awslabs/gluonts
Using dynamic categorical features in NN models
Aberta
#392 aberto em 15 de out. de 2019
enhancementgood first issuehelp wanted
Métricas do repositório
- Stars
- (3.888 estrelas)
- Métricas de merge de PR
- (Mesclagem média 26d 17h) (4 fundiu PRs em 30d)
Description
GluonTS allows to work with dynamic categorical features, but there is no way to use them in most of the NN models (e.g. DeepAR, Transformer, etc.)
They can be incorporated by applying embeddings and concatenating them with other dynamic features. Does it make sense to modify DeepAR and other models with this change, or is it better to stick with the current implementation and to write new model implementations that will use dynamic categorical features?