https://github.com/qinyao-he/bit-rnn
Quantize weights and activations in Recurrent Neural Networks.
https://github.com/qinyao-he/bit-rnn
language-model lowbit-neural-network paper recurrent-neural-networks tensorflow
Last synced: 11 months ago
JSON representation
Quantize weights and activations in Recurrent Neural Networks.
- Host: GitHub
- URL: https://github.com/qinyao-he/bit-rnn
- Owner: qinyao-he
- License: apache-2.0
- Created: 2016-11-26T07:30:49.000Z (over 9 years ago)
- Default Branch: master
- Last Pushed: 2018-07-27T23:45:26.000Z (almost 8 years ago)
- Last Synced: 2025-04-06T08:11:32.606Z (about 1 year ago)
- Topics: language-model, lowbit-neural-network, paper, recurrent-neural-networks, tensorflow
- Language: Python
- Homepage: https://arxiv.org/abs/1611.10176
- Size: 25.4 KB
- Stars: 94
- Watchers: 8
- Forks: 30
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
README
# Bit-RNN
Source code for paper: [Effective Quantization Methods for Recurrent Neural Networks](https://arxiv.org/abs/1611.10176).
The implementation of PTB language model is modified from examples in [tensorflow](https://github.com/tensorflow/tensorflow/tree/master/tensorflow/models/rnn/ptb).
## Requirments
Currently tested and run on [TensorFlow](https://www.tensorflow.org) 1.8 and Python 3.6. View other branches for legacy support.
You may download the data from [http://www.fit.vutbr.cz/~imikolov/rnnlm/simple-examples.tgz](http://www.fit.vutbr.cz/~imikolov/rnnlm/simple-examples.tgz).
## Run
```
python train.py --config=config.gru --data_path=YOUR_DATA_PATH
```
Currently default is 2-bit weights and activations. You may edit the config file in config folder to change configuration.
## Support
Submit issue for problem relate to the code itself. Send email to the author for general question about the paper.
## Citation
Please cite follow if you use our code in your research:
```
@article{DBLP:journals/corr/HeWZWYZZ16,
author = {Qinyao He and
He Wen and
Shuchang Zhou and
Yuxin Wu and
Cong Yao and
Xinyu Zhou and
Yuheng Zou},
title = {Effective Quantization Methods for Recurrent Neural Networks},
journal = {CoRR},
volume = {abs/1611.10176},
year = {2016},
url = {http://arxiv.org/abs/1611.10176},
timestamp = {Thu, 01 Dec 2016 19:32:08 +0100},
biburl = {http://dblp.uni-trier.de/rec/bib/journals/corr/HeWZWYZZ16},
bibsource = {dblp computer science bibliography, http://dblp.org}
}
```