Face recognition with deep neural networks.

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

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

Convolutional Recurrent Neural Network (CRNN) for image-based sequence recognition.

Memory Networks implementations

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

Neural model for converting Image-to-Markup (by Yuntian Deng yuntiandeng.com)

Example implementation of the DeepStack algorithm for no-limit Leduc poker

Generative Adversarial Text-to-Image Synthesis

Learning Efficient Convolutional Networks through Network Slimming, In ICCV 2017.

Autograd automatically differentiates native Torch code

THE Deep Learning Benchmarks

Training code for the networks described in "How far are we from solving the 2D & 3D Face Alignment problem? (and a dataset of 230,000 3D facial landmarks)" paper.

Real time face alignment