Torch模型导入

冻结param的3种方式

        for param in net.lstm.parameters():param.requires_grad = Truenet.lstm.requires_grad = True        # 无效net.lstm.state_dict()['weight_ih_l0'].requires_grad=Falsenet.lstm.weight_ih_l0.requires_grad = False# dir(net.lstm) to validate attributes of lstm module

optimizer