Software that can generate photos from paintings, turn horses into zebras, perform style transfer, and more.

Multi-layer Recurrent Neural Networks (LSTM, GRU, RNN) for character-level language models in Torch

Image-to-image translation with conditional adversarial nets

Densely Connected Convolutional Networks, In CVPR 2017 (Best Paper Award).

Modified implementation of DCGAN focused on generative art. Includes pre-trained models for landscapes, nude-portraits, and others.

Task generation for testing text understanding and reasoning

Activity Recognition Algorithms for the Charades Dataset

📝 A note-management application