Image Super-Resolution for Anime-Style Art

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

🔥 A cross-platform build utility based on Lua

Torch implementation of DeepMask and SharpMask

Code for the paper 'Let there be Color!: Joint End-to-end Learning of Global and Local Image Priors for Automatic Image Colorization with Simultaneous Classification'.

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

Implementation of a classification framework from the paper Aggregated Residual Transformations for Deep Neural Networks

The original code from the DeepMind article + my tweaks

Memory Networks implementations

High-Resolution Image Inpainting using Multi-Scale Neural Patch Synthesis

Torch on steroids

Generative Adversarial Text-to-Image Synthesis

Spatial CNN for traffic lane detection (AAAI2018)

Neural conversational model in Torch

End-to-end deep learning image-similarity search engine

Models and code related to sketch simplification of rough sketches.

Deep Multi-scale CNN for Dynamic Scene Deblurring

A Real-time Mario Kart 64 AI using ConvNets.

Torch implementation of "Enhanced Deep Residual Networks for Single Image Super-Resolution"

Code for the paper 'Globally and Locally Consistent Image Completion'. https://iizuka.cs.tsukuba.ac.jp/projects/completion/

A torch implementation of "Pixel-Level Domain Transfer"

Image De-raining Using a Conditional Generative Adversarial Network

Torch Implementation of "Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network"

Multi-style Generative Network for Real-time Transfer

Training code for "Coarse-to-Fine Volumetric Prediction for Single-Image 3D Human Pose", CVPR 2017