AgreeableLandscape to Memes · edit-23 years agoBanana for Classificationimagemessage-square14fedilinkarrow-up139arrow-down11
arrow-up138arrow-down1imageBanana for ClassificationAgreeableLandscape to Memes · edit-23 years agomessage-square14fedilink
minus-squareabbenmlinkfedilinkarrow-up7·3 years agowonder if that AI was trained on anything in particular
minus-squareAgreeableLandscapeOPlinkfedilinkarrow-up2·3 years agoIn theory they could have used some public domain datasets or even parts of Wikimedia Commons.
minus-squareArthur BesseMAlinkfedilinkarrow-up3·3 years agoIt 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.
minus-squareArthur BesseMAlinkfedilinkarrow-up1·3 years agoblack and white photos of black and white photos, presumably.
wonder if that AI was trained on anything in particular
Time will tell
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.
black and white photos of black and white photos, presumably.