← Back to API reference

neuraltrain.models.simpleconv.SimpleConvTimeAgg

pydantic model neuraltrain.models.simpleconv.SimpleConvTimeAgg

SimpleConv with temporal aggregation layer and optional output heads.

Parameters:

• time_agg_out –

  • “gap” : Global average pooling

  • ”linear” : Linear layer with one output

  • ”att” : Bahdanau attention layer

• n_time_groups – Number of groups within which to apply temporal aggregation, e.g. 4 means the time dimension will be split into 4 groups and each group will be aggregated (and optionally projected) separately.

Fields:

• n_time_groups (int | None)

• output_head_config (neuraltrain.models.common.Mlp | dict[str, neuraltrain.models.common.Mlp] | None)

• time_agg_out (Literal['gap', 'linear', 'att'])

field time_agg_out: Literal['gap', 'linear', 'att'] = 'gap'

field n_time_groups: int | None = None

field output_head_config: Mlp | dict[str, Mlp] | None = None

build(n_in_channels: int, n_outputs: int) → SimpleConvTimeAggModel

← Back to API reference