图像识别微调之后效果反而变差了 #3196

Open

Open

图像识别微调之后效果反而变差了#3196

chinesejunzai12

自有商品数据90w+, 目前使用的是general_PPLCNetV2_base_pretrained_v1.0.pdparams的基础上进行微调, 但是微调epoch为50轮之后, 评估结果f1值没有增加, 反而降低了, 大概得原因是什么?

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

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