Just like the point of ML models is for them to work on unseen data, the point of publishing ML methods is for them to work on new datasets
Show this thread
So don't evaluate your techniques on just one dataset. Otherwise I will start suspecting that your method is specific to this one dataset
-
-
Would be cool to have a place where people can link papers, Github repos and benchmarks against different datasets.
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
Fork kernel ... - MNIST ... + Fashion MNIST
https://www.kaggle.com/mrisdal/capsulenet-on-fashion-mnist/notebook …Thanks. Twitter will use this to make your timeline better. UndoUndo
-
Loading seems to be taking a while.
Twitter may be over capacity or experiencing a momentary hiccup. Try again or visit Twitter Status for more information.