AgreeableLandscape@lemmy.ml to Memes@lemmy.ml · edit-23 years agoBanana for Classificationlemmy.mlimagemessage-square13fedilinkarrow-up126arrow-down12
arrow-up124arrow-down1imageBanana for Classificationlemmy.mlAgreeableLandscape@lemmy.ml to Memes@lemmy.ml · edit-23 years agomessage-square13fedilink
minus-squareArthur Besse@lemmy.mlMlinkfedilinkarrow-up4·3 years agoI uploaded this image to a caption generator AI and it says: a close up of a clock on a wall a black and white photo of a clock a close up of a clock on a building a black and white picture of a clock a close up of a clock on the wall a close up of a black and white clock a close up of a clock on the side of a building a black and white photo of a clock on a wall a black and white photo of a black and white clock a black and white photo of a black and white photo of a clock so… not bananas.
minus-squareabbenm@lemmy.mllinkfedilinkarrow-up3·3 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-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.
I uploaded this image to a caption generator AI and it says:
so… not bananas.
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.