models

Models for timeseries forecasting.

Modules

pytorch_forecasting.models.base_model	Timeseries models share a number of common characteristics.
pytorch_forecasting.models.baseline	Baseline model.
pytorch_forecasting.models.deepar	DeepAR: Probabilistic forecasting with autoregressive recurrent networks which is the one of the most popular forecasting algorithms and is often used as a baseline
pytorch_forecasting.models.mlp	Simple models based on fully connected networks
pytorch_forecasting.models.nbeats	N-Beats model for timeseries forecasting without covariates.
pytorch_forecasting.models.nhits	N-HiTS model for timeseries forecasting with covariates.
pytorch_forecasting.models.nn
pytorch_forecasting.models.rnn	Simple recurrent model - either with LSTM or GRU cells.
pytorch_forecasting.models.temporal_fusion_transformer	The temporal fusion transformer is a powerful predictive model for forecasting timeseries