Layer for positional embedding — layer_pos_embedding_wrapper • deepG

Positional encoding layer with learned embedding.

Usage

layer_pos_embedding_wrapper(
  maxlen = 100,
  vocabulary_size = 4,
  load_r6 = FALSE,
  embed_dim = 64
)

Arguments

maxlen: Length of predictor sequence.
vocabulary_size: Number of unique character in vocabulary.
load_r6: Whether to load the R6 layer class.
embed_dim: Dimension for token embedding. No embedding if set to 0. Should be used when input is not one-hot encoded (integer sequence).

Value

A keras layer implementing positional embedding.

Examples

if (FALSE) { # reticulate::py_module_available("tensorflow")
l <- layer_pos_embedding_wrapper()
}