[Javier]

Hi,

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). https://drive.google.com/open?id=1vZBKGR-LkH4KLivZWpYapGWH7ZHewvcP
iOS: 100 msec – 200 msec (iPhone 7). https://drive.google.com/open?id=1lNhHue4xzQ7dHs24K_fSt84Os4bmNgZg
Android: 350 msec – 600 msec (Samsung Galaxy S8). https://drive.google.com/open?id=19uY2nq4rhTUiy9s2_DMUq8zV-29rpdtt
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?

Thanks.

[GüntherFelgo 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?

Best,
Günther

[Javier]

Thanks Günther,

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