AutoformerConfig

chronax.models.autoformer.AutoformerConfig

Hyperparameters for :class:AutoformerModel.

__init__(self, h=24, input_size=72, hidden_size=128, n_heads=4, factor=3, moving_avg_window=25, encoder_layers=2, decoder_layers=1, conv_hidden_size=32, decoder_input_size_multiplier=0.5, dropout=0.05, activation='gelu')

Parameter	Type	Default	Description
h	int	24	Forecast horizon.
input_size	int	72	Context window length fed to the encoder.
hidden_size	int	128	Embedding / attention hidden dimension.
n_heads	int	4	Number of auto-correlation heads (must divide hidden_size).
factor	int	3	Auto-correlation top-k factor (top_k = factor * log(L)).
moving_avg_window	int	25	Kernel size for the trend moving-average filter.
encoder_layers	int	2	Number of stacked encoder layers.
decoder_layers	int	1	Number of stacked decoder layers.
conv_hidden_size	int	32	Hidden channels for the position-wise FFN convolutions.
decoder_input_size_multiplier	float	0.5	Fraction of input_size used as the decoder start-token ("label") length; must be in (0, 1).
dropout	float	0.05	Dropout rate applied throughout (training only).
activation	str	"gelu"	FFN nonlinearity — "relu" or "gelu".

AutoformerModel

chronax.models.autoformer.AutoformerModel · inherits flax.linen.Module

Univariate Autoformer forecaster built with flax.linen. Forward pass: [B, input_size, 1] -> [B, h, 1].

__init__(self, config)

Parameter	Type	Default	Description
config	AutoformerConfig	-	(undocumented)

__call__(self, insample_y, deterministic=True) -> jnp.ndarray

(The forward pass of the model.)

Parameter	Type	Default	Description
insample_y	jnp.ndarray	-	(undocumented)
deterministic	bool	True	(undocumented)

Returns: jnp.ndarray (The forecast output, shape [B, h, 1]).