fixmatch
fixmatch copied to clipboard
commands to reproduce results in the paper
Hi can you provide the commands (like you did in MixMatch repo, the runs/ folder) to reproduce the results in the paper?
Thanks a lot! and thanks for the great work!
I wonder the same. I executed the FixMatch algorithm for CIFAR-10, yet the results are overfitting. If you provide specific commands and hyperparameter settings for acquiring same results in such datasets, it would be great. Thanks for the outstanding work and making such work public!