PaddleOCR
PaddleOCR copied to clipboard
PaddleOCR v2.2 导出的onnx模型c++推理与python推理结果差距
请提供下述完整信息以便快速定位问题/Please provide the following information to quickly locate the problem
- 系统环境/System Environment:Windows 10
- 版本号PaddleOCR:v2.2
- 问题相关组件/Related components:dbnet
将训练的DBNET检测模型利用脚本导出后,使用paddleocr 自带的python推理,结果与paddle模型一致,但是利用c++推理onnxruntime模型时候,推理的结果完全不一样,这里只对比了推理后的数据,后处理不涉及
做过的尝试:
- 控制输入的图片大小一致,以及一致的均值与方差
我也遇到这个问题了,你解决了吗?
我也遇到这个问题了,你解决了吗?
检查一下训练跟推理 图片的通道顺序
This issue has been automatically marked as stale because it has not had recent activity. It will be closed in 7 days if no further activity occurs. Thank you for your contributions.