After compiling a large enough collection of Keith Haring drawings, I converted them to SVG files so the line paths could be interpreted by TensorFlow. After the initial learning curves (this was my first deeper dive in TF), I was able to train the model on sample drawing datasets (boomerangs, kangaroos, etc) and finally on Keith Haring drawings and generate fake images in python. At the time of this project, David Ha was completing a system to export those weights to JS, to generate the images in realtime. I'm still continuing with this idea and am now working on creating a JS verison of this that works in 3D space.
RNN sequence length: 300, number of epochs: 300, min_num_stroke: 2, max_num_stroke: 8
RNN sequence length: 500, number of epochs: 500, min_num_stroke: 4, max_num_stroke: 16