search

sherjilozair / char-rnn-tensorflow

Multi-layer Recurrent Neural Networks (LSTM, RNN) for character-level language models in Python using Tensorflow
MIT License
2.64k stars 960 forks source link

Make sample play nicer with unicode. #40

Closed john-parton closed 8 years ago

john-parton commented 8 years ago

Further fixes for https://github.com/sherjilozair/char-rnn-tensorflow/issues/38

Basically, sample was building up a str instead of a unicode on python2.7. I used six.text_type and defaulted prime to u' ' to fix that.

One step closer to crazy emoji-based neural nets!

sherjilozair commented 8 years ago

Great! Thanks again for your contribution! Looking forward to your emoji-based results! 👍 💯