-
Notifications
You must be signed in to change notification settings - Fork 7.9k
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
关于Tablemaster模型的解码 #14283
Comments
Tablemaster模型的解码部分,特别是您提到的 1. 为什么需要减去
|
@flow3rdown 你是对的,是有bug。 |
用Tablemaster的原始训练权重推理的时候要去掉 w// 2,但是自己微调之后就不能加w // 2了,有点困惑。请问是Tablemaster原始模型在训练时候的数据集有什么特殊之处吗? |
模型的实现有变化,导致无法匹配上了。 |
请问这个问题好排查吗 |
切换到2.8.1试试 |
🔎 Search before asking
🐛 Bug (问题描述)
请教一下ppocr/postprocess/table_postprocess.py第184行x1和y1坐标为什么需要减去w //2呀?这样推理出的结果似乎会产生bbox漂移的问题,去掉之后是正常的。
PaddleOCR/ppocr/postprocess/table_postprocess.py
Lines 175 to 186 in c833dfc
🏃♂️ Environment (运行环境)
🌰 Minimal Reproducible Example (最小可复现问题的Demo)
The text was updated successfully, but these errors were encountered: