bi_gru {ttgsea}

R Documentation

Bidirectional GRU with embedding layer

Description

A predefined function that is used as a model in "ttgsea". This is a simple model, but you can define your own model. The loss function is "mean_squared_error" and the optimizer is "adam". Pearson correlation is used as a metric.

Usage

bi_gru(num_tokens, embedding_dim, length_seq, num_units)

Arguments

num_tokens	maximum number of tokens
embedding_dim	a non-negative integer for dimension of the dense embedding
length_seq	length of input sequences, input length of "layer_embedding""
num_units	dimensionality of the output space in the GRU layer

Value

model

Author(s)

Dongmin Jung

See Also

keras::keras_model_sequentia, keras::layer_embedding, keras::layer_gru, keras::bidirectional, keras::layer_dense, keras::compile

Examples

library(reticulate)
if (keras::is_keras_available() & reticulate::py_available()) {
  num_tokens <- 1000
  length_seq <- 30
  embedding_dim <- 50
  num_units <- 32
  model <- bi_gru(num_tokens, embedding_dim, length_seq, num_units)
  
  # stacked gru
  num_units_1 <- 32
  num_units_2 <- 16
  stacked_gru <- function(num_tokens, embedding_dim, length_seq,
                          num_units_1, num_units_2)
  {
    model <- keras::keras_model_sequential() %>%
      keras::layer_embedding(input_dim = num_tokens,
                             output_dim = embedding_dim,
                             input_length = length_seq,
                             mask_zero = TRUE) %>%
      keras::layer_gru(units = num_units_1,
                       activation = "relu",
                       return_sequences = TRUE) %>%
      keras::layer_gru(units = num_units_2,
                       activation = "relu") %>%
      keras::layer_dense(1)
      
    model %>%
      keras::compile(loss = "mean_squared_error",
                     optimizer = "adam",
                     metrics = custom_metric("pearson_correlation",
                                             metric_pearson_correlation))
  }
}

---