The performance of VAT algorithm is much lower.
LongLong-Jing opened this issue · 4 comments
Thanks for your implementation. I trained the VAT algorithm no the CIFAR10 datasets with the default parameters. However, it got 24.5% error rate on CIFAR10 dataset which is around 11% lower than the results that you reported in the table. Can I reproduce all the results in the table with default parameters?
Hi, LongLong-Jing!
All the results can be reproduced with default parameters.
You might have trained the model with CIFAR10 1k labels. (It means python build_dataset.py --dataset cifar10
)
Did you run python build_dataset.py --dataset cifar10 --nlabels 4000
and python train.py --dataset cifar10 --alg VAT
?
Hi @perrying,
Thanks for your very quick response. Yes. I checked the parameters and found that I used 1k labels. How many labeled images should I use to reproduce the results in the table?
You should use 4k labels for CIFAR10 and 1k labels for SVHN.
Thanks!