tf.layers.EmbeddingLayer module
tf.layers.EmbeddingLayer module¶
- class tf.layers.EmbeddingLayer.EmbeddingLayer(*args: Any, **kwargs: Any)¶
Bases:
modelzoo.common.tf.layers.BaseLayer.BaseLayerEmbedding layer. Built on top of the Keras Embedding layer.
- build(input_shape)¶
- call(inputs, pad_id=- 1, scale=1)¶
Get token embeddings of inputs.
- Parameters
inputs (Tensor) – A tensor with shape
[batch_size, length].pad_id – Integer specifying which input ID corresponds instead to padding. It does not need to be a legal vocabulary entry. Any
`inputs`elements equal to this value will not be looked up, but instead directly output zeros. On the Wafer Scale Engine, this indicates the presence of variable sequence length.scale – Scaling of the embedding (in MLPERF
hidden_size**0.5is used).
- Returns
A tensor of embeddings with shape
[batch_size, length, hidden_size]. Padded positions are filled with zeros.- Return type
embeddings (Tensor)
- embedding_table()¶