JIANG Yichen

Hi, is there any updates for this issue? Will it be fixed, or any walk around?

Same issue. It seems a legacy [issue](https://github.com/FreeOpcUa/python-opcua/issues/803) from the sync version. I am looking forward to the fix plan.

Sorry, is this the same issue with [the sync version](https://github.com/FreeOpcUa/python-opcua/issues/803)? The sync one looks very complicated and can cause severe result based on the implementation of client.

Yes, the computation of binary_crossentropy will lead to the output result different from that when the categorical_crossentropy used. It seems to me both will be okay for the detect-and-classify case,...

By the way, I also have another PR #315 about voc2012.py when I test for this issue.

> I ran into the same problem with score The problem is not the classification loss, but the way the score is calculated > > If we only have one...