Closed lizhenstat closed 5 years ago
Hi,
The clamp function here is to prevent numerical issues. Since the derivative of x^p is p*x^(p-1), when p < 1, it is essential to prevent x^(p-1) to be too big which introduces numerical unstable issues.
@ShichenLiu Oh! I got it, thanks a lot
Hi, I have a question on clap weights https://github.com/ShichenLiu/CondenseNet/blob/master/layers.py#L125
I don't understand the clamp function here. I tried to train condensenet-86 on cifar10 . with and without clamp functions with clamp: error rate = 95.06 without clamp: error rate = 94.96
Thanks in advance