更新日志 - RapidOCR 文档 #278
Unanswered
Replies: 2 comments
-
您好博主, 我目前检测模型使用PPOCRv3训练的, 然后转化为onnx后,发现 未转化onnx的检测推理模型, 可以检测到图片, 转化到onnx后 检测不到文字了, 识别模型是基于PPOCRv4做的训练, 转化后精度没损失, 可以识别, |
Beta Was this translation helpful? Give feedback.
0 replies
-
怀疑模型转换误差太大了,建议debug转换前后误差,前提是保证输入相同,让相同数据进去原始模型和onnx模型,借助np.testing.assert函数来判断是否有误差。
|
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
-
更新日志 - RapidOCR 文档
Awesome OCR multiple programing languages toolkits based on ONNXRuntime, OpenVION and PaddlePaddle.
https://rapidai.github.io/RapidOCRDocs/install_usage/rapidocr_api/changelog/
Beta Was this translation helpful? Give feedback.
All reactions