Stroke Maps, TensorFlow, and Deep Learning

Just completed recreations of The Scream and The Mona Lisa.  These are not meant to be accurate reproductions of the paintings, but an attempt at recreating how the artists painted each stroke.  The Idea being that once these strokes are mapped, TensorFlow and Deep Learning can use the data to make better pastiches.

This recreation attempts to capture and record the order of da Vinci's brushstrokes for use in Deep Learning analysis.

Reconstructive painting of Edvard Munch's The Scream. Not meant to be accurate reporduction, but instead mapping of how he may have made his strokes.