Closed jnhwkim closed 4 years ago
Thanks for your interest. The details of the Stanford40 experiment are as follows.
meta_lr=1e-3
and meta_wd=1e-4
. Other parameters are same as other experiments, e.g., beta=0.5
and T=2
.Could you check the split ratio and hyperparameter setting as mentioned above?
I've successfully reproduced, though I got a bit higher variance. Thanks.
I am sincerely thankful for this shared code. I've really enjoyed the work.
While I try to reproduce your reported table, I faced an issue with the reproducibility for Stanford40-Actions (though I've confirmed CUB200, Dog and Indoor). It gives me around 53% compared to the reported score of 63.08%. Let me check with few details: 1) how do you split the training data with what percent (I tried 20% and 25%)? 2) Is there any change for hyper-parameters? (Adam optimizer for meta-networks has 1e-3 or 1e-4 learning rate? Or, the weight decay is 0 or 1e-4? (Appendix B) 3) Any other comment?
Thanks in advance.
Jin-Hwa