That is the REAL question. I can't wait to see what comes of this.
Who is training a StyleGAN on this dataset?https://twitter.com/caseorganic/status/1352480295065317382 …
-
-
-
Umm. Maybe your future self (fingers crossed?)
End of conversation
New conversation -
-
-
The selfie filters of the near future will look like portraits of the past.
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
any good novelGAN?
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
I’ll definitely try and experiment with the dataset, looks like fun!
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
Don't you mean Dalle?
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
I'd prefer to train on a dataset that wasn't so obvious, like maybe 50,000 scraps of wrinkled paper.
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
Oh this should be fun. That’s my weekend taken care of! :)
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
I did a classifier some years ago with images I scraped from the Rijksmuseum. I found it hard to work with due to the extraordinary number of large frilly collars.
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
Will not converge unless you make a well-aligned thematic sub-selection.
-
See here: https://labs.brill.com/ictestset/ for the bees-knees of thematic selection.
End of conversation
New conversation -
Loading seems to be taking a while.
Twitter may be over capacity or experiencing a momentary hiccup. Try again or visit Twitter Status for more information.