微调表格识别模型SLANet plus，加入自己标注的无线表数据集，随着数据量越多，在验证集上的accuracy越低 #14477
Unanswered
Sherryran08
asked this question in
Q&A
Replies: 1 comment 1 reply
-
|
请教下解决了嘛 |
Beta Was this translation helpful? Give feedback.
1 reply
-
|
没有，效果还是很差，不知道是不是参数没调好 |
Beta Was this translation helpful? Give feedback.
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Uh oh!
There was an error while loading. Please reload this page.
-
加入了自己构建的800张表格识别训练数据集，随着数据量增加，在验证集上best accuracy降低，在800张训练集上（大多都是无线表数据，主要想提升无线表识别能力）best accuracy只有0.68；epoch：60，lr：5e-4；，训来之后推理效果感觉还没有base模型效果好。
原始推理效果：
微调后推理效果：
Beta Was this translation helpful? Give feedback.
All reactions