Implementation of Siamese network for handwritten Arabic characters using Keras.
- The dataset is available on Kaggle here.
- I have used 60% of the characters (16 characters) for training and used the other 40% for testing (12 characters).
- I chose 20 images for each class (character) randomly using different seeds and the performance was similar for each seed.
- The validation was done using N-way one shot learning over 500 trials with N in range (2-12).
- I have also tested it against Nearest neighbour.
- The training and validation were done using GPU and Google Colab.
- Model weights are available here with 92.8% accuracy on test data.
