Phillip Isola

Image-to-image translation with conditional adversarial nets

A 2017 research implementation of image-to-image translation using conditional GANs, train a model to convert images from one visual style into another, like maps to satellite photos or sketches to shoes.

Code for running real vs fake experiments on Amazon Mechanical Turk

Boundary detection and image segmentation using pointwise mutual information

Tools for visualizing neural nets

No description.

No description.

No description.

Load Caffe networks in Torch7

command line scripts for building a semantic graph

Caffe: a fast open framework for deep learning.

Computation using data flow graphs for scalable machine learning