keras_char_cnn_zhang: keras_char_cnn_zhang

In systats/deeplyr: Pretrained keras models for predicting ideology from tweets.

Description

Character Level Convolutional Neural Network for Text Classification, as described in Zhang et al., 2015 (http://arxiv.org/abs/1509.01626) https://github.com/mhjabreel/CharCnn_Keras/blob/master/models/char_cnn_zhang.py

Usage

keras_char_cnn_zhang(input_dim, embed_dim = 128, seq_len = 50,
  filter_size = 5, conv_layers = c(100, 60, 30), pool_size = 4,
  dens_layers = c(50, 30, 10), dropout = 0.2, output_dim = 1,
  output_fun = "sigmoid")

Arguments

input_dim	Number of unique vocabluary/tokens
embed_dim	Number of word vectors
seq_len	Length of the input sequences
filter_size	the window size (kernel_size)
conv_layers	number of filters by layer
pool_size	pooling dimension (filters)
dens_layers	Number of neurons by dense layer
dropout	a scalar between 0 and .5
output_dim	Number of neurons of the output layer
output_fun	Output activation function

Value

keras model

systats/deeplyr documentation built on Oct. 4, 2020, 7:59 p.m.