Edoardo Debenedetti
Edoardo Debenedetti
Hi! I agree to add optional support for DataLoaders. I can open a PR and work on it
Moreover, in the reference implementation, as fas as I understood, they do get a random sample of size 1. So, shouldn't the batch size of `z_loader` be 1, to behave...
I think a good solution, I adopted and I am using, is creating a `DataLoader` with the same set as the `train_loader`, but with a RandomSampler of size `recursion_depth`. So...
Hi, thanks for the submission! We will add it as soon as possible
Hi @ruitian12! A small update: I have seen that you may be using a model from timm. Can you please confirm that the architectures you are using are indeed `deit_{small,base}_patch16_224`...
That's great, thanks for letting me know!
Hi @ruitian12 do you have unaggregated results as we do for the other models [here](https://github.com/RobustBench/robustbench/blob/master/model_info/imagenet/corruptions/unaggregated_results_2d.csv) and [here](https://github.com/RobustBench/robustbench/blob/master/model_info/imagenet/corruptions/unaggregated_results_3d.csv)?
Hi! Sorry for _my_ late reply, but I've been very busy recently. Thanks for the update, I will finalize the addition of your model ASAP!
Hi, do you need a model specifically? If this is the case, I can prioritize uploading it to GitHub as part of a release
Hi @ruitian12, I am sorry it's taking so long, but I realized there are some changes to do before integrating new corruptions models. Once #111 will be merged we will...