An implementation of Skip-Thought Vectors in PyTorch.
- Download BookCorpus or any other data-set and concatenate all sentences into one file and put it in
- Modify the following line in
d = DataLoader("./data/dummy_corpus.txt")
- There is no early stopping.
Trainnotebook runs at the rate of 1 epoch / 2 days on an Nvidia 1080 Ti.
- Your model is saved when
./saved_modelswhen the average training loss in the last 20 iterations dips below the previous best.
Only implemented on classification tasks
- Download the movie review dataset and put
- You may also test on other classification tasks by downloading the datasets and providing their path and tasks type in