tfm.nlp.encoders.build_encoder

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.

Except as otherwise noted, the content of this page is licensed under the Creative Commons Attribution 4.0 License, and code samples are licensed under the Apache 2.0 License. For details, see the Google Developers Site Policies. Java is a registered trademark of Oracle and/or its affiliates. Some content is licensed under the numpy license.

Last updated 2024-02-02 UTC.

tfm.nlp.encoders.build_encoder

Args

Returns