Open ysig opened 2 years ago
Hey you seem to set len(sel.lex) as the size of the latent vector.
https://github.com/amzn/convolutional-handwriting-gan/blob/f7daa5045a281be23c1d20c5b74f12ffbddf69f9/models/ScrabbleGAN_baseModel.py#L109
self.lex is the lexicon and as so taking it's size will return the number of words found in the lexicon.
But as latent vector you need an one-hot on the alphabet size.
Of-course this will still work as len(self.lex) >> len(opt.n_classes) but there is probably something wrong.
Hi Thanks for your interest in this package.
You seem to be right, but since I am no longer able to edit this repo I cannot fix this. @sharonFogel can you help?
Hey you seem to set len(sel.lex) as the size of the latent vector.
https://github.com/amzn/convolutional-handwriting-gan/blob/f7daa5045a281be23c1d20c5b74f12ffbddf69f9/models/ScrabbleGAN_baseModel.py#L109
self.lex is the lexicon and as so taking it's size will return the number of words found in the lexicon.
But as latent vector you need an one-hot on the alphabet size.
Of-course this will still work as len(self.lex) >> len(opt.n_classes) but there is probably something wrong.