free_adv_train

free_adv_train copied to clipboard

Thanks for your work, it helps me a lot. I notice the delta in your algorithm is gradually accumulate. but that in 《Towards Deep Learning Models Resistant to Adversarial》 is...

ghost

I would really appreciate if you would share the trained robust cifar10 model. Despite the adversarial training is "free", it still requires 10+ GPU hours. Thank you so much!

Shawn-Shan

Thanks for your great work. I notice the training script mainfree.py of Pytorch version does not support multi-gpus training. Is there any technical issue?

iminfine

Hi, @ashafahi , thanks for your implementation, when evaluating your model during training, it seems like you did not switch off the batch norm, will that cause some difference in...

d12306

Why do you trained a model build from scratch instead of fine-tuning a pretrained model？

1

Hi， I notice that you did not use a pretrained model. Is it too hard to train? Or is its performation not good? Thanks.

Sumching

Bumps [tqdm](https://github.com/tqdm/tqdm) from 4.31.1 to 4.66.3. Release notes Sourced from tqdm's releases. tqdm v4.66.3 stable cli: eval safety (fixes CVE-2024-34062, GHSA-g7vv-2v7x-gj9p) tqdm v4.66.2 stable pandas: add DataFrame.progress_map (#1549) notebook: fix...

dependabot[bot]