AgreeableLandscape@lemmy.ml to Memes@lemmy.ml · edit-23 years agoBanana for Classificationlemmy.mlimagemessage-square14fedilinkarrow-up121arrow-down11
arrow-up120arrow-down1imageBanana for Classificationlemmy.mlAgreeableLandscape@lemmy.ml to Memes@lemmy.ml · edit-23 years agomessage-square14fedilink
minus-squareabbenm@lemmy.mllinkfedilinkarrow-up4·3 years agowonder if that AI was trained on anything in particular
minus-squareArthur Besse@lemmy.mlMlinkfedilinkarrow-up1·3 years agoblack and white photos of black and white photos, presumably.
minus-squareAgreeableLandscape@lemmy.mlOPlinkfedilinkarrow-up1·3 years agoIn theory they could have used some public domain datasets or even parts of Wikimedia Commons.
minus-squareArthur Besse@lemmy.mlMlinkfedilinkarrow-up2·3 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.
wonder if that AI was trained on anything in particular
Time will tell
black and white photos of black and white photos, presumably.
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.