Some of the models we put up have thousands of stars on GitHub and yet still no interface. You’d have to set up dependencies/etc and sometimes even write your own code, just for inference. Never understood why people who release state-of-the-art pretrained models don’t release a way to use or try them on a new input.
this is very cool! I have been reading about ml for a couple of years but have never played with it before. Really appreciate it! Shared with friends and family too :)
(I'm not a scientist/programmer)
So awesome to hear! If you have any feedback on how to make your experience better, would love to hear it. :)