Comments (15)
come-come
commented on July 23, 2024
1
同样问题+1 为什么呢？？
自己来解答一下： 需要对自己的数据进行特征归一化处理。（我的是因为没做归一化造成的）
from tensorflow-deepfm.
yn1166
commented on July 23, 2024
遇到了同样的问题，求大神帮忙
from tensorflow-deepfm.
ArriettyDouDou
commented on July 23, 2024
遇到了同样的问题，都预测成了1或0，auc是0.5。求帮忙
from tensorflow-deepfm.
a-bean-sprout
commented on July 23, 2024
遇到了同样的问题，都预测成了1或0，auc是0.5。求帮忙
不换数据，DeepFM模型AUC也才0.64左右，很奇怪。
from tensorflow-deepfm.
awonderfullife
commented on July 23, 2024
same problem
from tensorflow-deepfm.
726663676
commented on July 23, 2024
遇到了同样的问题，都预测成了1或0
from tensorflow-deepfm.
foreseez
commented on July 23, 2024
遇到了同样的问题，都预测成了1或0，auc是0.5。求帮忙
老哥你们的实验环境是怎么样的啊 我的是cuda10.0 tf1.14 不能运行成功 这上面也没说环境的安装这些。 你们运行成功了是吧
from tensorflow-deepfm.
come-come
commented on July 23, 2024
同样问题+1 为什么呢？？
from tensorflow-deepfm.
jinyryr
commented on July 23, 2024
遇到了同样的问题，困扰了好久没有思路
from tensorflow-deepfm.
jinyryr
commented on July 23, 2024
遇到了同样的问题，困扰了好久没有思路
问题解决了：需要对连续型特征进行标准化处理，否则模型参数学习失衡，导致最终结果受到影响
from tensorflow-deepfm.
LiuJP282
commented on July 23, 2024
遇到了同样的问题，都预测变成1或0，auc是0.5。求帮忙
不换数据，DeepFM模型AUC也才0.64左右，很奇怪。
我也是 ，兄弟你解决了吗 ？
from tensorflow-deepfm.
whk6688
commented on July 23, 2024
同样问题+1 为什么呢？？
自己来解答一下： 需要对自己的数据进行特征归一化处理。（我的是因为没做归一化造成的）
代码里不是自带归一化的处理吗，batch_norm_layer， 需要另外加归一化的逻辑吗？
from tensorflow-deepfm.
guotong1988
commented on July 23, 2024
THX
from tensorflow-deepfm.
washujiang
commented on July 23, 2024
对连续变量做极大极小值的归一化后，AUC从0.69变成了0.73，还是有效果的
from tensorflow-deepfm.
washujiang
commented on July 23, 2024
deepfm对异常值敏感吗
from tensorflow-deepfm.
Related Issues (20)
- 怎么将模型转换成pb文件呢？输出层和输入层是什么 HOT 1
- 为什么FM 侧y_first_order 里面没有增加一个单独的bias项, 只有关于feature权重的feature_bias
- 测试集为什么没有target，想xi,xv,ids就可以预测，损失怎么求得？
- 关于特征的处理问题
- question: can't multiply sequence by non-int of type 'float'
- from tensorflow.contrib.layers.python.layers import batch_norm as batch_norm
- fm输出的交叉特征个数不应该是 F*(F-1)/2吗？ HOT 1
- 使用criteo数据，精度到不了80% HOT 1
- 怎么获得example的数据集
- 120万数据提示内存不足
- 我小白，感觉这行代码挺有经验，motivation是？
- first order term 这里这个 求sum的操作 的意义是什么？ HOT 1
- 话说现在用TensorFlow分布式训练CTR模型怎么搞速度快啊？
- 话说CTR模型的交互类的特征是怎么做的和存储的？ HOT 1
- 数据在kaggle下载不了、需要注册账号，账号又注册不了，能把数据放上去吗？或者放到百度网盘也行
- In DeepFm.py line 102, why the second order term's size is (None, K) rather than (None, )? HOT 2
- tensor flow version HOT 2
- 算法如何调参
- 用的tenflow几
- 模型auc HOT 1
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.
from tensorflow-deepfm.