lostsartre/CF-NADE
Folders and files
| Name | Name | Last commit date | ||
|---|---|---|---|---|
Repository files navigation
//
// _oo0oo_
// o8888888o
// 88" . "88
// (| -_- |)
// 0\ = /0
// ___/`---'\___
// .' \\| |// '.
// / \\||| : |||// \
// / _||||| -:- |||||- \
// | | \\\ - /// | |
// | \_| ''\---/'' |_/ |
// \ .-\__ '-' ___/-. /
// ___'. .' /--.--\ `. .'___
// ."" '< `.___\_<|>_/___.' >' "".
// | | : `- \`.;`\ _ /`;.`/ - ` : | |
// \ \ `_. \_ __\ /__ _/ .-` / /
// =====`-.____`.___ \_____/___.-`___.-'=====
// `=---='
//
//
// ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
//
// 佛祖保佑 永无BUG
//
//
/*code is far away from bug with the animal protecting
* ┏┓ ┏┓
*┏┛┻━━━┛┻┓
*┃ ┃
*┃ ━ ┃
*┃ ┳┛ ┗┳ ┃
*┃ ┃
*┃ ┻ ┃
*┃ ┃
*┗━┓ ┏━┛
* ┃ ┃神兽保佑
* ┃ ┃代码无BUG!
* ┃ ┗━━━┓
* ┃ ┣┓
* ┃ ┏┛
* ┗┓┓┏━┳┓┏┛
* ┃┫┫ ┃┫┫
* ┗┻┛ ┗┻┛
*
*/
“”“
天灵灵,地灵灵,奉请祖师来显灵。
祖师我来拜一拜,倾听小弟内心音。
一请莱尊二进制,二请巴贝奇创雏形。
三请艾达写算法,四请诺依曼模式新。
五请阿兰俏图灵,六请里奇和汤普逊。
七请网络三鼻祖,八请盖茨比广进金。
九请理查推开源,十请林纳斯再更新。
最后再请BAT,保佑代码靓又金!
”“”
New implementation on code for "A Neural Autoregressive Approach to Collaborative Filtering", ICML 2016
See in /new_implement
Dependency:
You need to install:
Theano: http://deeplearning.net/software/theano/
blocks: http://blocks.readthedocs.io/en/latest/bricks_overview.html
version 0.1.1 is requred
In this code, you can use the code in "datasets" to generate a hdf5 dataset to feed CF-NADE.
Then you can run "learner_ordinalcost_directly_itembased_newsoftmax_timing.py" to train and
test CF-NADE.
And example to run the code is:
MovieLens1M=/Users/yin.zheng/ml_datasets/MovieLens1M-shuffle-itembased-0 python learner_ordinalcost_directly_itembased_newsoftmax_timing.py 512 10 60 0.001 0.1 0.001 1e-8 500 tanh 0 0.02 Adam 0 1 0.995 /tmp/cfnade
Releases
No releases published
Languages
- Python 59.3%
- Jupyter Notebook 40.7%