mirror of
https://github.com/wassname/Castor.git
synced 2026-10-29 12:40:22 +08:00
Victor Yang
51d8e29525
* update nce-sm * refactor code, update torchtext * use shared evaluation * refactor code, use shared data loader * refactor code * refactor code * refactor code according to Michael's great suggestions * update readme and requirement * update datasets and readme * update data loader * add space between + * update refactor code * add nce-mp * remove duplicate files * update readme, refactor code according to mp_cnn and delete duplicate code, follow PEP8 standard * refactor code, add/delete comments * import exit from sys
Castor
PyTorch deep learning models.
- SM model: Similarity between question and candidate answers.
Setting up PyTorch
You need Python 3.6 to use the models in this repository.
As per pytorch.org,
"Anaconda is our recommended package manager"
conda install pytorch torchvision -c soumith
Other pytorch installation modalities (e.g. via pip) can be seen at pytorch.org.
We also recommend gensim. We use some gensim modules to cache word embeddings.
conda install gensim
PyTorch has good support for GPU computations. CUDA installation guide for linux can be found here
NOTE: Install CUDA libraries before installing conda and pytorch.
data for models
Sourcing and pre-processing of input data for each model is described in respective model/README.md's
Baselines
- IDF Baseline: IDF overlap between question and candidate answers.
Tutorials
SM Model tutorial: sm_cnn/tutorial.ipynb - notebook that walks through SM CNN model, good for beginnners.