Skip to content
Branch: master
Find file History
Fetching latest commit…
Cannot retrieve the latest commit at this time.
Type Name Latest commit message Commit time
Failed to load latest commit information.


Implementation for Convolutional Neural Networks for Sentence Classification of Kim (2014) with PyTorch and Torchtext.

Quick Start

To run the model on the Reuters dataset, just run the following from the working directory:

python -m models.kim_cnn --mode static --dataset Reuters --batch-size 32 --lr 0.01 --epochs 30 --dropout 0.5 --seed 3435

The best model weights will be saved in


To test the model, you can use the following command.

python -m models.kim_cnn --dataset Reuters --mode static --batch-size 32 --trained-model models/kim_cnn/saves/Reuters/ --seed 3435

Model Types

  • rand: All words are randomly initialized and then modified during training.
  • static: A model with pre-trained vectors from word2vec. All words, including the unknown ones that are initialized with zero, are kept static and only the other parameters of the model are learned.
  • non-static: Same as above but the pretrained vectors are fine-tuned for each task.
  • multichannel: A model with two sets of word vectors. Each set of vectors is treated as a 'channel' and each filter is applied to both channels, but gradients are back-propagated only through one of the channels. Hence the model is able to fine-tune one set of vectors while keeping the other static. Both channels are initialized with word2vec.


We experiment the model on the following datasets:

  • Reuters (ModApte)
  • AAPD
  • IMDB
  • Yelp 2014


Adam is used for training.

You can’t perform that action at this time.