Logo Lanfrica
  • Home
  • Atlas
  • Insights
  • Docs
  • Sign in

© 2026 Lanfrica. All rights reserved. All copyrights of the resources shown on the Lanfrica website belong to the original copyright holders, unless explicitly stated otherwise.

Ethiopian-AI-Programmers/Geez-numbers-hand-writing-recognition-system

Domain:

natural language processing

Record type:

softwaredataset
Creator:
Eth
Host:
Hand writing recognition for geez numbers, Ethiopia # Geez-numbers-hand-writing-recognition-system , Hand writing recognition for geez numbers, Ethiopia the pre-trained saved model which is 'muclass_num.h5' only works for the numbers from 1 to 4 only ##### there are datasets that i am addisng time to time you can find the in the 'am_numbers' folder. in the Train_geeznum_am.py script you can simply change the number of steps per epoch to the number of the images and then run it.

Visit

github.com

Tasks

computer visionoptical character recognition

Languages

Amharic