How to modify the output layer to only give the next character in sequence given the previous characters ?

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 964 forks source link

How to modify the output layer to only give the next character in sequence given the previous characters ? #142

Closed jjsr closed 3 years ago

jjsr commented 3 years ago

I am new to NNs .I am able to understand the model is trained in a way that given input character sequence it can predict next character , Please guide me what model parameters i have to save while training or any pseudo algorithm to implement the same will help

victorr0 commented 3 years ago

Could you rephrase your question, because it is unclear / ambiguous. The char-rnn already does what you ask in the title of your question. Couldn't hurt to check out the README.md, Tuning-section may be helpful for model parameters.

jjsr commented 3 years ago

Thanks a lot victorr0 for writing back . Sorry for my bad phrasing . Yes I am able to figure that out later since i am quite new in the domain. Thanks for sharing this wonderful repo . that saves my life