Skip to content

An implementation of Skip-Thought Vectors in PyTorch

License

Notifications You must be signed in to change notification settings

katyakuda/skip-thoughts

 
 

Repository files navigation

skip-thoughts

An implementation of Skip-Thought Vectors in PyTorch.

Blog

Here's a blog explaining the subtleties of Skip-Thoughts blog blog

Instructions

Training

  • Download BookCorpus or any other data-set and concatenate all sentences into one file and put it in ./data/ directory
  • Modify the following line in Train.ipynb notebook accordingly: d = DataLoader("./data/dummy_corpus.txt")
  • There is no early stopping.
  • The Train notebook runs at the rate of 1 epoch / 2 days on an Nvidia 1080 Ti.
  • Your model is saved when ./saved_models when the average training loss in the last 20 iterations dips below the previous best.

Evaluation

Only implemented on classification tasks

  • Download the movie review dataset and put rt-polarity.neg and rt-polarity.pos in the ./tasks/mr_data directory.
  • You may also test on other classification tasks by downloading the datasets and providing their path and tasks type in Evaluate.ipynb

About

An implementation of Skip-Thought Vectors in PyTorch

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages

  • Python 71.9%
  • Jupyter Notebook 28.1%