Find the Best Demos and Examples

Check out this quick tour to find the best demos and examples for you, and to see how the Felgo SDK can help you to develop your next app or game!


OverviewFelgo 2 Support (Qt 5) › Android Performance Issues with the latest Felgo / Qt version?

Viewing 3 posts - 1 through 3 (of 3 total)
  • Author
  • #19533



    I am working on a multiplatform app for object detection applying machine learning, I am using the TensorFlow framework. I notice that in the latest Felgo version the performance of the Android app has considerably decreased. The inference time, the time for processing an image, has increased a lot on Android with the same device, Android version, neural network, TensorFlow version, and app code. I am only measuring the inference time, not the time spend in converting or drawing on the image. These are some estimated inference times on several platforms.

    Linux: 100 msec – 200 msec (Laptop).
    iOS: 100 msec – 200 msec (iPhone 7).
    Android: 350 msec – 600 msec (Samsung Galaxy S8).
    It used to be 100 msec – 200 msec in the previous Felgo version. Unfortunately, I do not have a screenshot of this.


    Maybe this related to changes in Felgo or in the Qt version regarding Android?



    Felgo Team

    Hi Javier,

    the latest Felgo update did not change the underlying Qt Version for Felgo. Also, with a quick first look, I do not see any update features and improvements that could be responsible to affect the performance on Android.

    Are you sure that the Felgo update is the only factor that could have affected the performance of your app?




    Thanks Günther,

    I will check it again and let you know if I find something.

Viewing 3 posts - 1 through 3 (of 3 total)

RSS feed for this thread

You must be logged in to reply to this topic.