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