Commit 1057efd8 authored by ana's avatar ana

Adding Readme CharRNN

parent e448e048
### Python 2.7
create virtual environment for project
$ virtualenv
$ pip install
$ pip freeze -> creates list of installed packages
### Requirements install
pip install -r requirements.txt
### Follow installation instructions Torch-RNN here:
http://pad.constantvzw.org/p/algorithmic_uncertainty.torch-rnn.install
(needs translation to English!)
### New text
copy .txt in charrnn/torch-rnn/data
Convert text to json, go to charrnn/torch-rnn/scripts
§ python preprocess.py
### Train on new text
Go to charrnn/torch-rnn
$ th train.lua -input_h5 data/timmermans.h5 -input_json data/timmermans.json -model_type rnn -num_layers 2 -rnn_size 256 -wordvec_size 128
### Print checkpoints
$ th sample.lua -checkpoint cv/checkpoint_89000.t7 -length 200
### Run model
Go to folder Frontend/build
launch public server :
$ python2 -m SimpleHTTPServer
Open Browser
localhost:8000
Launch api!
Go to folder Backend
$ python app.py
Markdown is supported
0% or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment