Interface for JSON specification of a MusicVAE model.
MusicVAE
max_seq_len: Model trained on dataset w/ this max sequence length.
mode: Pre-trained models have this parameter for legacy reasons. 0 for VAE, 1 for Decoder only. This model is Decoder only (not used).
name: QuickDraw name, like cat, dog, elephant, etc
scale_factor: the factor to convert from neural-network space to pixel space. Most pre-trained models have this number between 80-120
version: Pre-trained models have a version between 1-6, for the purpose of experimental research log.
Generated using TypeDoc
Interface for JSON specification of a
MusicVAEmodel.max_seq_len: Model trained on dataset w/ this max sequence length.
mode: Pre-trained models have this parameter for legacy reasons. 0 for VAE, 1 for Decoder only. This model is Decoder only (not used).
name: QuickDraw name, like cat, dog, elephant, etc
scale_factor: the factor to convert from neural-network space to pixel space. Most pre-trained models have this number between 80-120
version: Pre-trained models have a version between 1-6, for the purpose of experimental research log.