How to make the model inference faster?

[bytemani]

Hi, i'm using the converted tflite model with android system , but it takes about 3.x seconds to obtain the depth png. Is there any way to accelerate it? thx

[jojo13572001]

Sorry for the late reply. I've seen your support for mobile gpu. is this problem being solved now?

[rodrigoGA]

I congratulate you on the work, but it would be very interesting in the tflite model, to obtain a significant improvement in the inference time, even sacrificing accuracy, or even reducing the input size. To make the model executable in real time