PyTorch-NLP - Supporting Rapid Prototyping with a Toolkit (incl. Datasets and Neural Network Layers)

•    Python

---

PyTorch-NLP, or torchnlp for short, is a library of neural network layers, text processing modules and datasets designed to accelerate Natural Language Processing (NLP) research. Join our community, add datasets and neural network layers! Chat with us on Gitter and join the Google Group, we're eager to collaborate with you.

pytorch nlp natural-language-processing pytorch-nlp torchnlp data-loader embeddings word-vectors deep-learning dataset metrics neural-network sru machine-learning

KB-python-API - Python API for KB data-services

•    Python

---

KB-Python-API is a simple API for Python, the API provides easy access to free and CC-BY-NC-ND datasets provided by the National Library of the Netherlands (KB). It relies on the back-end infrastructure of the KB which consists of an SRU and OAI-MPH service. The KB Python API makes it easy to interact with historical data, for more information on the provided datasets and data-rights take a look at the DataServices page of the KB.

api search oai-pmh sru code4lib

keras-SRU - Implementation of Simple Recurrent Unit in Keras

•    Python

---

No longer a problem to have different input dimension than output dimension. Performance degrades substantially with larger batch sizes (about 6-7% on average over 5 runs) compared to 1 layer LSTM with batch size of 128. However, a multi layer SRU (I've tried with 3 layers), while a bit slower than a 1 layer LSTM, gets around the same score on batch size of 32 or 128.

keras sru recurrent-neural-networks