mirror of
https://github.com/wassname/Castor.git
synced 2026-10-07 11:13:23 +08:00
Michael Tu
09b3a790a2
* Add SICK torchtext Dataset * SICK dataset - torchtext postprocess into class probs * Update model, driver, trainer, evaluator for SICK for torchtext * MP-CNN: Fix bugs that prevent SICK from running on gpu 0 * MP-CNN: make SICK dataset w/ torchtext GPU-agnostic * MP-CNN: support sparse features / idf overlap with torchtext * Add MSRVID dataset with torchtext and update MP-CNN code to use it * MP-CNN: Make torchtext deterministic by setting python random seed * SICK and MSRVID datasets - add pair id for debug and build test vocab * MP-CNN: Update readme to address potential module not found error * MP-CNN: address review comments, can run on cpu
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.