Getting this error when picking a image #17539
Description
🔎 Search before asking
- I have searched the PaddleOCR Docs and found no similar bug report.
- I have searched the PaddleOCR Issues and found no similar bug report.
- I have searched the PaddleOCR Discussions and found no similar bug report.
🐛 Bug (问题描述)
I`m using it for OCR on korean manhwas. OCR gets done by PaddleOCR and gets sent to the AI model as text to get translated. Getting a error like this: I0123 10:21:47.322901 16792 onednn_context.cc:81] oneDNN v3.6.2
🔥 Error: (Unimplemented) ConvertPirAttribute2RuntimeAttribute not support [pir::ArrayAttributepir::DoubleAttribute] (at ..\paddle\fluid\framework\new_executor\instruction\onednn\onednn_instruction.cc:118)
🏃♂️ Environment (运行环境)
Windows 10
Python 3.10.11
RX 590 8 GB
16 GB RAM
Ryzen 5 5600
Using Vulkan
Using manga_server.py provided below
Using Manga Translator extension for Firefox below
🌰 Minimal Reproducible Example (最小可复现问题的Demo)
Getting the error using it with my Firefox add-on. When I pick an area of a korean manhwa text like image it gives the error: I0123 10:21:47.322901 16792 onednn_context.cc:81] oneDNN v3.6.2
🔥 Error: (Unimplemented) ConvertPirAttribute2RuntimeAttribute not support [pir::ArrayAttributepir::DoubleAttribute] (at ..\paddle\fluid\framework\new_executor\instruction\onednn\onednn_instruction.cc:118)