FADA-Pytorch icon indicating copy to clipboard operation
FADA-Pytorch copied to clipboard

pytorch implement for the paper Few-Shot Adversarial Domain Adaptation

Results 4 FADA-Pytorch issues
Sort by recently updated
recently updated
newest added

loss_sum = loss_X1 + loss_X2 + 0.2 * loss_dcd The coefficient of loss_dcd is -0.2, is that right ?

我想请问一下作者 我按照论文里的实验设置来跑mnist--->svhn 平均结果都比论文的低 有的低3点多 有的低差不多6个百分点 跑svhn--->mnist的时候 低一半多 想请问您一下 是什么问题呢

I try "loss_sum = loss_X1 + loss_X2", instead of "loss_sum = loss_X1 + loss_X2 + 0.2 * loss_dcd", and got better performence. I don't know why?

Bumps [scipy](https://github.com/scipy/scipy) from 1.3.0 to 1.10.0. Release notes Sourced from scipy's releases. SciPy 1.10.0 Release Notes SciPy 1.10.0 is the culmination of 6 months of hard work. It contains many...

dependencies