Tricks-of-Semi-supervisedDeepLeanring-Pytorch

Tricks-of-Semi-supervisedDeepLeanring-Pytorch copied to clipboard

Hi, thanks for sharing. I have been playing with FixMatch lately. Do you find eFixMatch perform better than iFixMatch? The comparison doesn't show up in the readme. Also, do you...

ElimsV

Hello, it's not that semi supervised learning like miamache can't be used on unbalanced data sets. I use it on my own data set. the test set accurate rises by...

ghost

FixMatch for single class

1

I try to apply FixMatch on one class data. For the unsupervised loss part, I modified the code like that. ``` self.uce_loss = torch.nn.BCEWithLogitsLoss(reduction='none') with torch.no_grad(): woutputs = self.model(weak_u) woutputs...

dendrobiumz

reimplement performance

1

it is a really nice work for semi-surpervised leaning. would you mind provide the performance of your code compared with paper performance?

valencebond

I found that there are bugs in the code, and the data in the dev set may be mixed in the test set ！

tony20086