Skip to content

Neural networks recognizing parts of constructor set LEGO

Notifications You must be signed in to change notification settings

korolaab/Lego-NET

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

88 Commits
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Lego-NET

Lego recognizing network. This solution is to be used as an AI part of robot which is sorting objects.

REQUIREMENTS

  • Python 3.5.2
  • Tensorflow 1.12.0
  • Keras 2.2.4

HOW TO TRAIN

  1. Extract "dataset" into the root of "Lego-NET".
  2. Open terminal.
  3. Input python train.py --model=cnnhave nice training. =)

HOW TO USE

Input python im_process.py --image=<path> --Weights=<weights path>. You will get a probability map for all objects.

EXAMPLES

CNN output example
Basic CNN output example
U-Net output example
U-Net output example

DATASET

Extract to root of Lego-NET archive

Images for test

Just extract and set one of them in arguments.(Images)

About

Neural networks recognizing parts of constructor set LEGO

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages