# biome.text.modules.heads.classification.record_classification Module

# RecordClassification Class

class RecordClassification (
    backbone: ModelBackbone,
    labels: List[str],
    record_keys: List[str],
    tokens_pooler: Union[Seq2VecEncoderConfiguration, NoneType] = None,
    fields_encoder: Union[Seq2SeqEncoderConfiguration, NoneType] = None,
    fields_pooler: Union[Seq2VecEncoderConfiguration, NoneType] = None,
    feedforward: Union[Seq2SeqEncoderConfiguration, NoneType] = None,
    multilabel: Union[bool, NoneType] = False,

Task head for data record classification. Accepts a variable data inputs and apply featuring over defined record keys.

This head applies a doc2vec architecture from a structured record data input

Initializes internal Module state, shared by both nn.Module and ScriptModule.

# Ancestors

# inputs Method

def inputs(self) -> Union[List[str], NoneType]

The inputs names are determined by configured record keys

# Inherited members

# RecordClassificationConfiguration Class

class RecordClassificationConfiguration (*args, **kwds)

Lazy initialization for document classification head components

# Ancestors

# Inherited members

Maintained by