Skip to content

MintOcha/flagid

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

13 Commits
 
 
 
 
 
 
 
 

Repository files navigation

flagid 🏳️

AI country flag identification neural network for detecting country flags in photos, based on efficientnet08. Fast 92% accurate AI flag identifier, trained on world flag dataset.

Features:

  • VERY easy to use
  • IDs blurry, rotated flags and images of flags in the wild
  • Fast and runs on dogshit PCs

Looking for contributions to read me with image examples

To train: https://www.kaggle.com/code/mreowie/country-flag-identifier/edit

Usage instructions

git clone https://github.com/MintOcha/flagid
cd flagid
  1. Install requirements
pip install torch torchvision pillow numpy requests opencv-python selenium webdriver-manager scikit-learn tqdm matplotlib
  1. Run the script! Set test_image_path = "image.png" to be your image name and run use_model.py

I hope i made this easy to use :)

image

Examples: image

results!!

    accuracy                           0.92      5154
   macro avg       0.92      0.92      0.92      5154
weighted avg       0.92      0.92      0.92      5154

About

Flag identifier AI trained on pytorch, RNN based on efficientnet08

Resources

Stars

0 stars

Watchers

0 watching

Forks

Packages

 
 
 

Contributors

Languages