Replies: 3 comments 7 replies
-
请具体说明你这里用的哪个读光模型,有两个一个是有线表格识别,一个是无线表格识别,我懵逼中
ONNX模型已经提供了,pypi上的whl包里就有对应的ONNX模型的 |
Beta Was this translation helpful? Give feedback.
2 replies
-
问题1,我不太记得了。有些久远了。 如果你发现的确不一样,那可能会是改了。 |
Beta Was this translation helpful? Give feedback.
0 replies
-
raise TypeError("Unable to load from type '{0}'".format(type(path_or_bytes))) |
Beta Was this translation helpful? Give feedback.
5 replies
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
-
您好,我最近也在做表格的抽取,也是用的读光模型和paddlepaddl的ocr,但对复杂表格的支持还存在一些bad case,看到此仓库想测试一下效果。目前有一些疑问:
1.读光模型的output的polygons的size为[N, 8],如官网所示。
但是本仓库的里的code,对polygons的取值方式为:
polygons[:, 0, 1]
想问格式是改掉了吗?
2.另外,转为onnx后的模型会提供吗?
Beta Was this translation helpful? Give feedback.
All reactions