-1

I was checking the feasibility of number of computer vision model that can run on the android devices simultaneously but could not find any resource for it.

I have two computer vision models, one is doing classification of images about 20 classes and another one I want to integrate is the image depth map model. Both of them will work on real time. Thus I want to know will they able to run on Android devices with limited ram of 1 Giga Byte.

Badar
  • 33
  • 6
  • well, consider the amount of ram required to hold one model's parameters. now consider if both would even fit in RAM. -- next you should consider the amount of computation and whether you'll be satisfied by the execution speed if both have to run at the same time. -- try asking in https://stats.stackexchange.com/ – Christoph Rackwitz Jun 23 '22 at 08:25
  • Yolo with 224x224 cross image with RGB colour is in first model. And I believe simple input parameters will be for other model – Badar Jun 24 '22 at 01:04
  • What do you mean by real-time @TowardIslam? 1FPS, 10FPS, ...? – Mike B Jul 08 '22 at 19:52
  • Consider 10 Fps – Badar Jul 11 '22 at 18:50

1 Answers1

0

My own experience is that this is highly dependent on hardware as well as the neural network architectures themselves and optimization methods performed on them. So there is not exact answer to your question.

However, I can tell you that 10 FPS will be very hard to achieve, specially with 1GB of RAM on an old device I assume. I have a TFLite Yolov5s model, quantized to INT8 which I pass 320x320 images to, running on an old Samsung tablet from 2015 (3GB of RAM), achieving an average inference time of 0.47 seconds. This is only one model.

Mike B
  • 2,136
  • 2
  • 12
  • 31