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

Image-to-image translation with conditional adversarial nets

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

Feedforward style transfer

Deep Residual Networks with 1K Layers

Generative Adversarial Text-to-Image Synthesis

Spatial CNN for traffic lane detection (AAAI2018)

Deep Networks with Stochastic Depth

Torch implementations of various types of autoencoders

gvnn: Geometric Vision with Neural Networks

THE Deep Learning Benchmarks

A deep learning library for streamlining research and development using the Torch7 distribution.

Learning Deep Representations of Fine-grained Visual Descriptions

Training Deep Neural Networks with Weights and Activations Constrained to +1 or -1

[CVPR 2017] Unsupervised deep learning using unlabelled videos on the web

deep extensions to nn

92.45% on CIFAR-10 in Torch

Deep Attention Recurrent Q-Network

Torch implementation of CVPR'17 - Local Binary Convolutional Neural Networks http://xujuefei.com/lbcnn.html

Weight initialisation schemes for Torch7 neural network modules

MPI for Torch

torch extensions