disiok / poetry-seq2seq Goto Github PK

• https://github.com/google/seq2seq
• https://github.com/farizrahman4u/seq2seq
• https://www.tensorflow.org/tutorials/seq2seq

Excuse me, after I ran the data_utils.py, I got the following result. I don't understand why the size of the training data is 0, could you please answer my question if you are available? Thank you.

Is it intended to function as a filter for generated text?

- Cluster character by rhyming, and remove generation and limit scope of first character to subset of rhyming ones
- Polishing: separate meaning modeling and pronunciation, additional pass to fix ping ze and rhyming
- Repeated training: downwards and upwards
- Restrict to nouns
- Fix embedding for end character

Add position information to word2vec, for example 3rd char on every line