char-rnn-tensorflow
char-rnn-tensorflow copied to clipboard
Multi-layer Recurrent Neural Networks (LSTM, RNN) for character-level language models in Python using Tensorflow
I am new to machine learning and trying to use the tool to train for creating 2D game maps. The format of my maps are 20 rows by 100 columns...
There is a small typo in utils.py. Should read `separate` rather than `seperate`. Semi-automated pull request generated by https://github.com/timgates42/meticulous/blob/master/docs/NOTE.md
in my gpu server, remove the summary tensor make training 10x times faster. Please consider add a switch to close tensorboard summary.
Hi, I was wondering if someone could confirm my suspicion. I think this code in model.py is not ever used with the way sampling is done currently. ``` Python def...
add tf
sorry,this is a test.
Thank you very much for your contribution but I have a question. I need to train the RNN model for digital data( A time series in numerical form).Finally, I need...
Hi, I'm using `char-rnn` for computing sentence probability, which is main functionality of language modeling. This piece of code feeds sentence chars one by one and finds out probability of...
Implement temperature #22 with default value as 1. Following description is cited from [karpathy/char-rnn ](https://github.com/karpathy/char-rnn). > Temperature. An important parameter you may want to play with is -temperature, which takes...
First of all, I'm confused as of how the `save_dir` works: if I train a network pointing to a directory, and then eventually train another one pointing to that same...
when generating texts from shakespeare's text as input text a lot of \n are present. Any solution for this ?