Open chenbinghui1 opened 2 years ago
In the demo, MaxNorm is applied in each epoch as you said. This corresponds to lines 140-142 in trainval.py.
You can move this code up in order to apply it per-iteration as in the paper. I will update the shared open-source code soon. Thank you!
Looks like there is a significant difference in performance between the two. Resnet34. Benchmarked with the code provided.
@ShadeAlsha @chenbinghui1
Yes, PGD is supposed to be applied in each iteration as in page 4 of the paper and as chenbinghui1 mentioned earlier :) I haven't updated the code yet, but in the mean time your modified version should be good if you just moved PGD to the iteration loop. Thanks for your interest!
Hello, I would like to ask, when I used the author's source code to fine-tune, how is it that the addition and removal of maximum regularization are the same? Does it seem to not work?
In paper, it claims that Maxnorm regularization is applied per iteration, but in the code, it seems to be applied per epoch? Am i right?