knowledge-distillation-pytorch
knowledge-distillation-pytorch copied to clipboard
in mnist folder,why teacher_mnist and stdudent_mnist do not contain the softmax?
Hi @parquets, FYI, they add softmax when they compute the loss function, see kd loss here https://github.com/peterliht/knowledge-distillation-pytorch/blob/master/model/net.py#L110-L112
Hi @parquets, FYI, they add softmax when they compute the loss function, see kd loss here https://github.com/peterliht/knowledge-distillation-pytorch/blob/master/model/net.py#L110-L112
thank you, I get it
@peterliht Could you give me pre-trained model for ResNet110?