Closed Jasonlee1995 closed 7 months ago
Hi Jason! These are fantastic observations. A few points to note:
I have added the custom_resnet file in the code. Sorry for the oversight. It should be straightforward to swap the model to CustomResNet18 as well
The ResNet 18 code for this repo differs from the other example difficulty paper such as EL2N ResNet 18 or forgetting ResNet 18.
This repo used ResNet 18 from torchvision, which has 7x7 conv and maxpool in the stem.
Since this setting is not suitable for low-resolution image dataset such as CIFAR-10, changing the stem is common for measuring the generalization performance of CIFAR-10 and CIFAR-100.
From the
Appendix C
, I found that some of the results were driven by ResNet 18 model.I think the mismatch between the ResNet 18 model used for the experiments and real may have some potential issues, such as different results and also the analysis. (I also checked the ResNet 50, but I cannot find the custom_resnet python file)