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
This. One of my most popular tweets was an offhand remark on how to eek out an extra 0.1% on ImageNet, which I regarded as useless b/c ‘interesting problems’ are not Imagenet, but the tweet *exploded* in popularity, which I found puzzling. Then I realized: they were all Kagglers
Oh well that makes perfect sense! Do you have a favorite architecture for your interesting work?
I wish. It’s usually trial & error, w/ different components, activations, layers, losses, etc. Just released a paper today on further results with SignalTrain architecture! https://twitter.com/drscotthawley/status/1271064318768005121?s=21 …. Which, in humilty, this paper exposes the model’s limitations.
I will say: skip connections + 1cycle learning rate schedule = at least a factor of 10 for lowering loss / decreasing training time. :-)
Yes agreed on those being crucial. Generally there's so few things that seem to -actually- matter in practice. Training regime on the pretrained backbone (going beyond ImageNet 1K, namely) would be another I'd say I feel confident o being important.
Twitter may be over capacity or experiencing a momentary hiccup. Try again or visit Twitter Status for more information.
