@TimG I believe convention is for the value of classvalue to start at 1, and not 0. I believe I've seen documentation to that effect, but I cannot find it at this moment. As a result of that, what you might be seeing is that your 0 class (if that is a legitimate value) is being combined or overwritten by NoData, because 0 is the conventional value for NoData. A NoData class should not show up in stats.txt, in my experience. When I ignore NoData, as you did, I do get the occasional pixel that comes up NoData (as you did in your reply), though there are significantly less of them than if I don't ignore NoData. I think Sandeep's suggestion of predict_background works better when the NoData class is still included, whereas I haven't seen much difference in the result of predict_background True vs False when NoData was ignored.
... View more
Re-creating this post: The URL is indeed encoded, but maybe not in the way you're thinking if you're trying to use 'decode' methods. This format is known as an encoded URL (see https://www.w3schools.com/html/html_urlencode.asp). I can't say if the changesUrl should be encoded, but I agree that the webhook payload includes an encoded URL. In Python, you can translate a URL-encoded string to a non-encoded URL via urllib.parse.unquote (https://docs.python.org/3/library/urllib.parse.html). EDIT: Carl pointed out that the requests library has similar functionality: requests.utils.unquote(url)
... View more