Image Super-Resolution for Anime-Style Art

Torch implementation of neural style algorithm

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

Code for the paper 'Let there be Color!: Joint End-to-end Learning of Global and Local Image Priors for Automatic Image Colorization with Simultaneous Classification'.

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

Memory Networks implementations

[ICCV 2017] Torch code for Grad-CAM

Arbitrary Style Transfer in Real-time with Adaptive Instance Normalization

Sequence-to-sequence model with LSTM encoder/decoders and attention

Task generation for testing text understanding and reasoning

Autograd automatically differentiates native Torch code

Train a deeper LSTM and normalized CNN Visual Question Answering model. This current code can get 58.16 on OpenEnded and 63.09 on Multiple-Choice on test-standard.

Code for the paper "A Theoretically Grounded Application of Dropout in Recurrent Neural Networks"

A Neural Turing Machine implementation in Torch.

Gated Graph Sequence Neural Networks

Simple Baseline for Visual Question Answering

Code for the ICCV 2015 paper "Discriminative Learning of Deep Convolutional Feature Point Descriptors"

Code for our CVPR 2016 paper on Fashion styles in 128 floats.

Code for "So similar and yet incompatible: Toward the automated identification of semantically compatible words" in NAACL 2015 proceedings