martin-gorner / tensorflow-rnn-shakespeare

Code from the "Tensorflow and deep learning - without a PhD, Part 2" session on Recurrent Neural Networks.
Apache License 2.0
534 stars 249 forks source link

ask about text generation phase #25

Closed atefa2009 closed 6 years ago

atefa2009 commented 6 years ago

in rnn_play.py generate great text ,but i have following question ?

1- can add (seed text) can be word or multiple words to generate some text based on it ? 2- if the question in 1 is no, what the evaluation method can be used to evaluate the generated text ?

to more understand i went to generate for example Advertising campaign

based on Advertising campaign dataset , how can evaluate the generated text without seed text ?

Thank you

martin-gorner commented 6 years ago

1- Yes you could run a sequence of characters through a trained cell to get the output state and start generating from that output state.