Stu Blair
Stu Blair
related question, @DavidMChan , is the `Avg. Gradient Norm` printed to the log the same/analogous to KLD ?
Thanks for the explanation! That makes sense. So, just to confirm-- there's no way at all currently to see the KL/D value ?
I can confirm that v1.8.0 breaks with the new jQuery due to the self-closing tag issue, and that the issue is fixed in v1.8.1
Hey @gerlowskija, thanks for the suggestion! This is a promising idea, but can you first give more examples other than "GoT" where it would be useful?
Looks like it shouldn't be too difficult, according to Apple at least -- https://developer.apple.com/library/safari/documentation/UserExperience/Conceptual/SafariExtensionsConversionGuide/Chapters/Chrome.html However, such an endeavor is beyond what I have time to do myself anytime soon, so...
Hi @DavidMChan , I found reducing perplexity seems to help the visuals look more like they used to. However, this does not work consistently for all datasets, unlike tsne-cuda v2,...