jc-leehub / recommend-system-tf2.0 Goto Github PK
View Code? Open in Web Editor NEW原理解析及代码实战，推荐算法也可以很简单 🔥 想要系统的学习推荐算法的小伙伴，欢迎 Star 或者 Fork 到自己仓库进行学习🚀 有任何疑问欢迎提 Issues，也可加文末的联系方式向我询问！
Home Page: https://github.com/jc-LeeHub/
recommend-system-tf2.0's People
Contributors
Stargazers
Watchers
Forkers
xiaming9880 yzflying finite-abelian mrfsc eva-ru lijianmin01 wangye8899 abc1239 sidingli wikiloa jamesbonddu farmerkb qingkongmengnuan williams-hao xvsfekcn yahooo-m hjh1213 sliu0614 zhangshuwenv charlie0215 yu3401 ikitkat zhangbo2008 cshaoping cheriseqianliu focusk stevenjokess greatestchili ewardyou fuxiang90 scievan ywan328 scflatex hailangzz pst2016 yssl0726 wallace-163 jetaimeh tongdechao10 fengxhao gshfly zhoulin0725 runner-yang xhfei1224 hzylf dailiangquan nsgjy 1427832045 uniquell qiruics huangdengrong mathlf2015 origami-og someintuition 3530204497 tiffen zhongwei8 shanllinjun hioneowner hq-cs neilliang90 heartbeatcode adminzhiyi wuhaotju jkzhang0000 jingever1230 lannycodes lemonskiller ahmat1914 myh286037565 yiming1012 soldierstone hgwu4869 allchen himiko14122 jma-code 245455758 luweicool oceangzy reborm minlee0202 yilinmaster cod11 darrenlei123 kzke ouykai nlp-zsy gl-coding homany xiaoxia0722 ddenglina disibutatian dachylong northtriorange twilight1223 genefeng hnbicycle jjb2021214976 mumukl xslxxfrecommend-system-tf2.0's Issues
xdeepfm 并没有用到categorical data
保存和加载模型
有试过怎么保存和加载模型吗 试过很多种方法都报错了 报错说是因为subclass。。。。。
DeepFm应该是实现错了
DeepFm里面的FM层应该把self.v参数去掉才对，这里面相当于对one-hot之后的embedding又做了一次embedding，换句话说这里不应该用原始完整的FM层。因为外面的embedding已经实现了FM里面的交叉矩阵。
如何进行model的存储
fm貌似实现的有问题
fm的k应该是对于每个特征都用一个k向量表示，而这个代码貌似是样本中所有特征的one-hot 然后concat一起，共同用一个k表示，这相当于是每个样本用一个k向量表示了，感觉有些问题
AUC and Accuracy
Recommend-System-tf2.0/FGCNN/train.py
Line 47 in 921da9f
print("AUC: ", accuracy_score(y_test, pre)) AUC不是这样计算的，这是计算accuracy。读取数据多的时候会oom
全量criteo数据集 十万条数据 40g内存都不够用
Wide&Deep 中wide侧和deep侧的输入问题
AFM的实现中特征交叉层只用了一部分的特征做特征交叉
您好，我看了AFM的实现代码，在layer.py中第70行将输入划分为dense_inputs和sparse_inputs，但是在后续的interaction_layer中只使用了sparse_inputs的embedding来做特征交叉，dense_inputs在后续的流程中完全没有用到，这里不是应该将dense_inputs和sparse_inputs的embedding都用来做特征交叉吗？
关于data
你好，可以共享一下data文件夹吗，或者提供一下data文件夹下载的百度或者谷歌地址
稀疏矩阵如果碰到新数据怎么处理
在create_criteo_dataset方法中，看到楼主对稀疏特征先采用label encoding的方法，这个情况如果后续碰到特征中新的label，应该要怎么处理呢？
楼主打算什么时候出多目标推荐算法？如esmm,mmoe,ple等
静等~~
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.