decoder.deep_perceiver_decoder

Classes

DeepPerceiverDecoderConfig

Configuration for the DeepPerceiverDecoder module.

Module Contents

class decoder.deep_perceiver_decoder.DeepPerceiverDecoderConfig(/, **data)

Bases: pydantic.BaseModel

Configuration for the DeepPerceiverDecoder module.

Create a new model by parsing and validating input data from keyword arguments.

Raises [ValidationError][pydantic_core.ValidationError] if the input data cannot be validated to form a valid model.

self is explicitly positional-only to allow self as a field name.

Parameters:

data (Any)

perceiver_block_config: emmi.schemas.modules.blocks.perceiver_block_config.PerceiverBlockConfig = None

Configuration for the Perceiver blocks used in the decoder.

depth: int = None

Number of deep perceiver decoder layers (i.e., depth of the network). Defaults to 1.

output_dim: int = None

Output dimension of the decoder.

input_dim: int = None

Input dimension for the query positions.