Comments (7)
主要看你target的选择,如果是分类问题,dt的output会返回正负样本的的概率,你可以用来排序
from deeptables.
主要看你target的选择,如果是分类问题,dt的output会返回正负样本的的概率,你可以用来排序
DeepFM有三个网络('linear', 'fm_nets', 'dnn_nets'),但是输出为[[4.0071368e-01 5.9928632e-01], [9.9921107e-01 7.8889728e-04]]类似的矩阵,请问这个值是哪两个网络的输出?谢谢。
from deeptables.
主要看你target的选择,如果是分类问题,dt的output会返回正负样本的的概率,你可以用来排序
返回正负样本的概率用加权平均值还是逻辑回归映射到<0,1>区间,进行分数排序?选取最高进行topN排序
from deeptables.
输出的二维向量分别是0,1的概率。这是三个网络add之后的输出,具体网络架构方面可以参考DeepFM的paper https://arxiv.org/pdf/1804.04950.pdf
from deeptables.
输出的二维向量分别是0,1的概率。这是三个网络add之后的输出,具体网络架构方面可以参考DeepFM的paper https://arxiv.org/pdf/1804.04950.pdf
那简单的说做召回或者排序就是把值为1的概率最大的进行再排序,选择最大概率的input,进行TopN?
from deeptables.
可以这么使用
from deeptables.
输出的二维向量分别是0,1的概率。这是三个网络add之后的输出,具体网络架构方面可以参考DeepFM的paper https://arxiv.org/pdf/1804.04950.pdf
那简单的说做召回或者排序就是把值为1的概率最大的进行再排序,选择最大概率的input,进行TopN?
论文中看到了sigmoid的预测值函数,没有看到正负样本的输出?
from deeptables.
Related Issues (20)
- TypeError: import_optional_dependency() got an unexpected keyword argument 'errors' HOT 1
- DeepFM example: AttributeError: module 'sklearn.utils' has no attribute '_deprecate_positional_args' HOT 3
- complete the unit test
- Trained model is saved to '/tmp/workdir' HOT 1
- Adding tensorboard HOT 4
- Which model support "multiclass" task HOT 3
- Enable custom cv iterator HOT 2
- No module named 'woodwork.serialize' HOT 7
- How to use both AUCPR and AUC as metric for 'deeptable.fit' HOT 1
- Error on deeptables import on colab HOT 4
- 版本介绍 HOT 3
- 模型保存不了 HOT 3
- 模型保存路径有问题 HOT 3
- incremental learning
- 数值特征处理
- Deserialization of a DeepTables model with a custom objective fails
- ValueError: not enough values to unpack (expected 7, got 3) HOT 3
- Performance may be degraded by the initialization scheme
- Model cannot be saved HOT 4
- Deeptable model can not work after loading model 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 deeptables.