jacobgil/pytorch-pruning

Will the pruned weight reactivated after finetuning?

igo312 opened this issue · 0 comments

igo312 commented

@jacobgil I find there is no limits when using optimizer.step(). So the pruned weight will get a gradient and after stepping, it will be no longer 0 which means it cannot be regarded as pruned?

Am I right? Hope for your response!