search

Jannoshh / simple-sam

Sharpness-Aware Minimization for Efficiently Improving Generalization
MIT License
41 stars 9 forks source link

Reproducing WRN-28-10 (SAM) for SVHN dataset #2

Closed akshaydp1995 closed 3 years ago

akshaydp1995 commented 3 years ago

I am trying to reproduce the results for WRN-28-10 (SAM) trained on 10-class classification SVHN dataset (Percentage Error 0.99) - https://paperswithcode.com/sota/image-classification-on-svhn

I'm able to train WRN-28-10 using https://github.com/hysts/pytorch_wrn (Modified the script to incorporate SAM into it)

I'm achieving a test accuracy of 93%. How can I replicate the SOTA Percentage Error 0.99 for WRN-28-10 (SAM). Which hyperparameters do I use?

Any help is appreciated!!

Jannoshh commented 3 years ago

As far as I can see the used hyperparameters are listed in Table 7 here: https://paperswithcode.com/paper/sharpness-aware-minimization-for-efficiently-1/review/?hl=21319