test my model on barracuda
    upload_2022-10-17_12-34-17.png

    Is there any reason that make my model perform so bad in barracuda?
    Thank you very much.
    This is the model that I am using: https://drive.google.com/file/d/1LqHnqQ0c14lAfga3Jf81te5buTYm4A-Q/view?usp=sharing
     
    nguyenhongson303, Oct 17, 2022
    #1

  2. Salah_laidoudi217

    Salah_laidoudi217

    Joined:
    Oct 18, 2023
    Posts:
    1
    Hello, did you manage to get any solutions?
     
    Salah_laidoudi217, Nov 20, 2023
    #2

  3. liutaurasvysniauskas_unity

    liutaurasvysniauskas_unity

    Unity Technologies

    Joined:
    Jun 14, 2022
    Posts:
    16
    Hi,
    Thank you for reporting this issue!
    Can you check if the inference is still slow with the Sentis 1.3.0-pre.2 package?
    The Sentis package is the new version of Barracuda, you can learn more about it here.
    If your problem still exists after upgrading, please report your issue in the Sentis Discussions forum.
    Thanks!
     
    liutaurasvysniauskas_unity, Nov 28, 2023
    #3