Interesting Machine Learning Projects

High-res in-painting

Photo Style Transfer

Cycle GAN

Image translation without input-output pairs.

Style Transfer, Tensorflow

Give computer two pictures and it will redraw the first one with the style of the second one.

Fast Style Transfer Even faster, realtime Style Transfer

Multiple transfers at the same time, Paper and another fast style transfer

The original Style Transfer requires lots of computational resources, this is simpler but faster version.

OpenFace, face recognition with Deep Learning

Super Resolution using Deep Learning

From left to right, the first column is the 16x16 input image, the second one is what you would get from a standard bicubic interpolation, the third is the output generated by the neural net, and on the right is the ground truth.

Also, similar project subpixel and one more project.

Neural Face, generate faces with DCGAN

Generate Anime Faces with DCGAN

Online Demo.

Image Completion with TensorFlow

Computer restores the missing part of the picture.

Text to Image

Tell computer how flower should looks like and it will draw it.

Image to Text

Computer creating little stories about pictures.

Super Resolution

Image Super-Resolution for Anime-Style Art.

Neural Doodle / Texture Transfer

Turn your two-bit doodles into fine artworks with deep neural networks, generate seamless textures from photos, transfer style from one image to another, perform example-based upscaling, but wait... there's more! (An implementation of Semantic Style Transfer.) Video.

Score Selfie

Computer tells if selfie is good or bad. Sorted selfies on the picture below - good at the top bad at the bottom.

Generate description of an Image

There's also similar tool from Google.

Colorize Image

There's also another project doing the same

Super Mario, Neural Net and Genetic Algorithms

And, similar project with the code and explanation.

Also Flappy Bird and car racing

Smile Vector

Makes people smile, or removes smile.

Visual Question Answering

Interactive Image Generation via Generative Adversarial Networks

Find Images by Sketch

Image Translation