Alibaba-AAIG / Beyond-ImageNet-Attack

Beyond imagenet attack (accepted by ICLR 2022) towards crafting adversarial examples for black-box domains.
MIT License
58 stars 8 forks source link

cursor already registered in Tk_GetCursor Aborted (core dumped) #5

Closed hoonsyang closed 1 year ago

hoonsyang commented 1 year ago

python train.py --model_type vgg16 --RN False --DA False

I tried the above default training, but the error occurred at the end of the batch (epoch 1) training. Can you help debug this please?

qilong-zhang commented 1 year ago

@hoonsyang Hi, could you paste the full information of this error? I gauss this error is cause by the version of your torch (yours may be not the same as ours).

hoonsyang commented 1 year ago

@qilong-zhang Thanks for the reply The full information is on the title. BTW, I tried once again, and there's no error at the moment. I'll let you know if it occurs again. Thanks:)