1

I am currently using a 'DeepLab-V1' to do image segmentation in an iOS native app, i want to migrate to 'DeepLab-V3' but can seem to find a way to do so.

Any example of 'DeepLab-V3' implemented in a Xcode project would be appreciated or instructions.

Kenpachi
  • 11
  • 1
  • What is the actual problem that you're running into? – Matthijs Hollemans Jul 07 '19 at 16:55
  • @MatthijsHollemans the data structure for the output is different, I can't seem to read it the same way from the output of V1. – Kenpachi Jul 09 '19 at 06:46
  • It would be helpful if you could describe those data structures and the differences between them. There's not much to go on for anyone trying to answer your question. In any case, my book Core ML Survival Guide has a chapter on DeepLab v3. The source code is here: https://github.com/hollance/coreml-survival-guide/blob/master/Scripts/deeplab.py – Matthijs Hollemans Jul 09 '19 at 12:07

0 Answers0