Closed yyao9 closed 5 years ago
Currently the interface is very crude. You can add whatever characters (say a-z) in the vocab list: (line 34, of char_rnn.py) using the command option --vocab.
parser.add_argument('--vocab', type=str, default="ab")
Will improve the interface to detect the vocab from the input text
I try to run the sample, and find out it seems currently the tool could support limited input characters, like string containing only 'a' and 'b', will the tool support all 256 characters given the minimum input unit is 1 byte, thanks.