search

google-research / fixmatch

A simple method to perform semi-supervised learning with limited data.
Apache License 2.0
1.1k stars 175 forks source link

Running fixmatch with RandAugment #19

Closed dsuess closed 4 years ago

dsuess commented 4 years ago

First of all, thanks for publishing the code for this paper -- it makes reproducing your work much easier.

I am trying to run fixmatch with RandAugment+Cutout instead of CTAugment (as it's much easier to implement in practice and the performance is often comparable). I've read #4 which states that fixmatch always uses CTAugment (additionally to what's provided in the --augment flag). So if I understand this correctly, --augment d.d.rac does not achieve what I want since CTAugment is always added on top? I suspect that's what's happening since I still see the CTAugment-weight printout when running training with that argument.

If that's the case, is there an easy way to disable CTAugment?

carlini commented 4 years ago

You can see the ablations for lots of examples on how we do these experiments, e.g.,

https://github.com/google-research/fixmatch/blob/master/ablation/ab_fixmatch_onlycutout.py

dsuess commented 4 years ago

Thanks, that folder contains everything I need