hpca. C++ implementation of the Hellinger PCA for computing word embeddings.
32phrase-based_image_captioning. Torch implementation of ICML 2015 paper about image captioning
9wikipedia-biography-dataset. This dataset gathers 728,321 biographies from wikipedia. It aims at evaluating text generation algorithms. For each article, we provide the first paragraph and the infobox (both tokenized).
4PyTorch-Project-Template. A best practice for pytorch project template architecture.
2lt3d. LookupTable allowing to forward n sequence of word
1mlsm. Parallel implementation of LogSoftMax
1