准循环神经网络 QRNN 提供了和 LSTM 相似的精度，但是基于使用实例可以比高度优化的 NVIDIA cuDNN LSTM 实现 2 到 17 倍快。
Quasi-Recurrent Neural Network (QRNN) for PyTorch
这个项目包含一个 PyTorch 实现的 Salesforce Research’s Quasi-Recurrent Neural Networks 论文.
This repository contains a PyTorch implementation of Salesforce Research’s Quasi-Recurrent Neural Networks paper.
The QRNN provides similar accuracy to the LSTM but can be betwen 2 and 17 times faster than the highly optimized NVIDIA cuDNN LSTM implementation depending on the use case.
To install, simply run:
pip install cupy pynvrtc git+https://github.com/salesforce/pytorch-qrnn
If you use this code or our results in your research, please cite:
@article{bradbury2016quasi,
title={{Quasi-Recurrent Neural Networks}},
author={Bradbury, James and Merity, Stephen and Xiong, Caiming and Socher, Richard},
journal={International Conference on Learning Representations (ICLR 2017)},
year={2017}
}
更多机器学习资源（微信群）：TensorFlow
