Skip to main content
Ctrl+K
pytorch-forecasting  documentation - Home pytorch-forecasting  documentation - Home
  • Getting started
  • Tutorials
  • Data
  • Models
  • Metrics
  • FAQ
  • Installation
  • API
  • Model Overview
  • Release Notes
  • GitHub
  • GitHub
Ctrl+K
  • Getting started
  • Tutorials
  • Data
  • Models
  • Metrics
  • FAQ
  • Installation
  • API
  • Model Overview
  • Release Notes
  • GitHub
  • GitHub
Ctrl+K

Section Navigation

  • Data
    • pytorch_forecasting.data.encoders.EncoderNormalizer
    • pytorch_forecasting.data.encoders.GroupNormalizer
    • pytorch_forecasting.data.encoders.MultiNormalizer
    • pytorch_forecasting.data.encoders.NaNLabelEncoder
    • pytorch_forecasting.data.encoders.TorchNormalizer
    • pytorch_forecasting.data.samplers.TimeSynchronizedBatchSampler
    • pytorch_forecasting.data.samplers.GroupedSampler
    • pytorch_forecasting.data.timeseries.TimeSeriesDataSet
  • Models
    • M Layer
      • pytorch_forecasting.models.deepar.DeepAR
      • pytorch_forecasting.models.mlp.DecoderMLP
      • pytorch_forecasting.models.nbeats.NBeats
      • pytorch_forecasting.models.nbeats.NBeatsKAN
      • pytorch_forecasting.models.nhits.NHiTS
      • pytorch_forecasting.models.rnn.RecurrentNetwork
      • pytorch_forecasting.models.temporal_fusion_transformer.TemporalFusionTransformer
      • pytorch_forecasting.models.tide.TiDEModel
      • pytorch_forecasting.models.timexer.TimeXer
      • pytorch_forecasting.models.xlstm.xLSTMTime
    • P Layer
      • pytorch_forecasting.models.deepar._deepar_pkg.DeepAR_pkg
      • pytorch_forecasting.models.mlp._decodermlp_pkg.DecoderMLP_pkg
      • pytorch_forecasting.models.nbeats._nbeats_pkg.NBeats_pkg
      • pytorch_forecasting.models.nbeats._nbeatskan_pkg.NBeatsKAN_pkg
      • pytorch_forecasting.models.nhits._nhits_pkg.NHiTS_pkg
      • pytorch_forecasting.models.rnn._rnn_pkg.RecurrentNetwork_pkg
      • pytorch_forecasting.models.temporal_fusion_transformer._tft_pkg.TemporalFusionTransformer_pkg
      • pytorch_forecasting.models.tide._tide_pkg.TiDEModel_pkg
  • Package
    • pytorch_forecasting.models.deepar._deepar_pkg.DeepAR_pkg
    • pytorch_forecasting.models.mlp._decodermlp_pkg.DecoderMLP_pkg
    • pytorch_forecasting.models.nbeats._nbeats_pkg.NBeats_pkg
    • pytorch_forecasting.models.nbeats._nbeatskan_pkg.NBeatsKAN_pkg
    • pytorch_forecasting.models.nhits._nhits_pkg.NHiTS_pkg
    • pytorch_forecasting.models.rnn._rnn_pkg.RecurrentNetwork_pkg
    • pytorch_forecasting.models.temporal_fusion_transformer._tft_pkg.TemporalFusionTransformer_pkg
    • pytorch_forecasting.models.tide._tide_pkg.TiDEModel_pkg
  • Metrics
    • pytorch_forecasting.metrics.quantile.QuantileLoss
    • pytorch_forecasting.metrics.point.CrossEntropy
    • pytorch_forecasting.metrics.point.PoissonLoss
    • pytorch_forecasting.metrics.point.SMAPE
    • pytorch_forecasting.metrics.point.MAPE
    • pytorch_forecasting.metrics.point.MAE
    • pytorch_forecasting.metrics.point.RMSE
    • pytorch_forecasting.metrics.point.MASE
    • pytorch_forecasting.metrics.point.TweedieLoss
    • pytorch_forecasting.metrics.distributions.NormalDistributionLoss
    • pytorch_forecasting.metrics.distributions.MultivariateNormalDistributionLoss
    • pytorch_forecasting.metrics.distributions.NegativeBinomialDistributionLoss
    • pytorch_forecasting.metrics.distributions.LogNormalDistributionLoss
    • pytorch_forecasting.metrics.distributions.BetaDistributionLoss
    • pytorch_forecasting.metrics.distributions.MQF2DistributionLoss
    • pytorch_forecasting.metrics.distributions.ImplicitQuantileNetworkDistributionLoss
  • Utils
    • utils
      • _classproperty
        • classproperty
      • _coerce
        • _coerce_to_dict
        • _coerce_to_list
      • _dependencies
        • _dependencies
        • tests
      • _estimator_checks
        • _get_test_names_for_obj
        • _get_test_names_from_class
        • check_estimator
        • parametrize_with_checks
      • _maint
        • _show_versions
      • _utils
        • apply_to_list
        • autocorrelation
        • concat_sequences
        • create_mask
        • detach
        • get_embedding_size
        • groupby_apply
        • integer_histogram
        • masked_op
        • move_to_device
        • next_fast_len
        • padded_stack
        • profile
        • repr_class
        • to_list
        • unpack_sequence
        • unsqueeze_like
        • InitialParameterRepresenterMixIn
        • OutputMixIn
        • TupleOutputMixIn
  • Tutorials
    • Demand forecasting with the Temporal Fusion Transformer
    • Interpretable forecasting with N-Beats
    • How to use custom data and implement custom models and metrics
    • Autoregressive modelling with DeepAR and DeepVAR
    • Multivariate quantiles and long horizon forecasting with N-HiTS
  • Getting started
  • API

API#

Try the API v2 pre-release!

You are viewing Documentation of v1 API. A New API version 2 is in development.
Try it out before release: v2 API Reference
Caution: v2 is WIP and unstable. Not yet production-ready.
  • Data
    • Time series data set
    • Details
  • Models
    • Architecture
    • Usage
    • Selecting an architecture
    • Details and available models
  • Package
    • Responsibilities of a v1 Package
    • Anatomy of a v1 Package
    • API Reference
  • Metrics
    • Details
  • Utils
    • utils
  • Tutorials
    • Demand forecasting with the Temporal Fusion Transformer
    • Interpretable forecasting with N-Beats
    • How to use custom data and implement custom models and metrics
    • Autoregressive modelling with DeepAR and DeepVAR
    • Multivariate quantiles and long horizon forecasting with N-HiTS

previous

Getting started

next

Data

Show Source

© Copyright 2020, present, the pytorch-forecasting developers.

Created using Sphinx 9.1.0.

Built with the PyData Sphinx Theme 0.19.0.