Differences between quant_layer.py about apot_quantization HOT 5 OPEN

Hi,

quant_layer.py in CIFAR10 is odder one. You are supposed to use ImageNet folder.
BTW, if you correctly migrate our code to MobileNetV2, you could merge to this branch!

Thanks.

from apot_quantization.

Thanks for your reply. I'll try~

from apot_quantization.

Hi,

quant_layer.py in CIFAR10 is odder one. You are supposed to use ImageNet folder.
BTW, if you correctly migrate our code to MobileNetV2, you could merge to this branch!

Thanks.

Hi,

I noticed that the difference between quant_layer.py is that the CIFAR10 one has backward path in the self-defined Pytorch function, but the ImageNet one doesn't. Does this mean that the Pytorch is strong enough to self-compute the backward gradient of RCF?

Thank you very much!

from apot_quantization.

yes, you are right.

from apot_quantization.

Thank you for your reply!

from apot_quantization.