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

🔥 A cross-platform build utility based on Lua

Image-to-image translation with conditional adversarial nets

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

Feedforward style transfer

Torch implementation of DeepMask and SharpMask

Open Source Neural Machine Translation in Torch (deprecated)

Torch implementation of ResNet from http://arxiv.org/abs/1512.03385 and training scripts

Memory Networks implementations

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

Implements an efficient softmax approximation as described in the paper "Efficient softmax approximation for GPUs" (http://arxiv.org/abs/1609.04309)

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