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

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

Facebook AI Research Sequence-to-Sequence Toolkit

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'.

Memory Networks implementations

A torch implementation of http://arxiv.org/abs/1511.06434

A Torch implementation of the object detection network from "A MultiPath Network for Object Detection" (https://arxiv.org/abs/1604.02135)

Facebook's extensions to torch/cunn.

Torch on steroids

LSTM language model with CNN over characters

Facebook libraries and utilities for Lua

Autograd automatically differentiates native Torch code

Text classification using a convolutional neural network.

Torch7+OpenCV+ConvNets

Implementation of http://arxiv.org/abs/1511.05641 that lets one build a larger net starting from a smaller one.

Multi-Perspective Convolutional Neural Networks for modeling textual similarity (He et al., EMNLP 2015)

Code for Kaggle EEG Detection competition

6th place solution in "Denoising Dirty Documents"

word2vec implementation for torch7

Learning to program in Lua using "Torch" and other useful libraries