Paddle OCR 推理模型转ONNX,固定shape后,ONNX结果相差很大,不固定shape,结果与paddle推理模型保持一致,这个问题要怎么处理哇: #13107
Unanswered
xiaoxianyu12
asked this question in
Q&A
Replies: 2 comments
-
动态shape效果更好 |
Beta Was this translation helpful? Give feedback.
0 replies
-
PaddleOCR中文本检测模型输入固定shape,会导致一些文字变形,推理结果自然更差一些 |
Beta Was this translation helpful? Give feedback.
0 replies
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.
-
问题描述 / Problem Description
请在此处详细的描述报错信息
Paddle OCR 推理模型转ONNX,固定shape后,ONNX结果相差很大,不固定shape,结果与paddle推理模型保持一致,这个问题要怎么处理哇:
尝试了2种方法:
①先将paddle推理模型的动态shape转为固定shape,再转成ONNX;
②先将paddle推理模型转为ONNX,此时ONNX模型为动态shape,再使用paddle2onnx.optimize将ONNX动态shape改为固定shape
这两种方法得到的固定shape的ONNX结果都和动态shape的结果有差异,请问这个怎么解决,怎么能够让Paddle OCR的模型转为固定shape的ONNX并且结果保持一致
运行环境 / Runtime Environment
复现代码 / Reproduction Code
完整报错 / Complete Error Message
可能解决方案 / Possible solutions
附件 / Appendix
Beta Was this translation helpful? Give feedback.
All reactions