d460: SketchRNN – A Neural Representation of Sketch Drawings – Source code

SketchRNN model released in Magenta: https://magenta.tensorflow.org/sketch_rnn

SketchRNN Source: https://github.com/tensorflow/magenta/tree/master/magenta/models/sketch_rnn

SketchRNN Dataset: https://github.com/googlecreativelab/quickdraw-dataset/blob/master/README.md

Paper: A Neural Representation of Sketch Drawings – https://arxiv.org/abs/1704.03477


We present sketchrnn, a recurrent neural network (RNN) able to construct stroke-based drawings of common objects. The model is trained on thousands of crude human-drawn images representing hundreds of classes. We outline a framework for conditional and unconditional sketch generation, and describe new robust training methods for generating coherent sketch drawings in a vector format.