Why the result with this implementation is better than reported one in the original paper?

kekmodel / FixMatch-pytorch

Unofficial PyTorch implementation of "FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidence"

MIT License

758 stars 170 forks source link

Open sooonwoo opened 3 years ago

sooonwoo commented 3 years ago

Hi, thanks for your impressive work!

It seems that we can get quite a lot better results with your implementation. Could you let me know what is the reason for the difference?

(Lb=40) 6.4% (Yours) | 13.81±3.37% (FixMatch(reported)) (Lb=20) 9% (Yours) | N/A. (FixMatch(reported))

kekmodel commented 2 years ago

I think it's weird, too. I think there is something wrong with my code.

lingjieyi commented 1 year ago

I think it's weird, too. I think there is something wrong with my code.

Did you only run seed=5? I got 85.24 by setting seed=1 and total_epoch = 512 running this code.