alibaba / alibaba/euler

运行LsHNE 结果无法理解

Open
#137 0 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

执行 python -m tf_euler --data_dir ppi --max_id 56944 --model lshne --mode train

结果如下
![微信图片_20190725164518](https://user-images.githubusercontent.com/18165278/61859960-b8aed280-aefb-11e9-92c5-194dc24a90b0.png)

问题一: topological sort failed with message
问题二: loss一直没变,没有得到训练

能否给予解答呢?谢谢

Contributor guide

No contributing guide indexed for this repository

Research direction

Start by rerunning `python -m tf_euler --data_dir ppi --max_id 56944 --model lshne --mode train` and capture the complete output around the “topological sort failed” message. Trace the LSHNE training entry point and determine whether the unchanged loss is expected or indicates a failure; done means both reported behaviors are explained or reproduced with a clear fix path.

Written by the indexing model from the issue text.

Assessment

Tech stack
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.