Souvik Kundu

This is the command we are using: python -m torch.distributed.launch --nproc_per_node=8 --master_port=12349 --use_env main_adv_deit.py --model deit_tiny_patch16_224_adv --batch-size=128 --data-path /datasets/imagenet-ilsvrc2012 --attack-iter 1 --attack-epsilon 4 --attack-step-size 4 --epoch 100 --reprob 0 --no-repeated-aug...

Okay, I will try with diet_small...have never tried yet.

Yes, I never tried with 8 gpu node for deit small. Trying now. So, the goal is to narrow down whether its model specific?

One reason to choose deit_tiny is to see the results quickly, as the deit_small takes little longer to train. unfortunately it is not working yet.

Can you let me know what arguments you used to tone down augmentation on diet tiny to make it work?

Running on deit_small, will let you know the results...its around 2x slower than deit_tiny, so will be little late.

Hi, I am facing issues with the Resnet50 model training on CIFAR-10. Even with lr of 0.01 it's throwing Nan after around 10 epochs (suddenly), so, I am not quite...

yes, this is too costly and slow to replace Convs.

Hi Nitin, RESNET_SNN_STDB class is missing in the spiking models file. Can you include that in the file?