The project is broken into three parts, each part run individually.
- GAN: Follow the Baseline Gan letter generator code jupyter notebook or run the notebook step-by-step
- Siamese Network: Follow the Siamese network jupyter notebook
- Convolutional GAN: Refer to the README within the CNN_GAN folder
Content of other folders:
generated_images
: GAN and CNN_GAN generated images, alongside the original EMNIST wordssiamese
: forgery data for the Siamese modelletter_recognition
: deprecated, not usedscribe
: examples generated from Graves' LSTM implementation