Software that can generate photos from paintings, turn horses into zebras, perform style transfer, and more.

Image-to-image translation with conditional adversarial nets

Modified implementation of DCGAN focused on generative art. Includes pre-trained models for landscapes, nude-portraits, and others.

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

This repository implements a demo of 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.

Generative Adversarial Text-to-Image Synthesis

Temporal Segments LSTM and Temporal-Inception for Activity Recognition

Code for the paper "A Theoretically Grounded Application of Dropout in Recurrent Neural Networks"

[CVPR 2017] Torch code for Visual Dialog

Volumetric CNN for feature extraction and object classification on 3D data.

Code for "Learning Feature Pyramids for Human Pose Estimation" (ICCV 2017)

This code implements a demo of the Binarized Convolutional Landmark Localizers for Human Pose Estimation and Face Alignment with Limited Resources paper by Adrian Bulat and Georgios Tzimiropoulos.

Deep metric learning using Triplet network

Code for "On the Effects of Batch and Weight Normalization in Generative Adversarial Networks"

Review Network for Caption Generation

Towards Neural Phrase-based Machine Translation

Torch implementation of SampleRNN: An Unconditional End-to-End Neural Audio Generation Model

DRESS simplification model (EMNLP 2017) described in http://aclweb.org/anthology/D/D17/D17-1062.pdf

Source code of DeepTracking research project

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

Torch Implemention of ECCV'16 paper: Attribute2Image

🔍 Decoding Diverse Solutions from Neural Sequence Models

Towards Diverse and Natural Image Descriptions via a Conditional GAN

Word2Vec implementation in Torch

word2vec implementation for torch7

Wide-residual network implementations. Best result for cifar10(97.12%), cifar100(84.12%), and other kaggle challenges

Neural network definition models

👀 A Chatbot based on VQA (Visual Question Answering)

Toy codes to kick-start deep learning for NLP !