Skip to content

Train_TransE 训练样本量过大会导致 Segmentation fault,怎么解决? #93

Open
@SHK92

Description

我用自己的数据生成的train.txt, entity2id.txt 和 relation2id.txt。train的样本量在1000w级。会报错。train.txt抽一个和FB15k中train.txt样本量相当的sample,是可以正常跑出结果的。但是数据量上去就不得行了。

Metadata

Assignees

No one assigned

    Labels

    No labels
    No labels

    Type

    No type

    Projects

    No projects

    Milestone

    No milestone

    Relationships

    None yet

    Development

    No branches or pull requests

    Issue actions