Fix initializations when extending from Model

MSRDL / Deep4Cast

Probabilistic Multivariate Time Series Forecast using Deep Learning

BSD 3-Clause "New" or "Revised" License

94 stars 22 forks source link

Fix initializations when extending from Model #55

Closed bischtob closed 5 years ago

bischtob commented 5 years ago

We want input and output dimensions to be user specified when initialization the model and forecaster class. This causes problems, because we have currently delayed initializations. For example, no real custom models or loss functions are currently accepted by the forecaster.