TalRub104

Hi, In the paper, you mentioned that during training, you used a patch extraction stride of 16, and during fine-tuning, you used a stride of 8. From the GitHub, I...

Hi, Why aren't you using the following simple preprocessing for your training and validation? `test_transform = trn.Compose( [trn.Resize(256), trn.CenterCrop(224), trn.ToTensor(), trn.Normalize(mean, std)] )` The code is taken from: https://github.com/hendrycks/natural-adv-examples/blob/master/eval.py

--dataset torch/CIFAR10

1

Hi, After downloading the CIFAR-10 dataset using the following command: python3 -c "from torchvision.datasets import CIFAR10; CIFAR10(CIFAR10, download=True)" I attempted to run the following command to fine-tune on CIFAR-10: python...

Hi, It appears that your code doesn't support preparing the standard ImageNet dataset as the test data. Could you please add the relevant code to support it for those of...

Hi, I was wondering how much time it would take to train MiniGPT-4 through its two training stages, assuming I use 4 A100 GPUs for the first stage and 1...

Hi, Could you please provide more information about your scripts? For instance, if I want to train or fine-tune one of the models you used with a robustness improvement method...