Torch implementation of neural style algorithm

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

Image-to-image translation with conditional adversarial nets

Feedforward style transfer

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

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

Arbitrary Style Transfer in Real-time with Adaptive Instance Normalization

3.8% and 18.3% on CIFAR-10 and CIFAR-100

Code for "Texture Networks: Feed-forward Synthesis of Textures and Stylized Images" paper.

Lua/Torch implementation of DQN (Nature, 2015)

Torch implementations of various types of autoencoders

Precomputed Real-Time Texture Synthesis with Markovian Generative Adversarial Networks

Code repository for Towards 3D Human Pose Estimation in the Wild: a Weakly-supervised Approach

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

Variational Autoencoder trained by Feature Perceputal Loss

CVPR2017 Face hallucination