Join GitHub today
GitHub is home to over 31 million developers working together to host and review code, manage projects, and build software together.Sign up
Entity recognition is inconsistent across runs #1336
I'm attempting some entity recognition, and the results keep changing for the same sentence when I reload the same model.
Sample run snapshot (verbatim)
I'm not sure, but this is unexpected given nothing really changes.
Info about spaCy
Something similar -
The current version on
There are two possible explanations for the inconsistency:
I think 2) is probably more likely. The good news is that the instability occurs also in the tensor values, not just in the parser or tagger. This means there's only a few places to look. It's probably the maxout or convolution functions.