And I'm sure we will *still* see "we cannot afford an ImageNet experiment" in papers for years to come. The 3200$ publication fee and 2000$ conference travel are no problemo though.
And I'm sure we will *still* see "we cannot afford an ImageNet experiment" in papers for years to come. The 3200$ publication fee and 2000$ conference travel are no problemo though.
@giffmana Spoken like a googler who never has to worry about such things. :) There are multiple reasons imagenet is difficult, and I’ve wanted to reduce the barriers for a long time.
@theshawwn Yeah I don't blame you for thinking so, but I've also ran ImageNet on my single or dual GPU(s) in the uni lab back when it was GTX780 times, and gotten insights from it... and would do it again.
@giffmana You were also 23 and had infinite time. It’s an underrated advantage. Compare how hard it is to do that vs train a language model on some text. I fine tuned GPT 2 on some elisp on colab. Impossible for imagenet.