keras_multi_cnn: keras cnn gru
In systats/textlearnR:

Word embedding + 1D pooled convolution + gru layer

1
2
3

keras_multi_cnn(input_dim, embed_dim = 128, seq_len = 50,
  filter_sizes = c(1, 2, 3, 4), num_filters = 50, output_dim = 2,
  output_fun = "softmax")

`input_dim`	Number of unique vocabluary/tokens
`embed_dim`	Number of word vectors
`seq_len`	Length of the input sequences
`output_dim`	Number of neurons of the output layer
`output_fun`	Output activation function
`n_filters`	the number of convolutional filters
`filter_size`	the window size (kernel_size)