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).

Efficient, reusable RNNs and LSTMs for torch

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

Lua Fun is a high-performance functional programming library for Lua designed with LuaJIT's trace compiler in mind.

[ICCV 2017] Torch code for Grad-CAM

Torch on steroids

Recurrent Neural Network library for Torch7's nn

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

Learning to Execute

Multi-Scale Dense Networks for Resource Efficient Image Classification （ICLR 2018 Oral）

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

Spatio-temporal video autoencoder with convolutional LSTMs

Implementation of Variational Auto-Encoder in Torch7

Practical 6: LSTM language models

Deep Unsupervised Clustering with Gaussian Mixture Variational Autoencoders

OpenCV bindings for Torch.

Torch implementation of DRAW: A Recurrent Neural Network For Image Generation

Fast R-CNN Torch Implementation

Experimental Torch7 implementation of RCNN for Object Detection with a Region Proposal Network

Multi-threaded VGG 19 feature extractor in Torch

A lightweight Lua-based IDE for Lua with code completion, syntax highlighting, live coding, remote debugger, and code analyzer

OverFeat-Torch7 Wrapper Library

Full convolution MultiBox Detector ( like SSD) implemented in Torch.

Playing with an LSTM neural network.