tfm.nlp.networks.BertEncoder

Stay organized with collections Save and categorize content based on your preferences.

Bi-directional Transformer-based encoder network.

tfm.nlp.networks.BertEncoder(
    vocab_size,
    hidden_size=768,
    num_layers=12,
    num_attention_heads=12,
    max_sequence_length=512,
    type_vocab_size=16,
    inner_dim=3072,
    inner_activation=(lambda x: tf.keras.activations.gelu(x, approximate=True)),
    output_dropout=0.1,
    attention_dropout=0.1,
    initializer=tf.keras.initializers.TruncatedNormal(stddev=0.02),
    output_range=None,
    embedding_width=None,
    embedding_layer=None,
    norm_first=False,
    dict_outputs=False,
    return_all_encoder_outputs=False,
    return_attention_scores: bool = False,
    **kwargs
)

This network implements a bi-directional Transformer-based encoder as described in "BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding" (https://arxiv.org/abs/1810.04805). It includes the embedding lookups and transformer layers, but not the masked language model or classification task networks.

The default values for this object are taken from the BERT-Base implementation in "BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding".

vocab_size The size of the token vocabulary.
hidden_size The size of the transformer hidden layers.
num_layers The number of transformer layers.
num_attention_heads The number of attention heads for each transformer. The hidden size must be divisible by the number of attention heads.
max_sequence_length The maximum sequence length that this encoder can consume. If None, max_sequence_length uses the value from sequence length. This determines the variable shape for positional embeddings.
type_vocab_size The number of types that the 'type_ids' input can take.
inner_dim The output dimension of the first Dense layer in a two-layer feedforward network for each transformer.
inner_activation The activation for the first Dense layer in a two-layer feedforward network for each transformer.
output_dropout Dropout probability for the post-attention and output dropout.
attention_dropout The dropout rate to use for the attention layers within the transformer layers.
initializer The initialzer to use for all weights in this encoder.
output_range The sequence output range, [0, output_range), by slicing the target sequence of the last transformer layer. None means the entire target sequence will attend to the source sequence, which yields the full output.
embedding_width The width of the word embeddings. If the embedding width is not equal to hidden size, embedding parameters will be factorized into two matrices in the shape of ['vocab_size', 'embedding_width'] and 'embedding_width', 'hidden_size'.
embedding_layer An optional Layer instance which will be called to generate embeddings for the input word IDs.
norm_first Whether to normalize inputs to attention and intermediate dense layers. If set False, output of attention and intermediate dense layers is normalized.
dict_outputs Whether to use a dictionary as the model outputs.
return_all_encoder_outputs Whether to output sequence embedding outputs of all encoder transformer layers. Note: when the following dict_outputs argument is True, all encoder outputs are always returned in the dict, keyed by encoder_outputs.
return_attention_scores Whether to add an additional output containing the attention scores of all transformer layers. This will be a list of length num_layers, and each element will be in the shape [batch_size, num_attention_heads, seq_dim, seq_dim].

pooler_layer The pooler dense layer after the transformer layers.
transformer_layers List of Transformer layers in the encoder.

Methods

call

call(
    inputs, training=None, mask=None
)

Calls the model on new inputs and returns the outputs as tensors.

In this case call() just reapplies all ops in the graph to the new inputs (e.g. build a new computational graph from the provided inputs).

Args
inputs Input tensor, or dict/list/tuple of input tensors.
training Boolean or boolean scalar tensor, indicating whether to run the Network in training mode or inference mode.
mask A mask or list of masks. A mask can be either a boolean tensor or None (no mask). For more details, check the guide here.

Returns
A tensor if there is a single output, or a list of tensors if there are more than one outputs.

get_embedding_layer

View source

get_embedding_layer()

get_embedding_table

View source

get_embedding_table()