You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Sorry if this has been discussed before, I haven't found anything related though.
I have a relatively huge local and growing photo collection, main focus on lepidoptera
I use digikam for photo management and the inaturalist api, including object detection works fairly well.
Most of the photos are already tagged (manually over the years), but I'd love to have some feature, using a local llm
which would allow an automagic tagging of my future pictures.
I've found this llm, which was trained using local data from Singapore,
so I wondered if you considered offering "more official" llms for offline use trained from your data collection.
Maybe even "topic" specific to keep the vram requirement low (apparently I wouldn't mind a specific lepidoptera model ;))
I'm eager to receive your reply.
Please keep up your great work with inaturalist!
The text was updated successfully, but these errors were encountered:
Hello,
Sorry if this has been discussed before, I haven't found anything related though.
I have a relatively huge local and growing photo collection, main focus on lepidoptera
I use digikam for photo management and the inaturalist api, including object detection works fairly well.
Most of the photos are already tagged (manually over the years), but I'd love to have some feature, using a local llm
which would allow an automagic tagging of my future pictures.
I've found this llm, which was trained using local data from Singapore,
so I wondered if you considered offering "more official" llms for offline use trained from your data collection.
Maybe even "topic" specific to keep the vram requirement low (apparently I wouldn't mind a specific lepidoptera model ;))
I'm eager to receive your reply.
Please keep up your great work with inaturalist!
The text was updated successfully, but these errors were encountered: