A simple LSTM based Statement of Purpose Generator for grad school.
Branch: master
Clone or download
Fetching latest commit…
Cannot retrieve the latest commit at this time.
Permalink
Type Name Latest commit message Commit time
Failed to load latest commit information.
data/sop
.gitignore
Peek 2018-11-16 14-57.gif
README.md
data.py
generate.py
generated.txt
main.py
model.pt
model.py
requirements.txt

README.md

SOP-Generator

A simple LSTM based Statement of Purpose Generator for grad school. :)

Alt Text

Prerequisites

  • Pytorch 0.4
  • Python 2.x / 3.x

Generate

Generate samples from the trained model.

python generate.py --data ./data/sop/ --seed 6 # play with seed to get different text

Training

python main.py --cuda --epochs 500 --data data/sop/ --tied # Train a tied LSTM on SOP dataset with CUDA for 500 epochs

The model uses the nn.RNN module (and its sister modules nn.GRU and nn.LSTM) which will automatically use the cuDNN backend if run on CUDA with cuDNN installed.

During training, if a keyboard interrupt (Ctrl-C) is received, training is stopped and the current model is evaluated against the test dataset.

Contributors

Credits

pytorch/examples/tree/master/word_language_model