Skip to content

Latest commit

 

History

History
36 lines (30 loc) · 961 Bytes

README.md

File metadata and controls

36 lines (30 loc) · 961 Bytes

Classification of handwritten chess move records

The model recognizes written text using the AlexNet architecture.

You can test the model's performance at ChessVisionLab.com

Create environment for train and evaluate model

  1. Clone chess-vision-lab repo
    git clone https://github.com/JacekMaksymiuk/chess-vision-lab && cd chess-vision-lab
  2. Prepare env: unzip dataset and create necessary folders
    make install

Train and validate model

  1. Run console in docker
    make console
  2. Start training in console
    ../bin/train.sh

Runs the classification for the given images of handwritten moves

  1. Run console in docker
    make console
  2. Start training in console
    ../bin/train.sh