pytorch模型微调——不训练某些层的参数

code

  ### //不训练某些层
  frozen_layers = [net.cnn, net.rnn, net.layer0, net.layer0_1]
  for layer in frozen_layers:
    for name, value in layer.named_parameters():
      value.requires_grad = False
  params = filter(lambda p: p.requires_grad, net.parameters())

解释

通过net的named_parameters()属性进行遍历