SMASH
SMASH copied to clipboard
Accuracy only about 27% on CIFAR-100
Hi,
I like the idea very much, but I am wondering how this work is going since there have been no updates for 4 months.
I ran the 3 instructions twice mentioned in the readme, and achieved only 27.2% and 26.5% val error on CIFAR-100, substantially higher than the paper.
Is this because the default setting is incorrect, or the variance is huge due to randomness?
Thank you!
My train on cifar10 just could not reach 4.03%, I use test data and big op