You can add location information to your Tweets, such as your city or precise location, from the web and via third-party applications. You always have the option to delete your Tweet location history. Learn more
In case anybody was wondering about how I monitor progress in DeOldify- I don’t pay a huge amount of attention to training/validation loss because they don’t actually capture a lot of the issues I wind up seeing (artifacts, uniformly black renders, etc).https://twitter.com/citnaj/status/1200854194002878464 …
And then I have both the Jupyter notebook “test” image suites and then a batch of 100s of more public domain images. It’s painful and tedious but using my eyes on these directly I’ve found is the only reliable way I have to measure progress. And even the you have to be extremely
careful about perception issues- you misremember stuff easily, and literally see things differently depending on context. So I don’t necessarily take a first go at it as the final say as to whether or not the model is great or not.
And yes this process drives me nuts and please tell me if there’s a better way lol
There isn’t a better way. Or if there is, I haven’t found it in like 8 years of graphics research. Even in the most rigorous academic circles, the test used in most cases is “show these images to a bunch of humans and see how many can spot differences.”
And as you say, the viewing conditions matter a lot. *Especially* for color. FWIW, I used an i1DisplayPro for calibrating my U2711 monitor. Back in 2012 that was pretty much top of the line calibration+monitor combo for digital work.
Twitter may be over capacity or experiencing a momentary hiccup. Try again or visit Twitter Status for more information.
