this post was submitted on 18 Jan 2022
25 points (93.1% liked)
Memes
45620 readers
1606 users here now
Rules:
- Be civil and nice.
- Try not to excessively repost, as a rule of thumb, wait at least 2 months to do it if you have to.
founded 5 years ago
MODERATORS
you are viewing a single comment's thread
view the rest of the comments
view the rest of the comments
In theory they could have used some public domain datasets or even parts of Wikimedia Commons.
It appears that the captioning model on that website was trained on the MSCOCO dataset which was sourced from from Google and Bing image search, and also from Flickr.