Computer Vision Update - July 2021

I can’t speak for others, but I would like to know when the next start date is simply so that I might get identification changes I am already planning on making into the next model so that they might be reflected by the next flowering season in 2022.

In the short term these changes will be taking misidentified specimens out of the research grade pool for one common, yet overidentified, species (roughly 150 out of 3300). About half of those will remain at genus level and the other half will be distributed among other species in the genus which typically have many fewer RG observations. Over time those may become RG observations in their new species as other identifiers react to the changes, but this may take a while and may not occur before the cutoff. Through these changes, one additional species might obtain the number of observations necessary to be included in the model, but it is borderline at this point and probably will have to wait through one more growing season.

If you do decide against releasing the cutoff date, then you could you at least announce when the new model run has started. At that point at least I might know if my changes made it in or if I can simply take my foot of the gas so to speak.

Thanks.

5 Likes

This topic was automatically closed 60 days after the last reply. New replies are no longer allowed.