zhujiesuper

Results 4 issues of zhujiesuper

def distillation(y, labels, teacher_scores, temp, alpha): print("teacher_scores",teacher_scores) return nn.KLDivLoss()(F.log_softmax(y / temp, dim=1), F.softmax(teacher_scores / temp, dim=1)) * ( temp * temp * 2.0 * alpha) + F.cross_entropy(y, labels) * (1....

help wanted
question