loss is nan #1

Open

wangyingshuai111

opened

on Feb 20, 2019

楼主，您好，我的训练数据特征比较稀疏，有好多0，训练loss一直为nan，请问有什么解决办法么？
非常期待您的回答

to join this conversation on GitHub. Already have an account? Sign in to comment

Metadata

Assignees

No one assigned

Labels

No labels

No labels

Projects

No projects

Milestone

No milestone

Relationships

None yet

Development

No branches or pull requests