Vinci
Vinci
Thank you for you share, but when i run like below, i get result :acc1=0.00 acc5=0.00 ''python quantize.py --type cifar10 --quant_method linear --param_bits 16 --fwd_bits 16 --bn_bits 16 --gpu 0...
I am new to the field of adversarial attacks. I noticed that the natural accuracies of ResNet18 and ResNet50 in CIFAR10 are 78.38% and 79.15% respectively, which are much lower...
I am new to the field of adversarial attacks. I noticed that the natural accuracies of ResNet18 and ResNet50 in CIFAR10 are 78.38% and 79.15% respectively, which are much lower...
你好,我想问一下,ResNet18在位宽为4时top5精度已经下降了接近了2%了。那将数据位宽提高到6,或者8效果如何呢。谢谢!