alibaba / alibaba/euler

label反转?

Open
#125 2 comments 0 reactions 0 assignees View on GitHub
Dominant language
C++
Stars
2.9k
Forks
553
PR merge metrics
No merged PRs in 30d

Description

数据准备完成后,用feature_ops_test.py测试get_dense_feature,发现结果正常;
相同数据跑graphsage,在models/base.py下,打印下图对应inputs和labels,发现和实际图的完全相(实际0输出1,实际1输出0),想咨询这样是正常的吗?
![image](https://user-images.githubusercontent.com/18044452/60336492-115d7f00-99d3-11e9-8a52-c32e5bb5d00d.png)

对应的打印数据代码如下:
![image](https://user-images.githubusercontent.com/18044452/60336627-77e29d00-99d3-11e9-8fab-7c1d5bd1cbea.png)

对应的测试graph如下:

[data.zip](https://github.com/alibaba/euler/files/3338789/data.zip)

Contributor guide

No contributing guide indexed for this repository

Research direction

Reproduce the report using feature_ops_test.py, models/base.py, and the provided data.zip graph. Inspect the printed inputs and labels against the expected graph values, then determine whether the inversion is expected behavior or a defect and record the verified outcome.

Written by the indexing model from the issue text.

Assessment

Tech stack
cpp, python
Domain
machine-learning
Issue type
Bug
Difficulty
4/5
Estimated time
3-5 days
Activity status
Stale
Clarity
Needs clarification
Newbie friendliness
25/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.