keras_gru_cnn: keras gru cnn
In systats/textlearnR:

Word embedding + gru global average & max + 1D pooled convolution

1
2
3

keras_gru_cnn(input_dim, embed_dim = 128, seq_len = 50, gru_dim = 64,
  gru_drop = 0.2, filter_sizes = c(3, 2), n_filters = c(120, 60),
  pool_size = 4, output_fun = "softmax", output_dim = 1)

`input_dim`	Number of unique vocabluary/tokens
`embed_dim`	Number of word vectors
`seq_len`	Length of the input sequences
`gru_dim`	Number of lstm neurons (default 32)
`gru_drop`	default is 2
`n_filters`	the number of convolutional filters
`pool_size`	pooling dimension (filters)
`output_fun`	Output activation function
`output_dim`	Number of neurons of the output layer
`filter_size`	the window size (kernel_size)