Was wondering if anyone has crossed upon this problem:
Overall everything is working but for some images I get these invalid responses. Any clue would be appreciated.
Hello from Microsoft Cognitive Service Face Team,
And really sorry for the inconvenience cause by our current training strategy. AFAIK, it is still computation/time cost to train a person group, that is why we make it as an asynchronous call and need training again after the person group is modified.
If you have any further problem, please feel free to update.