Instantiate a Transformer encoder network from EncoderConfig.
tfm.nlp.encoders.build_encoder(
config: tfm.nlp.encoders.EncoderConfig
,
embedding_layer: Optional[tf.keras.layers.Layer] = None,
encoder_cls=None,
bypass_config: bool = False
)
Args |
config
|
the one-of encoder config, which provides encoder parameters of a
chosen encoder.
|
embedding_layer
|
an external embedding layer passed to the encoder.
|
encoder_cls
|
an external encoder cls not included in the supported encoders,
usually used by gin.configurable.
|
bypass_config
|
whether to ignore config instance to create the object with
encoder_cls .
|
Returns |
An encoder instance.
|